Predicting the Outcome of NBA Playoffs Based on the Maximum Entropy Principle

Directory of Open Access Journals (Sweden)

Ge Cheng

2016-12-01

Full Text Available Predicting the outcome of National Basketball Association (NBA matches poses a challenging problem of interest to the research community as well as the general public. In this article, we formalize the problem of predicting NBA game results as a classification problem and apply the principle of Maximum Entropy to construct an NBA Maximum Entropy (NBAME model that fits to discrete statistics for NBA games, and then predict the outcomes of NBA playoffs using the model. Our results reveal that the model is able to predict the winning team with 74.4% accuracy, outperforming other classical machine learning algorithms that could only afford a maximum prediction accuracy of 70.6% in the experiments that we performed.

Predicting the Outcome of NBA Playoffs Based on the Maximum Entropy Principle

OpenAIRE

Ge Cheng; Zhenyu Zhang; Moses Ntanda Kyebambe; Nasser Kimbugwe

2016-01-01

Predicting the outcome of National Basketball Association (NBA) matches poses a challenging problem of interest to the research community as well as the general public. In this article, we formalize the problem of predicting NBA game results as a classification problem and apply the principle of Maximum Entropy to construct an NBA Maximum Entropy (NBAME) model that fits to discrete statistics for NBA games, and then predict the outcomes of NBA playoffs using the model. Our results reveal that...

Predictive modeling of complications.

Science.gov (United States)

Osorio, Joseph A; Scheer, Justin K; Ames, Christopher P

2016-09-01

Predictive analytic algorithms are designed to identify patterns in the data that allow for accurate predictions without the need for a hypothesis. Therefore, predictive modeling can provide detailed and patient-specific information that can be readily applied when discussing the risks of surgery with a patient. There are few studies using predictive modeling techniques in the adult spine surgery literature. These types of studies represent the beginning of the use of predictive analytics in spine surgery outcomes. We will discuss the advancements in the field of spine surgery with respect to predictive analytics, the controversies surrounding the technique, and the future directions.

Predicting outcome of status epilepticus.

Science.gov (United States)

Leitinger, M; Kalss, G; Rohracher, A; Pilz, G; Novak, H; Höfler, J; Deak, I; Kuchukhidze, G; Dobesberger, J; Wakonig, A; Trinka, E

2015-08-01

Status epilepticus (SE) is a frequent neurological emergency complicated by high mortality and often poor functional outcome in survivors. The aim of this study was to review available clinical scores to predict outcome. Literature review. PubMed Search terms were "score", "outcome", and "status epilepticus" (April 9th 2015). Publications with abstracts available in English, no other language restrictions, or any restrictions concerning investigated patients were included. Two scores were identified: "Status Epilepticus Severity Score--STESS" and "Epidemiology based Mortality score in SE--EMSE". A comprehensive comparison of test parameters concerning performance, options, and limitations was performed. Epidemiology based Mortality score in SE allows detailed individualization of risk factors and is significantly superior to STESS in a retrospective explorative study. In particular, EMSE is very good at detection of good and bad outcome, whereas STESS detecting bad outcome is limited by a ceiling effect and uncertainty of correct cutoff value. Epidemiology based Mortality score in SE can be adapted to different regions in the world and to advances in medicine, as new data emerge. In addition, we designed a reporting standard for status epilepticus to enhance acquisition and communication of outcome relevant data. A data acquisition sheet used from patient admission in emergency room, from the EEG lab to intensive care unit, is provided for optimized data collection. Status Epilepticus Severity Score is easy to perform and predicts bad outcome, but has a low predictive value for good outcomes. Epidemiology based Mortality score in SE is superior to STESS in predicting good or bad outcome but needs marginally more time to perform. Epidemiology based Mortality score in SE may prove very useful for risk stratification in interventional studies and is recommended for individual outcome prediction. Prospective validation in different cohorts is needed for EMSE, whereas

Comparison of Physician-Predicted to Measured Low Vision Outcomes

Science.gov (United States)

Chan, Tiffany L.; Goldstein, Judith E.; Massof, Robert W.

2013-01-01

Purpose To compare low vision rehabilitation (LVR) physicians’ predictions of the probability of success of LVR to patients’ self-reported outcomes after provision of usual outpatient LVR services; and to determine if patients’ traits influence physician ratings. Methods The Activity Inventory (AI), a self-report visual function questionnaire, was administered pre and post-LVR to 316 low vision patients served by 28 LVR centers that participated in a collaborative observational study. The physical component of the Short Form-36, Geriatric Depression Scale, and Telephone Interview for Cognitive Status were also administered pre-LVR to measure physical capability, depression and cognitive status. Following patient evaluation, 38 LVR physicians estimated the probability of outcome success (POS), using their own criteria. The POS ratings and change in functional ability were used to assess the effects of patients’ baseline traits on predicted outcomes. Results A regression analysis with a hierarchical random effects model showed no relationship between LVR physician POS estimates and AI-based outcomes. In another analysis, Kappa statistics were calculated to determine the probability of agreement between POS and AI-based outcomes for different outcome criteria. Across all comparisons, none of the kappa values were significantly different from 0, which indicates the rate of agreement is equivalent to chance. In an exploratory analysis, hierarchical mixed effects regression models show that POS ratings are associated with information about the patient’s cognitive functioning and the combination of visual acuity and functional ability, as opposed to visual acuity or functional ability alone. Conclusions Physicians’ predictions of LVR outcomes appear to be influenced by knowledge of patients’ cognitive functioning and the combination of visual acuity and functional ability - information physicians acquire from the patient’s history and examination. However

Chronic Kidney Disease – Where Next? Predicting Outcomes and Planning Care Pathways

Directory of Open Access Journals (Sweden)

Angharad Marks

2014-07-01

Full Text Available With the introduction of the National Kidney Foundation Kidney Disease Outcomes Quality Initiative chronic kidney disease (CKD guidelines, CKD has been identified as common, particularly in the elderly. The outcomes for those with CKD can be poor: mortality, initiation of renal replacement therapy, and progressive deterioration in kidney function, with its associated complications. In young people with CKD, the risk of poor outcome is high and the social cost substantial, but the actual number of patients affected is relatively small. In the elderly, the risk of poor outcome is substantially lower, but due to the high prevalence of CKD the actual number of poor outcomes attributable to CKD is higher. Predicting which patients are at greatest risk, and being able to tailor care appropriately, has significant potential benefits. Risk prediction models in CKD are being developed and show promise but thus far have limitations. In this review we describe the pathway for developing and evaluating risk prediction tools, and consider what models we have for CKD prediction and where next.

A predictive model for pressure ulcer outcome: the Wound Healing Index.

Science.gov (United States)

Horn, Susan D; Barrett, Ryan S; Fife, Caroline E; Thomson, Brett

2015-12-01

The purpose of this learning activity is to provide information regarding the creation of a risk-stratification system to predict the likelihood of the healing of body and heel pressure ulcers (PrUs). This continuing education activity is intended for physicians and nurses with an interest in skin and wound care. After participating in this educational activity, the participant should be better able to:1. Explain the need for a PrU risk stratification tool.2. Describe the purpose and methodology of the study.3. Delineate the results of the study and development of the Wound Healing Index. : To create a validated system to predict the healing likelihood of patients with body and heel pressure ulcers (PrUs), incorporating only patient- and wound-specific variables. The US Wound Registry data were examined retrospectively and assigned a clear outcome (healed, amputated, and so on). Significant variables were identified with bivariate analyses. Multivariable logistic regression models were created based on significant factors (P wound clinics in 24 states : A total of 7973 body PrUs and 2350 heel PrUs were eligible for analysis. Not applicable : Healed PrU MAIN RESULTS:: Because of missing data elements, the logistic regression development model included 6640 body PrUs, of which 4300 healed (64.8%), and the 10% validation sample included 709 PrUs, of which 477 healed (67.3%). For heel PrUs, the logistic regression development model included 1909 heel PrUs, of which 1240 healed (65.0%), and the 10% validation sample included 203 PrUs, of which 133 healed (65.5%). Variables significantly predicting healing were PrU size, PrU age, number of concurrent wounds of any etiology, PrU Stage III or IV, evidence of bioburden/infection, patient age, being nonambulatory, having renal transplant, paralysis, malnutrition, and/or patient hospitalization for any reason. Body and heel PrU Wound Healing Indices are comprehensive, user-friendly, and validated predictive models for

Predicting radiotherapy outcomes using statistical learning techniques

International Nuclear Information System (INIS)

El Naqa, Issam; Bradley, Jeffrey D; Deasy, Joseph O; Lindsay, Patricia E; Hope, Andrew J

2009-01-01

Radiotherapy outcomes are determined by complex interactions between treatment, anatomical and patient-related variables. A common obstacle to building maximally predictive outcome models for clinical practice is the failure to capture potential complexity of heterogeneous variable interactions and applicability beyond institutional data. We describe a statistical learning methodology that can automatically screen for nonlinear relations among prognostic variables and generalize to unseen data before. In this work, several types of linear and nonlinear kernels to generate interaction terms and approximate the treatment-response function are evaluated. Examples of institutional datasets of esophagitis, pneumonitis and xerostomia endpoints were used. Furthermore, an independent RTOG dataset was used for 'generalizabilty' validation. We formulated the discrimination between risk groups as a supervised learning problem. The distribution of patient groups was initially analyzed using principle components analysis (PCA) to uncover potential nonlinear behavior. The performance of the different methods was evaluated using bivariate correlations and actuarial analysis. Over-fitting was controlled via cross-validation resampling. Our results suggest that a modified support vector machine (SVM) kernel method provided superior performance on leave-one-out testing compared to logistic regression and neural networks in cases where the data exhibited nonlinear behavior on PCA. For instance, in prediction of esophagitis and pneumonitis endpoints, which exhibited nonlinear behavior on PCA, the method provided 21% and 60% improvements, respectively. Furthermore, evaluation on the independent pneumonitis RTOG dataset demonstrated good generalizabilty beyond institutional data in contrast with other models. This indicates that the prediction of treatment response can be improved by utilizing nonlinear kernel methods for discovering important nonlinear interactions among model

Development and Validation of a Predictive Model for Functional Outcome After Stroke Rehabilitation: The Maugeri Model.

Science.gov (United States)

Scrutinio, Domenico; Lanzillo, Bernardo; Guida, Pietro; Mastropasqua, Filippo; Monitillo, Vincenzo; Pusineri, Monica; Formica, Roberto; Russo, Giovanna; Guarnaschelli, Caterina; Ferretti, Chiara; Calabrese, Gianluigi

2017-12-01

Prediction of outcome after stroke rehabilitation may help clinicians in decision-making and planning rehabilitation care. We developed and validated a predictive tool to estimate the probability of achieving improvement in physical functioning (model 1) and a level of independence requiring no more than supervision (model 2) after stroke rehabilitation. The models were derived from 717 patients admitted for stroke rehabilitation. We used multivariable logistic regression analysis to build each model. Then, each model was prospectively validated in 875 patients. Model 1 included age, time from stroke occurrence to rehabilitation admission, admission motor and cognitive Functional Independence Measure scores, and neglect. Model 2 included age, male gender, time since stroke onset, and admission motor and cognitive Functional Independence Measure score. Both models demonstrated excellent discrimination. In the derivation cohort, the area under the curve was 0.883 (95% confidence intervals, 0.858-0.910) for model 1 and 0.913 (95% confidence intervals, 0.884-0.942) for model 2. The Hosmer-Lemeshow χ 2 was 4.12 ( P =0.249) and 1.20 ( P =0.754), respectively. In the validation cohort, the area under the curve was 0.866 (95% confidence intervals, 0.840-0.892) for model 1 and 0.850 (95% confidence intervals, 0.815-0.885) for model 2. The Hosmer-Lemeshow χ 2 was 8.86 ( P =0.115) and 34.50 ( P =0.001), respectively. Both improvement in physical functioning (hazard ratios, 0.43; 0.25-0.71; P =0.001) and a level of independence requiring no more than supervision (hazard ratios, 0.32; 0.14-0.68; P =0.004) were independently associated with improved 4-year survival. A calculator is freely available for download at https://goo.gl/fEAp81. This study provides researchers and clinicians with an easy-to-use, accurate, and validated predictive tool for potential application in rehabilitation research and stroke management. © 2017 American Heart Association, Inc.

Cancer imaging phenomics toolkit: quantitative imaging analytics for precision diagnostics and predictive modeling of clinical outcome.

Science.gov (United States)

Davatzikos, Christos; Rathore, Saima; Bakas, Spyridon; Pati, Sarthak; Bergman, Mark; Kalarot, Ratheesh; Sridharan, Patmaa; Gastounioti, Aimilia; Jahani, Nariman; Cohen, Eric; Akbari, Hamed; Tunc, Birkan; Doshi, Jimit; Parker, Drew; Hsieh, Michael; Sotiras, Aristeidis; Li, Hongming; Ou, Yangming; Doot, Robert K; Bilello, Michel; Fan, Yong; Shinohara, Russell T; Yushkevich, Paul; Verma, Ragini; Kontos, Despina

2018-01-01

The growth of multiparametric imaging protocols has paved the way for quantitative imaging phenotypes that predict treatment response and clinical outcome, reflect underlying cancer molecular characteristics and spatiotemporal heterogeneity, and can guide personalized treatment planning. This growth has underlined the need for efficient quantitative analytics to derive high-dimensional imaging signatures of diagnostic and predictive value in this emerging era of integrated precision diagnostics. This paper presents cancer imaging phenomics toolkit (CaPTk), a new and dynamically growing software platform for analysis of radiographic images of cancer, currently focusing on brain, breast, and lung cancer. CaPTk leverages the value of quantitative imaging analytics along with machine learning to derive phenotypic imaging signatures, based on two-level functionality. First, image analysis algorithms are used to extract comprehensive panels of diverse and complementary features, such as multiparametric intensity histogram distributions, texture, shape, kinetics, connectomics, and spatial patterns. At the second level, these quantitative imaging signatures are fed into multivariate machine learning models to produce diagnostic, prognostic, and predictive biomarkers. Results from clinical studies in three areas are shown: (i) computational neuro-oncology of brain gliomas for precision diagnostics, prediction of outcome, and treatment planning; (ii) prediction of treatment response for breast and lung cancer, and (iii) risk assessment for breast cancer.

Prognostic breast cancer signature identified from 3D culture model accurately predicts clinical outcome across independent datasets

Energy Technology Data Exchange (ETDEWEB)

Martin, Katherine J.; Patrick, Denis R.; Bissell, Mina J.; Fournier, Marcia V.

2008-10-20

One of the major tenets in breast cancer research is that early detection is vital for patient survival by increasing treatment options. To that end, we have previously used a novel unsupervised approach to identify a set of genes whose expression predicts prognosis of breast cancer patients. The predictive genes were selected in a well-defined three dimensional (3D) cell culture model of non-malignant human mammary epithelial cell morphogenesis as down-regulated during breast epithelial cell acinar formation and cell cycle arrest. Here we examine the ability of this gene signature (3D-signature) to predict prognosis in three independent breast cancer microarray datasets having 295, 286, and 118 samples, respectively. Our results show that the 3D-signature accurately predicts prognosis in three unrelated patient datasets. At 10 years, the probability of positive outcome was 52, 51, and 47 percent in the group with a poor-prognosis signature and 91, 75, and 71 percent in the group with a good-prognosis signature for the three datasets, respectively (Kaplan-Meier survival analysis, p<0.05). Hazard ratios for poor outcome were 5.5 (95% CI 3.0 to 12.2, p<0.0001), 2.4 (95% CI 1.6 to 3.6, p<0.0001) and 1.9 (95% CI 1.1 to 3.2, p = 0.016) and remained significant for the two larger datasets when corrected for estrogen receptor (ER) status. Hence the 3D-signature accurately predicts breast cancer outcome in both ER-positive and ER-negative tumors, though individual genes differed in their prognostic ability in the two subtypes. Genes that were prognostic in ER+ patients are AURKA, CEP55, RRM2, EPHA2, FGFBP1, and VRK1, while genes prognostic in ER patients include ACTB, FOXM1 and SERPINE2 (Kaplan-Meier p<0.05). Multivariable Cox regression analysis in the largest dataset showed that the 3D-signature was a strong independent factor in predicting breast cancer outcome. The 3D-signature accurately predicts breast cancer outcome across multiple datasets and holds prognostic

An analysis from the Quality Outcomes Database, Part 1. Disability, quality of life, and pain outcomes following lumbar spine surgery: predicting likely individual patient outcomes for shared decision-making.

Science.gov (United States)

McGirt, Matthew J; Bydon, Mohamad; Archer, Kristin R; Devin, Clinton J; Chotai, Silky; Parker, Scott L; Nian, Hui; Harrell, Frank E; Speroff, Theodore; Dittus, Robert S; Philips, Sharon E; Shaffrey, Christopher I; Foley, Kevin T; Asher, Anthony L

2017-10-01

OBJECTIVE Quality and outcomes registry platforms lie at the center of many emerging evidence-driven reform models. Specifically, clinical registry data are progressively informing health care decision-making. In this analysis, the authors used data from a national prospective outcomes registry (the Quality Outcomes Database) to develop a predictive model for 12-month postoperative pain, disability, and quality of life (QOL) in patients undergoing elective lumbar spine surgery. METHODS Included in this analysis were 7618 patients who had completed 12 months of follow-up. The authors prospectively assessed baseline and 12-month patient-reported outcomes (PROs) via telephone interviews. The PROs assessed were those ascertained using the Oswestry Disability Index (ODI), EQ-5D, and numeric rating scale (NRS) for back pain (BP) and leg pain (LP). Variables analyzed for the predictive model included age, gender, body mass index, race, education level, history of prior surgery, smoking status, comorbid conditions, American Society of Anesthesiologists (ASA) score, symptom duration, indication for surgery, number of levels surgically treated, history of fusion surgery, surgical approach, receipt of workers' compensation, liability insurance, insurance status, and ambulatory ability. To create a predictive model, each 12-month PRO was treated as an ordinal dependent variable and a separate proportional-odds ordinal logistic regression model was fitted for each PRO. RESULTS There was a significant improvement in all PROs (p disability, QOL, and pain outcomes following lumbar spine surgery were employment status, baseline NRS-BP scores, psychological distress, baseline ODI scores, level of education, workers' compensation status, symptom duration, race, baseline NRS-LP scores, ASA score, age, predominant symptom, smoking status, and insurance status. The prediction discrimination of the 4 separate novel predictive models was good, with a c-index of 0.69 for ODI, 0.69 for EQ-5

Predicting Community College Outcomes: Does High School CTE Participation Have a Significant Effect?

Science.gov (United States)

Dietrich, Cecile; Lichtenberger, Eric; Kamalludeen, Rosemaliza

2016-01-01

This study explored the relative importance of participation in high school career and technical education (CTE) programs in predicting community college outcomes. A hierarchical generalized linear model (HGLM) was used to predict community college outcome attainment among a random sample of direct community college entrants. Results show that…

Comparison of classification methods for voxel-based prediction of acute ischemic stroke outcome following intra-arterial intervention

Science.gov (United States)

Winder, Anthony J.; Siemonsen, Susanne; Flottmann, Fabian; Fiehler, Jens; Forkert, Nils D.

2017-03-01

Voxel-based tissue outcome prediction in acute ischemic stroke patients is highly relevant for both clinical routine and research. Previous research has shown that features extracted from baseline multi-parametric MRI datasets have a high predictive value and can be used for the training of classifiers, which can generate tissue outcome predictions for both intravenous and conservative treatments. However, with the recent advent and popularization of intra-arterial thrombectomy treatment, novel research specifically addressing the utility of predictive classi- fiers for thrombectomy intervention is necessary for a holistic understanding of current stroke treatment options. The aim of this work was to develop three clinically viable tissue outcome prediction models using approximate nearest-neighbor, generalized linear model, and random decision forest approaches and to evaluate the accuracy of predicting tissue outcome after intra-arterial treatment. Therefore, the three machine learning models were trained, evaluated, and compared using datasets of 42 acute ischemic stroke patients treated with intra-arterial thrombectomy. Classifier training utilized eight voxel-based features extracted from baseline MRI datasets and five global features. Evaluation of classifier-based predictions was performed via comparison to the known tissue outcome, which was determined in follow-up imaging, using the Dice coefficient and leave-on-patient-out cross validation. The random decision forest prediction model led to the best tissue outcome predictions with a mean Dice coefficient of 0.37. The approximate nearest-neighbor and generalized linear model performed equally suboptimally with average Dice coefficients of 0.28 and 0.27 respectively, suggesting that both non-linearity and machine learning are desirable properties of a classifier well-suited to the intra-arterial tissue outcome prediction problem.

Comparison of statistical and clinical predictions of functional outcome after ischemic stroke.

Directory of Open Access Journals (Sweden)

Douglas D Thompson

Full Text Available To determine whether the predictions of functional outcome after ischemic stroke made at the bedside using a doctor's clinical experience were more or less accurate than the predictions made by clinical prediction models (CPMs.A prospective cohort study of nine hundred and thirty one ischemic stroke patients recruited consecutively at the outpatient, inpatient and emergency departments of the Western General Hospital, Edinburgh between 2002 and 2005. Doctors made informal predictions of six month functional outcome on the Oxford Handicap Scale (OHS. Patients were followed up at six months with a validated postal questionnaire. For each patient we calculated the absolute predicted risk of death or dependence (OHS≥3 using five previously described CPMs. The specificity of a doctor's informal predictions of OHS≥3 at six months was good 0.96 (95% CI: 0.94 to 0.97 and similar to CPMs (range 0.94 to 0.96; however the sensitivity of both informal clinical predictions 0.44 (95% CI: 0.39 to 0.49 and clinical prediction models (range 0.38 to 0.45 was poor. The prediction of the level of disability after stroke was similar for informal clinical predictions (ordinal c-statistic 0.74 with 95% CI 0.72 to 0.76 and CPMs (range 0.69 to 0.75. No patient or clinician characteristic affected the accuracy of informal predictions, though predictions were more accurate in outpatients.CPMs are at least as good as informal clinical predictions in discriminating between good and bad functional outcome after ischemic stroke. The place of these models in clinical practice has yet to be determined.

Predictive modeling of outcomes following definitive chemoradiotherapy for oropharyngeal cancer based on FDG-PET image characteristics

Science.gov (United States)

Folkert, Michael R.; Setton, Jeremy; Apte, Aditya P.; Grkovski, Milan; Young, Robert J.; Schöder, Heiko; Thorstad, Wade L.; Lee, Nancy Y.; Deasy, Joseph O.; Oh, Jung Hun

2017-07-01

In this study, we investigate the use of imaging feature-based outcomes research (‘radiomics’) combined with machine learning techniques to develop robust predictive models for the risk of all-cause mortality (ACM), local failure (LF), and distant metastasis (DM) following definitive chemoradiation therapy (CRT). One hundred seventy four patients with stage III-IV oropharyngeal cancer (OC) treated at our institution with CRT with retrievable pre- and post-treatment 18F-fluorodeoxyglucose positron emission tomography (FDG-PET) scans were identified. From pre-treatment PET scans, 24 representative imaging features of FDG-avid disease regions were extracted. Using machine learning-based feature selection methods, multiparameter logistic regression models were built incorporating clinical factors and imaging features. All model building methods were tested by cross validation to avoid overfitting, and final outcome models were validated on an independent dataset from a collaborating institution. Multiparameter models were statistically significant on 5 fold cross validation with the area under the receiver operating characteristic curve (AUC)  =  0.65 (p  =  0.004), 0.73 (p  =  0.026), and 0.66 (p  =  0.015) for ACM, LF, and DM, respectively. The model for LF retained significance on the independent validation cohort with AUC  =  0.68 (p  =  0.029) whereas the models for ACM and DM did not reach statistical significance, but resulted in comparable predictive power to the 5 fold cross validation with AUC  =  0.60 (p  =  0.092) and 0.65 (p  =  0.062), respectively. In the largest study of its kind to date, predictive features including increasing metabolic tumor volume, increasing image heterogeneity, and increasing tumor surface irregularity significantly correlated to mortality, LF, and DM on 5 fold cross validation in a relatively uniform single-institution cohort. The LF model also retained

Neonatal Pulmonary MRI of Bronchopulmonary Dysplasia Predicts Short-term Clinical Outcomes.

Science.gov (United States)

Higano, Nara S; Spielberg, David R; Fleck, Robert J; Schapiro, Andrew H; Walkup, Laura L; Hahn, Andrew D; Tkach, Jean A; Kingma, Paul S; Merhar, Stephanie L; Fain, Sean B; Woods, Jason C

2018-05-23

Bronchopulmonary dysplasia (BPD) is a serious neonatal pulmonary condition associated with premature birth, but the underlying parenchymal disease and trajectory are poorly characterized. The current NICHD/NHLBI definition of BPD severity is based on degree of prematurity and extent of oxygen requirement. However, no clear link exists between initial diagnosis and clinical outcomes. We hypothesized that magnetic resonance imaging (MRI) of structural parenchymal abnormalities will correlate with NICHD-defined BPD disease severity and predict short-term respiratory outcomes. Forty-two neonates (20 severe BPD, 6 moderate, 7 mild, 9 non-BPD controls; 40±3 weeks post-menstrual age) underwent quiet-breathing structural pulmonary MRI (ultrashort echo-time and gradient echo) in a NICU-sited, neonatal-sized 1.5T scanner, without sedation or respiratory support unless already clinically prescribed. Disease severity was scored independently by two radiologists. Mean scores were compared to clinical severity and short-term respiratory outcomes. Outcomes were predicted using univariate and multivariable models including clinical data and scores. MRI scores significantly correlated with severities and predicted respiratory support at NICU discharge (P<0.0001). In multivariable models, MRI scores were by far the strongest predictor of respiratory support duration over clinical data, including birth weight and gestational age. Notably, NICHD severity level was not predictive of discharge support. Quiet-breathing neonatal pulmonary MRI can independently assess structural abnormalities of BPD, describe disease severity, and predict short-term outcomes more accurately than any individual standard clinical measure. Importantly, this non-ionizing technique can be implemented to phenotype disease and has potential to serially assess efficacy of individualized therapies.

Network information improves cancer outcome prediction.

Science.gov (United States)

Roy, Janine; Winter, Christof; Isik, Zerrin; Schroeder, Michael

2014-07-01

Disease progression in cancer can vary substantially between patients. Yet, patients often receive the same treatment. Recently, there has been much work on predicting disease progression and patient outcome variables from gene expression in order to personalize treatment options. Despite first diagnostic kits in the market, there are open problems such as the choice of random gene signatures or noisy expression data. One approach to deal with these two problems employs protein-protein interaction networks and ranks genes using the random surfer model of Google's PageRank algorithm. In this work, we created a benchmark dataset collection comprising 25 cancer outcome prediction datasets from literature and systematically evaluated the use of networks and a PageRank derivative, NetRank, for signature identification. We show that the NetRank performs significantly better than classical methods such as fold change or t-test. Despite an order of magnitude difference in network size, a regulatory and protein-protein interaction network perform equally well. Experimental evaluation on cancer outcome prediction in all of the 25 underlying datasets suggests that the network-based methodology identifies highly overlapping signatures over all cancer types, in contrast to classical methods that fail to identify highly common gene sets across the same cancer types. Integration of network information into gene expression analysis allows the identification of more reliable and accurate biomarkers and provides a deeper understanding of processes occurring in cancer development and progression. © The Author 2012. Published by Oxford University Press. For Permissions, please email: journals.permissions@oup.com.

Cross-trial prediction of treatment outcome in depression: a machine learning approach.

Science.gov (United States)

Chekroud, Adam Mourad; Zotti, Ryan Joseph; Shehzad, Zarrar; Gueorguieva, Ralitza; Johnson, Marcia K; Trivedi, Madhukar H; Cannon, Tyrone D; Krystal, John Harrison; Corlett, Philip Robert

2016-03-01

Antidepressant treatment efficacy is low, but might be improved by matching patients to interventions. At present, clinicians have no empirically validated mechanisms to assess whether a patient with depression will respond to a specific antidepressant. We aimed to develop an algorithm to assess whether patients will achieve symptomatic remission from a 12-week course of citalopram. We used patient-reported data from patients with depression (n=4041, with 1949 completers) from level 1 of the Sequenced Treatment Alternatives to Relieve Depression (STAR*D; ClinicalTrials.gov, number NCT00021528) to identify variables that were most predictive of treatment outcome, and used these variables to train a machine-learning model to predict clinical remission. We externally validated the model in the escitalopram treatment group (n=151) of an independent clinical trial (Combining Medications to Enhance Depression Outcomes [COMED]; ClinicalTrials.gov, number NCT00590863). We identified 25 variables that were most predictive of treatment outcome from 164 patient-reportable variables, and used these to train the model. The model was internally cross-validated, and predicted outcomes in the STAR*D cohort with accuracy significantly above chance (64·6% [SD 3·2]; p<0·0001). The model was externally validated in the escitalopram treatment group (N=151) of COMED (accuracy 59·6%, p=0.043). The model also performed significantly above chance in a combined escitalopram-buproprion treatment group in COMED (n=134; accuracy 59·7%, p=0·023), but not in a combined venlafaxine-mirtazapine group (n=140; accuracy 51·4%, p=0·53), suggesting specificity of the model to underlying mechanisms. Building statistical models by mining existing clinical trial data can enable prospective identification of patients who are likely to respond to a specific antidepressant. Yale University. Copyright © 2016 Elsevier Ltd. All rights reserved.

Risk prediction model: Statistical and artificial neural network approach

Science.gov (United States)

Paiman, Nuur Azreen; Hariri, Azian; Masood, Ibrahim

2017-04-01

Prediction models are increasingly gaining popularity and had been used in numerous areas of studies to complement and fulfilled clinical reasoning and decision making nowadays. The adoption of such models assist physician's decision making, individual's behavior, and consequently improve individual outcomes and the cost-effectiveness of care. The objective of this paper is to reviewed articles related to risk prediction model in order to understand the suitable approach, development and the validation process of risk prediction model. A qualitative review of the aims, methods and significant main outcomes of the nineteen published articles that developed risk prediction models from numerous fields were done. This paper also reviewed on how researchers develop and validate the risk prediction models based on statistical and artificial neural network approach. From the review done, some methodological recommendation in developing and validating the prediction model were highlighted. According to studies that had been done, artificial neural network approached in developing the prediction model were more accurate compared to statistical approach. However currently, only limited published literature discussed on which approach is more accurate for risk prediction model development.

Early functional MRI activation predicts motor outcome after ischemic stroke: a longitudinal, multimodal study.

Science.gov (United States)

Du, Juan; Yang, Fang; Zhang, Zhiqiang; Hu, Jingze; Xu, Qiang; Hu, Jianping; Zeng, Fanyong; Lu, Guangming; Liu, Xinfeng

2018-05-15

An accurate prediction of long term outcome after stroke is urgently required to provide early individualized neurorehabilitation. This study aimed to examine the added value of early neuroimaging measures and identify the best approaches for predicting motor outcome after stroke. This prospective study involved 34 first-ever ischemic stroke patients (time since stroke: 1-14 days) with upper limb impairment. All patients underwent baseline multimodal assessments that included clinical (age, motor impairment), neurophysiological (motor-evoked potentials, MEP) and neuroimaging (diffusion tensor imaging and motor task-based fMRI) measures, and also underwent reassessment 3 months after stroke. Bivariate analysis and multivariate linear regression models were used to predict the motor scores (Fugl-Meyer assessment, FMA) at 3 months post-stroke. With bivariate analysis, better motor outcome significantly correlated with (1) less initial motor impairment and disability, (2) less corticospinal tract injury, (3) the initial presence of MEPs, (4) stronger baseline motor fMRI activations. In multivariate analysis, incorporating neuroimaging data improved the predictive accuracy relative to only clinical and neurophysiological assessments. Baseline fMRI activation in SMA was an independent predictor of motor outcome after stroke. A multimodal model incorporating fMRI and clinical measures best predicted the motor outcome following stroke. fMRI measures obtained early after stroke provided independent prediction of long-term motor outcome.

Performance of third-trimester combined screening model for prediction of adverse perinatal outcome.

Science.gov (United States)

Miranda, J; Triunfo, S; Rodriguez-Lopez, M; Sairanen, M; Kouru, H; Parra-Saavedra, M; Crovetto, F; Figueras, F; Crispi, F; Gratacós, E

2017-09-01

To explore the potential value of third-trimester combined screening for the prediction of adverse perinatal outcome (APO) in the general population and among small-for-gestational-age (SGA) fetuses. This was a nested case-control study within a prospective cohort of 1590 singleton gestations undergoing third-trimester evaluation (32 + 0 to 36 + 6 weeks' gestation). Maternal baseline characteristics, mean arterial blood pressure, fetoplacental ultrasound and circulating biochemical markers (placental growth factor (PlGF), lipocalin-2, unconjugated estriol and inhibin A) were assessed in all women who subsequently had an APO (n = 148) and in a control group without perinatal complications (n = 902). APO was defined as the occurrence of stillbirth, umbilical artery cord blood pH < 7.15, 5-min Apgar score < 7 or emergency operative delivery for fetal distress. Logistic regression models were developed for the prediction of APO in the general population and among SGA cases (defined as customized birth weight < 10 th centile). The prevalence of APO was 9.3% in the general population and 27.4% among SGA cases. In the general population, a combined screening model including a-priori risk (maternal characteristics), estimated fetal weight (EFW) centile, umbilical artery pulsatility index (UA-PI), estriol and PlGF achieved a detection rate for APO of 26% (area under receiver-operating characteristics curve (AUC), 0.59 (95% CI, 0.54-0.65)), at a 10% false-positive rate (FPR). Among SGA cases, a model including a-priori risk, EFW centile, UA-PI, cerebroplacental ratio, estriol and PlGF predicted 62% of APO (AUC, 0.86 (95% CI, 0.80-0.92)) at a FPR of 10%. The use of fetal ultrasound and maternal biochemical markers at 32-36 weeks provides a poor prediction of APO in the general population. Although it remains limited, the performance of the screening model is improved when applied to fetuses with suboptimal fetal growth. Copyright © 2016 ISUOG. Published by John Wiley & Sons

Clinical Prediction Models for Cardiovascular Disease: Tufts Predictive Analytics and Comparative Effectiveness Clinical Prediction Model Database.

Science.gov (United States)

Wessler, Benjamin S; Lai Yh, Lana; Kramer, Whitney; Cangelosi, Michael; Raman, Gowri; Lutz, Jennifer S; Kent, David M

2015-07-01

Clinical prediction models (CPMs) estimate the probability of clinical outcomes and hold the potential to improve decision making and individualize care. For patients with cardiovascular disease, there are numerous CPMs available although the extent of this literature is not well described. We conducted a systematic review for articles containing CPMs for cardiovascular disease published between January 1990 and May 2012. Cardiovascular disease includes coronary heart disease, heart failure, arrhythmias, stroke, venous thromboembolism, and peripheral vascular disease. We created a novel database and characterized CPMs based on the stage of development, population under study, performance, covariates, and predicted outcomes. There are 796 models included in this database. The number of CPMs published each year is increasing steadily over time. Seven hundred seventeen (90%) are de novo CPMs, 21 (3%) are CPM recalibrations, and 58 (7%) are CPM adaptations. This database contains CPMs for 31 index conditions, including 215 CPMs for patients with coronary artery disease, 168 CPMs for population samples, and 79 models for patients with heart failure. There are 77 distinct index/outcome pairings. Of the de novo models in this database, 450 (63%) report a c-statistic and 259 (36%) report some information on calibration. There is an abundance of CPMs available for a wide assortment of cardiovascular disease conditions, with substantial redundancy in the literature. The comparative performance of these models, the consistency of effects and risk estimates across models and the actual and potential clinical impact of this body of literature is poorly understood. © 2015 American Heart Association, Inc.

What Factors are Predictive of Patient-reported Outcomes? A Prospective Study of 337 Shoulder Arthroplasties.

Science.gov (United States)

Matsen, Frederick A; Russ, Stacy M; Vu, Phuong T; Hsu, Jason E; Lucas, Robert M; Comstock, Bryan A

2016-11-01

Although shoulder arthroplasties generally are effective in improving patients' comfort and function, the results are variable for reasons that are not well understood. We posed two questions: (1) What factors are associated with better 2-year outcomes after shoulder arthroplasty? (2) What are the sensitivities, specificities, and positive and negative predictive values of a multivariate predictive model for better outcome? Three hundred thirty-nine patients having a shoulder arthroplasty (hemiarthroplasty, arthroplasty for cuff tear arthropathy, ream and run arthroplasty, total shoulder or reverse total shoulder arthroplasty) between August 24, 2010 and December 31, 2012 consented to participate in this prospective study. Two patients were excluded because they were missing baseline variables. Forty-three patients were missing 2-year data. Univariate and multivariate analyses determined the relationship of baseline patient, shoulder, and surgical characteristics to a "better" outcome, defined as an improvement of at least 30% of the maximal possible improvement in the Simple Shoulder Test. The results were used to develop a predictive model, the accuracy of which was tested using a 10-fold cross-validation. After controlling for potentially relevant confounding variables, the multivariate analysis showed that the factors significantly associated with better outcomes were American Society of Anesthesiologists Class I (odds ratio [OR], 1.94; 95% CI, 1.03-3.65; p = 0.041), shoulder problem not related to work (OR, 5.36; 95% CI, 2.15-13.37; p factors listed above. The area under the receiver operating characteristic curve generated from the cross-validated enhanced predictive model was 0.79 (generally values of 0.7 to 0.8 are considered fair and values of 0.8 to 0.9 are considered good). The false-positive fraction and the true-positive fraction depended on the cutoff probability selected (ie, the selected probability above which the prediction would be classified as

Action-outcome learning and prediction shape the window of simultaneity of audiovisual outcomes.

Science.gov (United States)

Desantis, Andrea; Haggard, Patrick

2016-08-01

To form a coherent representation of the objects around us, the brain must group the different sensory features composing these objects. Here, we investigated whether actions contribute in this grouping process. In particular, we assessed whether action-outcome learning and prediction contribute to audiovisual temporal binding. Participants were presented with two audiovisual pairs: one pair was triggered by a left action, and the other by a right action. In a later test phase, the audio and visual components of these pairs were presented at different onset times. Participants judged whether they were simultaneous or not. To assess the role of action-outcome prediction on audiovisual simultaneity, each action triggered either the same audiovisual pair as in the learning phase ('predicted' pair), or the pair that had previously been associated with the other action ('unpredicted' pair). We found the time window within which auditory and visual events appeared simultaneous increased for predicted compared to unpredicted pairs. However, no change in audiovisual simultaneity was observed when audiovisual pairs followed visual cues, rather than voluntary actions. This suggests that only action-outcome learning promotes temporal grouping of audio and visual effects. In a second experiment we observed that changes in audiovisual simultaneity do not only depend on our ability to predict what outcomes our actions generate, but also on learning the delay between the action and the multisensory outcome. When participants learned that the delay between action and audiovisual pair was variable, the window of audiovisual simultaneity for predicted pairs increased, relative to a fixed action-outcome pair delay. This suggests that participants learn action-based predictions of audiovisual outcome, and adapt their temporal perception of outcome events based on such predictions. Copyright © 2016 The Authors. Published by Elsevier B.V. All rights reserved.

Using predictive analytics and big data to optimize pharmaceutical outcomes.

Science.gov (United States)

Hernandez, Inmaculada; Zhang, Yuting

2017-09-15

The steps involved, the resources needed, and the challenges associated with applying predictive analytics in healthcare are described, with a review of successful applications of predictive analytics in implementing population health management interventions that target medication-related patient outcomes. In healthcare, the term big data typically refers to large quantities of electronic health record, administrative claims, and clinical trial data as well as data collected from smartphone applications, wearable devices, social media, and personal genomics services; predictive analytics refers to innovative methods of analysis developed to overcome challenges associated with big data, including a variety of statistical techniques ranging from predictive modeling to machine learning to data mining. Predictive analytics using big data have been applied successfully in several areas of medication management, such as in the identification of complex patients or those at highest risk for medication noncompliance or adverse effects. Because predictive analytics can be used in predicting different outcomes, they can provide pharmacists with a better understanding of the risks for specific medication-related problems that each patient faces. This information will enable pharmacists to deliver interventions tailored to patients' needs. In order to take full advantage of these benefits, however, clinicians will have to understand the basics of big data and predictive analytics. Predictive analytics that leverage big data will become an indispensable tool for clinicians in mapping interventions and improving patient outcomes. Copyright © 2017 by the American Society of Health-System Pharmacists, Inc. All rights reserved.

[Acute kidney injury after pediatric cardiac surgery: risk factors and outcomes. Proposal for a predictive model].

Science.gov (United States)

Cardoso, Bárbara; Laranjo, Sérgio; Gomes, Inês; Freitas, Isabel; Trigo, Conceição; Fragata, Isabel; Fragata, José; Pinto, Fátima

2016-02-01

To characterize the epidemiology and risk factors for acute kidney injury (AKI) after pediatric cardiac surgery in our center, to determine its association with poor short-term outcomes, and to develop a logistic regression model that will predict the risk of AKI for the study population. This single-center, retrospective study included consecutive pediatric patients with congenital heart disease who underwent cardiac surgery between January 2010 and December 2012. Exclusion criteria were a history of renal disease, dialysis or renal transplantation. Of the 325 patients included, median age three years (1 day-18 years), AKI occurred in 40 (12.3%) on the first postoperative day. Overall mortality was 13 (4%), nine of whom were in the AKI group. AKI was significantly associated with length of intensive care unit stay, length of mechanical ventilation and in-hospital death (p<0.01). Patients' age and postoperative serum creatinine, blood urea nitrogen and lactate levels were included in the logistic regression model as predictor variables. The model accurately predicted AKI in this population, with a maximum combined sensitivity of 82.1% and specificity of 75.4%. AKI is common and is associated with poor short-term outcomes in this setting. Younger age and higher postoperative serum creatinine, blood urea nitrogen and lactate levels were powerful predictors of renal injury in this population. The proposed model could be a useful tool for risk stratification of these patients. Copyright © 2015 Sociedade Portuguesa de Cardiologia. Published by Elsevier España. All rights reserved.

Early post-stroke cognition in stroke rehabilitation patients predicts functional outcome at 13 months.

Science.gov (United States)

Wagle, Jørgen; Farner, Lasse; Flekkøy, Kjell; Bruun Wyller, Torgeir; Sandvik, Leiv; Fure, Brynjar; Stensrød, Brynhild; Engedal, Knut

2011-01-01

To identify prognostic factors associated with functional outcome at 13 months in a sample of stroke rehabilitation patients. Specifically, we hypothesized that cognitive functioning early after stroke would predict long-term functional outcome independently of other factors. 163 stroke rehabilitation patients underwent a structured neuropsychological examination 2-3 weeks after hospital admittance, and their functional status was subsequently evaluated 13 months later with the modified Rankin Scale (mRS) as outcome measure. Three predictive models were built using linear regression analyses: a biological model (sociodemographics, apolipoprotein E genotype, prestroke vascular factors, lesion characteristics and neurological stroke-related impairment); a functional model (pre- and early post-stroke cognitive functioning, personal and instrumental activities of daily living, ADL, and depressive symptoms), and a combined model (including significant variables, with p value Stroke Scale; β = 0.402, p stroke cognitive functioning (Repeatable Battery of Neuropsychological Status, RBANS; β = -0.248, p = 0.001) and prestroke personal ADL (Barthel Index; β = -0.217, p = 0.002). Further linear regression analyses of which RBANS indexes and subtests best predicted long-term functional outcome showed that Coding (β = -0.484, p stroke cognitive functioning as measured by the RBANS is a significant and independent predictor of long-term functional post-stroke outcome. Copyright © 2011 S. Karger AG, Basel.

Methodological Challenges in Examining the Impact of Healthcare Predictive Analytics on Nursing-Sensitive Patient Outcomes.

Science.gov (United States)

Jeffery, Alvin D

2015-06-01

The expansion of real-time analytic abilities within current electronic health records has led to innovations in predictive modeling and clinical decision support systems. However, the ability of these systems to influence patient outcomes is currently unknown. Even though nurses are the largest profession within the healthcare workforce, little research has been performed to explore the impact of clinical decision support on their decisions and the patient outcomes associated with them. A scoping literature review explored the impact clinical decision support systems containing healthcare predictive analytics have on four nursing-sensitive patient outcomes (pressure ulcers, failure to rescue, falls, and infections). While many articles discussed variable selection and predictive model development/validation, only four articles examined the impact on patient outcomes. The novelty of predictive analytics and the inherent methodological challenges in studying clinical decision support impact are likely responsible for this paucity of literature. Major methodological challenges include (1) multilevel nature of intervention, (2) treatment fidelity, and (3) adequacy of clinicians' subsequent behavior. There is currently insufficient evidence to demonstrate efficacy of healthcare predictive analytics-enhanced clinical decision support systems on nursing-sensitive patient outcomes. Innovative research methods and a greater emphasis on studying this phenomenon are needed.

Mortality and One-Year Functional Outcome in Elderly and Very Old Patients with Severe Traumatic Brain Injuries: Observed and Predicted

Directory of Open Access Journals (Sweden)

Cecilie Røe

2015-01-01

Full Text Available The aim of the present study was to evaluate mortality and functional outcome in old and very old patients with severe traumatic brain injury (TBI and compare to the predicted outcome according to the internet based CRASH (Corticosteroid Randomization After Significant Head injury model based prediction, from the Medical Research Council (MRC. Methods. Prospective, national multicenter study including patients with severe TBI ≥65 years. Predicted mortality and outcome were calculated based on clinical information (CRASH basic (age, GCS score, and pupil reactivity to light, as well as with additional CT findings (CRASH CT. Observed 14-day mortality and favorable/unfavorable outcome according to the Glasgow Outcome Scale at one year was compared to the predicted outcome according to the CRASH models. Results. 97 patients, mean age 75 (SD 7 years, 64% men, were included. Two patients were lost to follow-up; 48 died within 14 days. The predicted versus the observed odds ratio (OR for mortality was 2.65. Unfavorable outcome (GOSE < 5 was observed at one year follow-up in 72% of patients. The CRASH models predicted unfavorable outcome in all patients. Conclusion. The CRASH model overestimated mortality and unfavorable outcome in old and very old Norwegian patients with severe TBI.

Mortality and One-Year Functional Outcome in Elderly and Very Old Patients with Severe Traumatic Brain Injuries: Observed and Predicted

Science.gov (United States)

Røe, Cecilie; Skandsen, Toril; Manskow, Unn; Ader, Tiina; Anke, Audny

2015-01-01

The aim of the present study was to evaluate mortality and functional outcome in old and very old patients with severe traumatic brain injury (TBI) and compare to the predicted outcome according to the internet based CRASH (Corticosteroid Randomization After Significant Head injury) model based prediction, from the Medical Research Council (MRC). Methods. Prospective, national multicenter study including patients with severe TBI ≥65 years. Predicted mortality and outcome were calculated based on clinical information (CRASH basic) (age, GCS score, and pupil reactivity to light), as well as with additional CT findings (CRASH CT). Observed 14-day mortality and favorable/unfavorable outcome according to the Glasgow Outcome Scale at one year was compared to the predicted outcome according to the CRASH models. Results. 97 patients, mean age 75 (SD 7) years, 64% men, were included. Two patients were lost to follow-up; 48 died within 14 days. The predicted versus the observed odds ratio (OR) for mortality was 2.65. Unfavorable outcome (GOSE < 5) was observed at one year follow-up in 72% of patients. The CRASH models predicted unfavorable outcome in all patients. Conclusion. The CRASH model overestimated mortality and unfavorable outcome in old and very old Norwegian patients with severe TBI. PMID:26688614

Predictive Utility of Personality Disorder in Depression: Comparison of Outcomes and Taxonomic Approach.

Science.gov (United States)

Newton-Howes, Giles; Mulder, Roger; Ellis, Pete M; Boden, Joseph M; Joyce, Peter

2017-09-19

There is debate around the best model for diagnosing personality disorder, both in terms of its relationship to the empirical data and clinical utility. Four randomized controlled trials examining various treatments for depression were analyzed at an individual patient level. Three different approaches to the diagnosis of personality disorder were analyzed in these patients. A total of 578 depressed patients were included in the analysis. Personality disorder, however measured, was of little predictive utility in the short term but added significantly to predictive modelling of medium-term outcomes, accounting for more than twice as much of the variance in social functioning outcome as depression psychopathology. Personality disorder assessment is of predictive utility with longer timeframes and when considering social outcomes as opposed to symptom counts. This utility is sufficiently great that there appears to be value in assessing personality; however, no particular approach outperforms any other.

Should the IDC-9 Trauma Mortality Prediction Model become the new paradigm for benchmarking trauma outcomes?

Science.gov (United States)

Haider, Adil H; Villegas, Cassandra V; Saleem, Taimur; Efron, David T; Stevens, Kent A; Oyetunji, Tolulope A; Cornwell, Edward E; Bowman, Stephen; Haack, Sara; Baker, Susan P; Schneider, Eric B

2012-06-01

Optimum quantification of injury severity remains an imprecise science with a need for improvement. The accuracy of the criterion standard Injury Severity Score (ISS) worsens as a patient's injury severity increases, especially among patients with penetrating trauma. The objective of this study was to comprehensively compare the mortality prediction ability of three anatomic injury severity indices: the ISS, the New ISS (NISS), and the DRG International Classification of Diseases-9th Rev.-Trauma Mortality Prediction Model (TMPM-ICD-9), a recently developed contemporary injury assessment model. Retrospective analysis of patients in the National Trauma Data Bank from 2007 to 2008. The TMPM-ICD-9 values were computed and compared with the ISS and NISS for each patient using in-hospital mortality after trauma as the outcome measure. Discrimination and calibration were compared using the area under the receiver operator characteristic curve. Subgroup analysis was performed to compare each score across varying ranges of injury severity and across different types of injury. A total of 533,898 patients were identified with a crude mortality rate of 4.7%. The ISS and NISS performed equally in the groups with minor (ISS, 1-8) and moderate (ISS, 9-15) injuries, regardless of the injury type. However, in the populations with severe (ISS, 16-24) and very severe (ISS, ≥ 25) injuries for all injury types, the NISS predicted mortality better than the ISS did. The TMPM-ICD-9 outperformed both the NISS and ISS almost consistently. The NISS and TMPM-ICD-9 are both superior predictors of mortality as compared with the ISS. The immediate adoption of NISS for evaluating trauma outcomes using trauma registry data is recommended. The TMPM-ICD-9 may be an even better measure of human injury, and its use in administrative or nonregistry data is suggested. Further research on its attributes is recommended because it has the potential to become the basis for benchmarking trauma outcomes

Learned predictiveness and outcome predictability effects are not simply two sides of the same coin.

Science.gov (United States)

Thorwart, Anna; Livesey, Evan J; Wilhelm, Francisco; Liu, Wei; Lachnit, Harald

2017-10-01

The Learned Predictiveness effect refers to the observation that learning about the relationship between a cue and an outcome is influenced by the predictive relevance of the cue for other outcomes. Similarly, the Outcome Predictability effect refers to a recent observation that the previous predictability of an outcome affects learning about this outcome in new situations, too. We hypothesize that both effects may be two manifestations of the same phenomenon and stimuli that have been involved in highly predictive relationships may be learned about faster when they are involved in new relationships regardless of their functional role in predictive learning as cues and outcomes. Four experiments manipulated both the relationships and the function of the stimuli. While we were able to replicate the standard effects, they did not survive a transfer to situations where the functional role of the stimuli changed, that is the outcome of the first phase becomes a cue in the second learning phase or the cue of the first phase becomes the outcome of the second phase. Furthermore, unlike learned predictiveness, there was little indication that the distribution of overt attention in the second phase was influenced by previous predictability. The results suggest that these 2 very similar effects are not manifestations of a more general phenomenon but rather independent from each other. (PsycINFO Database Record (c) 2017 APA, all rights reserved).

Early Adolescent Affect Predicts Later Life Outcomes.

Science.gov (United States)

Kansky, Jessica; Allen, Joseph P; Diener, Ed

2016-07-01

Subjective well-being as a predictor for later behavior and health has highlighted its relationship to health, work performance, and social relationships. However, the majority of such studies neglect the developmental nature of well-being in contributing to important changes across the transition to adulthood. To examine the potential role of subjective well-being as a long-term predictor of critical life outcomes, we examined indicators of positive and negative affect at age 14 as predictors of relationship, adjustment, self-worth, and career outcomes a decade later at ages 23 to 25, controlling for family income and gender. We utilised multi-informant methods including reports from the target participant, close friends, and romantic partners in a demographically diverse community sample of 184 participants. Early adolescent positive affect predicted fewer relationship problems (less self-reported and partner-reported conflict, and greater friendship attachment as rated by close peers) and healthy adjustment to adulthood (lower levels of depression, anxiety, and loneliness). It also predicted positive work functioning (higher levels of career satisfaction and job competence) and increased self-worth. Negative affect did not significantly predict any of these important life outcomes. In addition to predicting desirable mean levels of later outcomes, early positive affect predicted beneficial changes across time in many outcomes. The findings extend early research on the beneficial outcomes of subjective well-being by having an earlier assessment of well-being, including informant reports in measuring a large variety of outcome variables, and by extending the findings to a lower socioeconomic group of a diverse and younger sample. The results highlight the importance of considering positive affect as an important component of subjective well-being distinct from negative affect. © 2016 The International Association of Applied Psychology.

Predictive Models and Computational Embryology

Science.gov (United States)

EPA’s ‘virtual embryo’ project is building an integrative systems biology framework for predictive models of developmental toxicity. One schema involves a knowledge-driven adverse outcome pathway (AOP) framework utilizing information from public databases, standardized ontologies...

Individualized prediction of seizure relapse and outcomes following antiepileptic drug withdrawal after pediatric epilepsy surgery.

Science.gov (United States)

Lamberink, Herm J; Boshuisen, Kim; Otte, Willem M; Geleijns, Karin; Braun, Kees P J

2018-03-01

The objective of this study was to create a clinically useful tool for individualized prediction of seizure outcomes following antiepileptic drug withdrawal after pediatric epilepsy surgery. We used data from the European retrospective TimeToStop study, which included 766 children from 15 centers, to perform a proportional hazard regression analysis. The 2 outcome measures were seizure recurrence and seizure freedom in the last year of follow-up. Prognostic factors were identified through systematic review of the literature. The strongest predictors for each outcome were selected through backward selection, after which nomograms were created. The final models included 3 to 5 factors per model. Discrimination in terms of adjusted concordance statistic was 0.68 (95% confidence interval [CI] 0.67-0.69) for predicting seizure recurrence and 0.73 (95% CI 0.72-0.75) for predicting eventual seizure freedom. An online prediction tool is provided on www.epilepsypredictiontools.info/ttswithdrawal. The presented models can improve counseling of patients and parents regarding postoperative antiepileptic drug policies, by estimating individualized risks of seizure recurrence and eventual outcome. Wiley Periodicals, Inc. © 2018 International League Against Epilepsy.

The benefit of non contrast-enhanced magnetic resonance angiography for predicting vascular access surgery outcome: a computer model perspective.

Directory of Open Access Journals (Sweden)

Maarten A G Merkx

Full Text Available INTRODUCTION: Vascular access (VA surgery, a prerequisite for hemodialysis treatment of end-stage renal-disease (ESRD patients, is hampered by complication rates, which are frequently related to flow enhancement. To assist in VA surgery planning, a patient-specific computer model for postoperative flow enhancement was developed. The purpose of this study is to assess the benefit of non contrast-enhanced magnetic resonance angiography (NCE-MRA data as patient-specific geometrical input for the model-based prediction of surgery outcome. METHODS: 25 ESRD patients were included in this study. All patients received a NCE-MRA examination of the upper extremity blood vessels in addition to routine ultrasound (US. Local arterial radii were assessed from NCE-MRA and converted to model input using a linear fit per artery. Venous radii were determined with US. The effect of radius measurement uncertainty on model predictions was accounted for by performing Monte-Carlo simulations. The resulting flow prediction interval of the computer model was compared with the postoperative flow obtained from US. Patients with no overlap between model-based prediction and postoperative measurement were further analyzed to determine whether an increase in geometrical detail improved computer model prediction. RESULTS: Overlap between postoperative flows and model-based predictions was obtained for 71% of patients. Detailed inspection of non-overlapping cases revealed that the geometrical details that could be assessed from NCE-MRA explained most of the differences, and moreover, upon addition of these details in the computer model the flow predictions improved. CONCLUSIONS: The results demonstrate clearly that NCE-MRA does provide valuable geometrical information for VA surgery planning. Therefore, it is recommended to use this modality, at least for patients at risk for local or global narrowing of the blood vessels as well as for patients for whom an US-based model

Predicting Social Anxiety Treatment Outcome Based on Therapeutic Email Conversations.

Science.gov (United States)

Hoogendoorn, Mark; Berger, Thomas; Schulz, Ava; Stolz, Timo; Szolovits, Peter

2017-09-01

Predicting therapeutic outcome in the mental health domain is of utmost importance to enable therapists to provide the most effective treatment to a patient. Using information from the writings of a patient can potentially be a valuable source of information, especially now that more and more treatments involve computer-based exercises or electronic conversations between patient and therapist. In this paper, we study predictive modeling using writings of patients under treatment for a social anxiety disorder. We extract a wealth of information from the text written by patients including their usage of words, the topics they talk about, the sentiment of the messages, and the style of writing. In addition, we study trends over time with respect to those measures. We then apply machine learning algorithms to generate the predictive models. Based on a dataset of 69 patients, we are able to show that we can predict therapy outcome with an area under the curve of 0.83 halfway through the therapy and with a precision of 0.78 when using the full data (i.e., the entire treatment period). Due to the limited number of participants, it is hard to generalize the results, but they do show great potential in this type of information.

Macaques can predict social outcomes from facial expressions.

Science.gov (United States)

Waller, Bridget M; Whitehouse, Jamie; Micheletta, Jérôme

2016-09-01

There is widespread acceptance that facial expressions are useful in social interactions, but empirical demonstration of their adaptive function has remained elusive. Here, we investigated whether macaques can use the facial expressions of others to predict the future outcomes of social interaction. Crested macaques (Macaca nigra) were shown an approach between two unknown individuals on a touchscreen and were required to choose between one of two potential social outcomes. The facial expressions of the actors were manipulated in the last frame of the video. One subject reached the experimental stage and accurately predicted different social outcomes depending on which facial expressions the actors displayed. The bared-teeth display (homologue of the human smile) was most strongly associated with predicted friendly outcomes. Contrary to our predictions, screams and threat faces were not associated more with conflict outcomes. Overall, therefore, the presence of any facial expression (compared to neutral) caused the subject to choose friendly outcomes more than negative outcomes. Facial expression in general, therefore, indicated a reduced likelihood of social conflict. The findings dispute traditional theories that view expressions only as indicators of present emotion and instead suggest that expressions form part of complex social interactions where individuals think beyond the present.

Towards single embryo transfer? Modelling clinical outcomes of potential treatment choices using multiple data sources: predictive models and patient perspectives.

Science.gov (United States)

Roberts, Sa; McGowan, L; Hirst, Wm; Brison, Dr; Vail, A; Lieberman, Ba

2010-07-01

In vitro fertilisation (IVF) treatments involve an egg retrieval process, fertilisation and culture of the resultant embryos in the laboratory, and the transfer of embryos back to the mother over one or more transfer cycles. The first transfer is usually of fresh embryos and the remainder may be cryopreserved for future frozen cycles. Most commonly in UK practice two embryos are transferred (double embryo transfer, DET). IVF techniques have led to an increase in the number of multiple births, carrying an increased risk of maternal and infant morbidity. The UK Human Fertilisation and Embryology Authority (HFEA) has adopted a multiple birth minimisation strategy. One way of achieving this would be by increased use of single embryo transfer (SET). To collate cohort data from treatment centres and the HFEA; to develop predictive models for live birth and twinning probabilities from fresh and frozen embryo transfers and predict outcomes from treatment scenarios; to understand patients' perspectives and use the modelling results to investigate the acceptability of twin reduction policies. A multidisciplinary approach was adopted, combining statistical modelling with qualitative exploration of patients' perspectives: interviews were conducted with 27 couples at various stages of IVF treatment at both UK NHS and private clinics; datasets were collated of over 90,000 patients from the HFEA registry and nearly 9000 patients from five clinics, both over the period 2000-5; models were developed to determine live birth and twin outcomes and predict the outcomes of policies for selecting patients for SET or DET in the fresh cycle following egg retrieval and fertilisation, and the predictions were used in simulations of treatments; two focus groups were convened, one NHS and one web based on a patient organisation's website, to present the results of the statistical analyses and explore potential treatment policies. The statistical analysis revealed no characteristics that

Leg pain and psychological variables predict outcome 2-3 years after lumbar fusion surgery.

Science.gov (United States)

Abbott, Allan D; Tyni-Lenné, Raija; Hedlund, Rune

2011-10-01

Prediction studies testing a thorough range of psychological variables in addition to demographic, work-related and clinical variables are lacking in lumbar fusion surgery research. This prospective cohort study aimed at examining predictions of functional disability, back pain and health-related quality of life (HRQOL) 2-3 years after lumbar fusion by regressing nonlinear relations in a multivariate predictive model of pre-surgical variables. Before and 2-3 years after lumbar fusion surgery, patients completed measures investigating demographics, work-related variables, clinical variables, functional self-efficacy, outcome expectancy, fear of movement/(re)injury, mental health and pain coping. Categorical regression with optimal scaling transformation, elastic net regularization and bootstrapping were used to investigate predictor variables and address predictive model validity. The most parsimonious and stable subset of pre-surgical predictor variables explained 41.6, 36.0 and 25.6% of the variance in functional disability, back pain intensity and HRQOL 2-3 years after lumbar fusion. Pre-surgical control over pain significantly predicted functional disability and HRQOL. Pre-surgical catastrophizing and leg pain intensity significantly predicted functional disability and back pain while the pre-surgical straight leg raise significantly predicted back pain. Post-operative psychomotor therapy also significantly predicted functional disability while pre-surgical outcome expectations significantly predicted HRQOL. For the median dichotomised classification of functional disability, back pain intensity and HRQOL levels 2-3 years post-surgery, the discriminative ability of the prediction models was of good quality. The results demonstrate the importance of pre-surgical psychological factors, leg pain intensity, straight leg raise and post-operative psychomotor therapy in the predictions of functional disability, back pain and HRQOL-related outcomes.

Development and validation of clinical prediction models for mortality, functional outcome and cognitive impairment after stroke: a study protocol.

Science.gov (United States)

Fahey, Marion; Rudd, Anthony; Béjot, Yannick; Wolfe, Charles; Douiri, Abdel

2017-08-18

Stroke is a leading cause of adult disability and death worldwide. The neurological impairments associated with stroke prevent patients from performing basic daily activities and have enormous impact on families and caregivers. Practical and accurate tools to assist in predicting outcome after stroke at patient level can provide significant aid for patient management. Furthermore, prediction models of this kind can be useful for clinical research, health economics, policymaking and clinical decision support. 2869 patients with first-ever stroke from South London Stroke Register (SLSR) (1995-2004) will be included in the development cohort. We will use information captured after baseline to construct multilevel models and a Cox proportional hazard model to predict cognitive impairment, functional outcome and mortality up to 5 years after stroke. Repeated random subsampling validation (Monte Carlo cross-validation) will be evaluated in model development. Data from participants recruited to the stroke register (2005-2014) will be used for temporal validation of the models. Data from participants recruited to the Dijon Stroke Register (1985-2015) will be used for external validation. Discrimination, calibration and clinical utility of the models will be presented. Patients, or for patients who cannot consent their relatives, gave written informed consent to participate in stroke-related studies within the SLSR. The SLSR design was approved by the ethics committees of Guy's and St Thomas' NHS Foundation Trust, Kings College Hospital, Queens Square and Westminster Hospitals (London). The Dijon Stroke Registry was approved by the Comité National des Registres and the InVS and has authorisation of the Commission Nationale de l'Informatique et des Libertés. © Article author(s) (or their employer(s) unless otherwise stated in the text of the article) 2017. All rights reserved. No commercial use is permitted unless otherwise expressly granted.

Modeling length of stay as an optimized two-dass prediction problem

NARCIS (Netherlands)

Verduijn, M.; Peek, N.; Voorbraak, F.; de Jonge, E.; de Mol, B. A. J. M.

2007-01-01

Objectives. To develop a predictive model for the outcome length of stay at the Intensive Care Unit (ICU LOS), including the choice of an optimal dichotomization threshold for this outcome. Reduction of prediction problems of this type of outcome to a two-doss problem is a common strategy to

Neonatal Sleep-Wake Analyses Predict 18-month Neurodevelopmental Outcomes.

Science.gov (United States)

Shellhaas, Renée A; Burns, Joseph W; Hassan, Fauziya; Carlson, Martha D; Barks, John D E; Chervin, Ronald D

2017-11-01

The neurological examination of critically ill neonates is largely limited to reflexive behavior. The exam often ignores sleep-wake physiology that may reflect brain integrity and influence long-term outcomes. We assessed whether polysomnography and concurrent cerebral near-infrared spectroscopy (NIRS) might improve prediction of 18-month neurodevelopmental outcomes. Term newborns with suspected seizures underwent standardized neurologic examinations to generate Thompson scores and had 12-hour bedside polysomnography with concurrent cerebral NIRS. For each infant, the distribution of sleep-wake stages and electroencephalogram delta power were computed. NIRS-derived fractional tissue oxygen extraction (FTOE) was calculated across sleep-wake stages. At age 18-22 months, surviving participants were evaluated with Bayley Scales of Infant Development (Bayley-III), 3rd edition. Twenty-nine participants completed Bayley-III. Increased newborn time in quiet sleep predicted worse 18-month cognitive and motor scores (robust regression models, adjusted r2 = 0.22, p = .007, and 0.27, .004, respectively). Decreased 0.5-2 Hz electroencephalograph (EEG) power during quiet sleep predicted worse 18-month language and motor scores (adjusted r2 = 0.25, p = .0005, and 0.33, .001, respectively). Predictive values remained significant after adjustment for neonatal Thompson scores or exposure to phenobarbital. Similarly, an attenuated difference in FTOE, between neonatal wakefulness and quiet sleep, predicted worse 18-month cognitive, language, and motor scores in adjusted analyses (each p sleep-as quantified by increased time in quiet sleep, lower electroencephalogram delta power during that stage, and muted differences in FTOE between quiet sleep and wakefulness-may improve prediction of adverse long-term outcomes for newborns with neurological dysfunction. © Sleep Research Society 2017. Published by Oxford University Press on behalf of the Sleep Research Society. All rights reserved

Risk Prediction Model for Severe Postoperative Complication in Bariatric Surgery.

Science.gov (United States)

Stenberg, Erik; Cao, Yang; Szabo, Eva; Näslund, Erik; Näslund, Ingmar; Ottosson, Johan

2018-01-12

Factors associated with risk for adverse outcome are important considerations in the preoperative assessment of patients for bariatric surgery. As yet, prediction models based on preoperative risk factors have not been able to predict adverse outcome sufficiently. This study aimed to identify preoperative risk factors and to construct a risk prediction model based on these. Patients who underwent a bariatric surgical procedure in Sweden between 2010 and 2014 were identified from the Scandinavian Obesity Surgery Registry (SOReg). Associations between preoperative potential risk factors and severe postoperative complications were analysed using a logistic regression model. A multivariate model for risk prediction was created and validated in the SOReg for patients who underwent bariatric surgery in Sweden, 2015. Revision surgery (standardized OR 1.19, 95% confidence interval (CI) 1.14-0.24, p prediction model. Despite high specificity, the sensitivity of the model was low. Revision surgery, high age, low BMI, large waist circumference, and dyspepsia/GERD were associated with an increased risk for severe postoperative complication. The prediction model based on these factors, however, had a sensitivity that was too low to predict risk in the individual patient case.

AN EFFICIENT PATIENT INFLOW PREDICTION MODEL FOR HOSPITAL RESOURCE MANAGEMENT

Directory of Open Access Journals (Sweden)

Kottalanka Srikanth

2017-07-01

Full Text Available There has been increasing demand in improving service provisioning in hospital resources management. Hospital industries work with strict budget constraint at the same time assures quality care. To achieve quality care with budget constraint an efficient prediction model is required. Recently there has been various time series based prediction model has been proposed to manage hospital resources such ambulance monitoring, emergency care and so on. These models are not efficient as they do not consider the nature of scenario such climate condition etc. To address this artificial intelligence is adopted. The issues with existing prediction are that the training suffers from local optima error. This induces overhead and affects the accuracy in prediction. To overcome the local minima error, this work presents a patient inflow prediction model by adopting resilient backpropagation neural network. Experiment are conducted to evaluate the performance of proposed model inter of RMSE and MAPE. The outcome shows the proposed model reduces RMSE and MAPE over existing back propagation based artificial neural network. The overall outcomes show the proposed prediction model improves the accuracy of prediction which aid in improving the quality of health care management.

Factors Influencing the Predictive Power of Models for Predicting Mortality and/or Heart Failure Hospitalization in Patients With Heart Failure

NARCIS (Netherlands)

Ouwerkerk, Wouter; Voors, Adriaan A.; Zwinderman, Aeilko H.

2014-01-01

The present paper systematically reviews and compares existing prediction models in order to establish the strongest variables, models, and model characteristics in patients with heart failure predicting outcome. To improve decision making accurately predicting mortality and heart-failure

The Use of Artificial Neural Networks in Prediction of Congenital CMV Outcome from Sequence Data

Directory of Open Access Journals (Sweden)

Ravit Arav-Boger

2008-01-01

Full Text Available A large number of CMV strains has been reported to circulate in the human population, and the biological significance of these strains is currently an active area of research. The analysis of complex genetic information may be limited using conventional phylogenetic techniques. We constructed artificial neural networks to determine their feasibility in predicting the outcome of congenital CMV disease (defined as presence of CMV symptoms at birth based on two data sets: 54 sequences of CMV gene UL144 obtained from 54 amniotic fluids of women who contracted acute CMV infection during their pregnancy, and 80 sequences of 4 genes (US28, UL144, UL146 and UL147 obtained from urine, saliva or blood of 20 congenitally infected infants that displayed different outcomes at birth. When data from all four genes was used in the 20-infants’ set, the artificial neural network model accurately identified outcome in 90% of cases. While US28 and UL147 had low yield in predicting outcome, UL144 and UL146 predicted outcome in 80% and 85% respectively when used separately. The model identified specific nucleotide positions that were highly relevant to prediction of outcome. The artificial neural network classified genotypes in agreement with classic phylogenetic analysis. We suggest that artificial neural networks can accurately and efficiently analyze sequences obtained from larger cohorts to determine specific outcomes.The ANN training and analysis code is commercially available from Optimal Neural Informatics (Pikesville, MD.

Machine learning for outcome prediction of acute ischemic stroke post intra-arterial therapy.

Directory of Open Access Journals (Sweden)

Hamed Asadi

Full Text Available INTRODUCTION: Stroke is a major cause of death and disability. Accurately predicting stroke outcome from a set of predictive variables may identify high-risk patients and guide treatment approaches, leading to decreased morbidity. Logistic regression models allow for the identification and validation of predictive variables. However, advanced machine learning algorithms offer an alternative, in particular, for large-scale multi-institutional data, with the advantage of easily incorporating newly available data to improve prediction performance. Our aim was to design and compare different machine learning methods, capable of predicting the outcome of endovascular intervention in acute anterior circulation ischaemic stroke. METHOD: We conducted a retrospective study of a prospectively collected database of acute ischaemic stroke treated by endovascular intervention. Using SPSS®, MATLAB®, and Rapidminer®, classical statistics as well as artificial neural network and support vector algorithms were applied to design a supervised machine capable of classifying these predictors into potential good and poor outcomes. These algorithms were trained, validated and tested using randomly divided data. RESULTS: We included 107 consecutive acute anterior circulation ischaemic stroke patients treated by endovascular technique. Sixty-six were male and the mean age of 65.3. All the available demographic, procedural and clinical factors were included into the models. The final confusion matrix of the neural network, demonstrated an overall congruency of ∼ 80% between the target and output classes, with favourable receiving operative characteristics. However, after optimisation, the support vector machine had a relatively better performance, with a root mean squared error of 2.064 (SD: ± 0.408. DISCUSSION: We showed promising accuracy of outcome prediction, using supervised machine learning algorithms, with potential for incorporation of larger multicenter

Cerebrospinal fluid neurofilament light chain levels predict visual outcome after optic neuritis

DEFF Research Database (Denmark)

Modvig, Signe; Degn, M; Sander, B

2016-01-01

BACKGROUND: Optic neuritis is a good model for multiple sclerosis relapse, but currently no tests can accurately predict visual outcome. OBJECTIVE: The purpose of this study was to examine whether cerebrospinal fluid (CSF) biomarkers of tissue damage and remodelling (neurofilament light chain (NF......-L, β=-1.1, p=0.0150 for GC-IPL). Complete/incomplete remission was determined based on LCVA from 30 healthy controls. NF-L had a positive predictive value of 91% and an area under the curve (AUC) of 0.79 for incomplete remission. CONCLUSION: CSF NF-L is a promising biomarker of visual outcome after...

Setting the vision: applied patient-reported outcomes and smart, connected digital healthcare systems to improve patient-centered outcomes prediction in critical illness.

Science.gov (United States)

Wysham, Nicholas G; Abernethy, Amy P; Cox, Christopher E

2014-10-01

Prediction models in critical illness are generally limited to short-term mortality and uncommonly include patient-centered outcomes. Current outcome prediction tools are also insensitive to individual context or evolution in healthcare practice, potentially limiting their value over time. Improved prognostication of patient-centered outcomes in critical illness could enhance decision-making quality in the ICU. Patient-reported outcomes have emerged as precise methodological measures of patient-centered variables and have been successfully employed using diverse platforms and technologies, enhancing the value of research in critical illness survivorship and in direct patient care. The learning health system is an emerging ideal characterized by integration of multiple data sources into a smart and interconnected health information technology infrastructure with the goal of rapidly optimizing patient care. We propose a vision of a smart, interconnected learning health system with integrated electronic patient-reported outcomes to optimize patient-centered care, including critical care outcome prediction. A learning health system infrastructure integrating electronic patient-reported outcomes may aid in the management of critical illness-associated conditions and yield tools to improve prognostication of patient-centered outcomes in critical illness.

Combining clinical variables to optimize prediction of antidepressant treatment outcomes.

Science.gov (United States)

Iniesta, Raquel; Malki, Karim; Maier, Wolfgang; Rietschel, Marcella; Mors, Ole; Hauser, Joanna; Henigsberg, Neven; Dernovsek, Mojca Zvezdana; Souery, Daniel; Stahl, Daniel; Dobson, Richard; Aitchison, Katherine J; Farmer, Anne; Lewis, Cathryn M; McGuffin, Peter; Uher, Rudolf

2016-07-01

The outcome of treatment with antidepressants varies markedly across people with the same diagnosis. A clinically significant prediction of outcomes could spare the frustration of trial and error approach and improve the outcomes of major depressive disorder through individualized treatment selection. It is likely that a combination of multiple predictors is needed to achieve such prediction. We used elastic net regularized regression to optimize prediction of symptom improvement and remission during treatment with escitalopram or nortriptyline and to identify contributing predictors from a range of demographic and clinical variables in 793 adults with major depressive disorder. A combination of demographic and clinical variables, with strong contributions from symptoms of depressed mood, reduced interest, decreased activity, indecisiveness, pessimism and anxiety significantly predicted treatment outcomes, explaining 5-10% of variance in symptom improvement with escitalopram. Similar combinations of variables predicted remission with area under the curve 0.72, explaining approximately 15% of variance (pseudo R(2)) in who achieves remission, with strong contributions from body mass index, appetite, interest-activity symptom dimension and anxious-somatizing depression subtype. Escitalopram-specific outcome prediction was more accurate than generic outcome prediction, and reached effect sizes that were near or above a previously established benchmark for clinical significance. Outcome prediction on the nortriptyline arm did not significantly differ from chance. These results suggest that easily obtained demographic and clinical variables can predict therapeutic response to escitalopram with clinically meaningful accuracy, suggesting a potential for individualized prescription of this antidepressant drug. Copyright © 2016 The Authors. Published by Elsevier Ltd.. All rights reserved.

An MEG signature corresponding to an axiomatic model of reward prediction error.

Science.gov (United States)

Talmi, Deborah; Fuentemilla, Lluis; Litvak, Vladimir; Duzel, Emrah; Dolan, Raymond J

2012-01-02

Optimal decision-making is guided by evaluating the outcomes of previous decisions. Prediction errors are theoretical teaching signals which integrate two features of an outcome: its inherent value and prior expectation of its occurrence. To uncover the magnetic signature of prediction errors in the human brain we acquired magnetoencephalographic (MEG) data while participants performed a gambling task. Our primary objective was to use formal criteria, based upon an axiomatic model (Caplin and Dean, 2008a), to determine the presence and timing profile of MEG signals that express prediction errors. We report analyses at the sensor level, implemented in SPM8, time locked to outcome onset. We identified, for the first time, a MEG signature of prediction error, which emerged approximately 320 ms after an outcome and expressed as an interaction between outcome valence and probability. This signal followed earlier, separate signals for outcome valence and probability, which emerged approximately 200 ms after an outcome. Strikingly, the time course of the prediction error signal, as well as the early valence signal, resembled the Feedback-Related Negativity (FRN). In simultaneously acquired EEG data we obtained a robust FRN, but the win and loss signals that comprised this difference wave did not comply with the axiomatic model. Our findings motivate an explicit examination of the critical issue of timing embodied in computational models of prediction errors as seen in human electrophysiological data. Copyright © 2011 Elsevier Inc. All rights reserved.

Dynamic prediction of patient outcomes during ongoing cardiopulmonary resuscitation.

Science.gov (United States)

Kim, Joonghee; Kim, Kyuseok; Callaway, Clifton W; Doh, Kibbeum; Choi, Jungho; Park, Jongdae; Jo, You Hwan; Lee, Jae Hyuk

2017-02-01

The probability of the return of spontaneous circulation (ROSC) and subsequent favourable outcomes changes dynamically during advanced cardiac life support (ACLS). We sought to model these changes using time-to-event analysis in out-of-hospital cardiac arrest (OHCA) patients. Adult (≥18 years old), non-traumatic OHCA patients without prehospital ROSC were included. Utstein variables and initial arterial blood gas measurements were used as predictors. The incidence rate of ROSC during the first 30min of ACLS in the emergency department (ED) was modelled using spline-based parametric survival analysis. Conditional probabilities of subsequent outcomes after ROSC (1-week and 1-month survival and 6-month neurologic recovery) were modelled using multivariable logistic regression. The ROSC and conditional probability models were then combined to estimate the likelihood of achieving ROSC and subsequent outcomes by providing k additional minutes of effort. A total of 727 patients were analyzed. The incidence rate of ROSC increased rapidly until the 10th minute of ED ACLS, and it subsequently decreased. The conditional probabilities of subsequent outcomes after ROSC were also dependent on the duration of resuscitation with odds ratios for 1-week and 1-month survival and neurologic recovery of 0.93 (95% CI: 0.90-0.96, p<0.001), 0.93 (0.88-0.97, p=0.001) and 0.93 (0.87-0.99, p=0.031) per 1-min increase, respectively. Calibration testing of the combined models showed good correlation between mean predicted probability and actual prevalence. The probability of ROSC and favourable subsequent outcomes changed according to a multiphasic pattern over the first 30min of ACLS, and modelling of the dynamic changes was feasible. Copyright © 2016 Elsevier Ireland Ltd. All rights reserved.

Boolean network model for cancer pathways: predicting carcinogenesis and targeted therapy outcomes.

Directory of Open Access Journals (Sweden)

Herman F Fumiã

Full Text Available A Boolean dynamical system integrating the main signaling pathways involved in cancer is constructed based on the currently known protein-protein interaction network. This system exhibits stationary protein activation patterns--attractors--dependent on the cell's microenvironment. These dynamical attractors were determined through simulations and their stabilities against mutations were tested. In a higher hierarchical level, it was possible to group the network attractors into distinct cell phenotypes and determine driver mutations that promote phenotypic transitions. We find that driver nodes are not necessarily central in the network topology, but at least they are direct regulators of central components towards which converge or through which crosstalk distinct cancer signaling pathways. The predicted drivers are in agreement with those pointed out by diverse census of cancer genes recently performed for several human cancers. Furthermore, our results demonstrate that cell phenotypes can evolve towards full malignancy through distinct sequences of accumulated mutations. In particular, the network model supports routes of carcinogenesis known for some tumor types. Finally, the Boolean network model is employed to evaluate the outcome of molecularly targeted cancer therapies. The major find is that monotherapies were additive in their effects and that the association of targeted drugs is necessary for cancer eradication.

A points-based algorithm for prognosticating clinical outcome of Chiari malformation Type I with syringomyelia: results from a predictive model analysis of 82 surgically managed adult patients.

Science.gov (United States)

Thakar, Sumit; Sivaraju, Laxminadh; Jacob, Kuruthukulangara S; Arun, Aditya Atal; Aryan, Saritha; Mohan, Dilip; Sai Kiran, Narayanam Anantha; Hegde, Alangar S

2018-01-01

OBJECTIVE Although various predictors of postoperative outcome have been previously identified in patients with Chiari malformation Type I (CMI) with syringomyelia, there is no known algorithm for predicting a multifactorial outcome measure in this widely studied disorder. Using one of the largest preoperative variable arrays used so far in CMI research, the authors attempted to generate a formula for predicting postoperative outcome. METHODS Data from the clinical records of 82 symptomatic adult patients with CMI and altered hindbrain CSF flow who were managed with foramen magnum decompression, C-1 laminectomy, and duraplasty over an 8-year period were collected and analyzed. Various preoperative clinical and radiological variables in the 57 patients who formed the study cohort were assessed in a bivariate analysis to determine their ability to predict clinical outcome (as measured on the Chicago Chiari Outcome Scale [CCOS]) and the resolution of syrinx at the last follow-up. The variables that were significant in the bivariate analysis were further analyzed in a multiple linear regression analysis. Different regression models were tested, and the model with the best prediction of CCOS was identified and internally validated in a subcohort of 25 patients. RESULTS There was no correlation between CCOS score and syrinx resolution (p = 0.24) at a mean ± SD follow-up of 40.29 ± 10.36 months. Multiple linear regression analysis revealed that the presence of gait instability, obex position, and the M-line-fourth ventricle vertex (FVV) distance correlated with CCOS score, while the presence of motor deficits was associated with poor syrinx resolution (p ≤ 0.05). The algorithm generated from the regression model demonstrated good diagnostic accuracy (area under curve 0.81), with a score of more than 128 points demonstrating 100% specificity for clinical improvement (CCOS score of 11 or greater). The model had excellent reliability (κ = 0.85) and was validated with

Fronto-Temporal Connectivity Predicts ECT Outcome in Major Depression

Directory of Open Access Journals (Sweden)

Amber M. Leaver

2018-03-01

Full Text Available BackgroundElectroconvulsive therapy (ECT is arguably the most effective available treatment for severe depression. Recent studies have used MRI data to predict clinical outcome to ECT and other antidepressant therapies. One challenge facing such studies is selecting from among the many available metrics, which characterize complementary and sometimes non-overlapping aspects of brain function and connectomics. Here, we assessed the ability of aggregated, functional MRI metrics of basal brain activity and connectivity to predict antidepressant response to ECT using machine learning.MethodsA radial support vector machine was trained using arterial spin labeling (ASL and blood-oxygen-level-dependent (BOLD functional magnetic resonance imaging (fMRI metrics from n = 46 (26 female, mean age 42 depressed patients prior to ECT (majority right-unilateral stimulation. Image preprocessing was applied using standard procedures, and metrics included cerebral blood flow in ASL, and regional homogeneity, fractional amplitude of low-frequency modulations, and graph theory metrics (strength, local efficiency, and clustering in BOLD data. A 5-repeated 5-fold cross-validation procedure with nested feature-selection validated model performance. Linear regressions were applied post hoc to aid interpretation of discriminative features.ResultsThe range of balanced accuracy in models performing statistically above chance was 58–68%. Here, prediction of non-responders was slightly higher than for responders (maximum performance 74 and 64%, respectively. Several features were consistently selected across cross-validation folds, mostly within frontal and temporal regions. Among these were connectivity strength among: a fronto-parietal network [including left dorsolateral prefrontal cortex (DLPFC], motor and temporal networks (near ECT electrodes, and/or subgenual anterior cingulate cortex (sgACC.ConclusionOur data indicate that pattern classification of multimodal f

Machine learning approach for the outcome prediction of temporal lobe epilepsy surgery.

Directory of Open Access Journals (Sweden)

Rubén Armañanzas

Full Text Available Epilepsy surgery is effective in reducing both the number and frequency of seizures, particularly in temporal lobe epilepsy (TLE. Nevertheless, a significant proportion of these patients continue suffering seizures after surgery. Here we used a machine learning approach to predict the outcome of epilepsy surgery based on supervised classification data mining taking into account not only the common clinical variables, but also pathological and neuropsychological evaluations. We have generated models capable of predicting whether a patient with TLE secondary to hippocampal sclerosis will fully recover from epilepsy or not. The machine learning analysis revealed that outcome could be predicted with an estimated accuracy of almost 90% using some clinical and neuropsychological features. Importantly, not all the features were needed to perform the prediction; some of them proved to be irrelevant to the prognosis. Personality style was found to be one of the key features to predict the outcome. Although we examined relatively few cases, findings were verified across all data, showing that the machine learning approach described in the present study may be a powerful method. Since neuropsychological assessment of epileptic patients is a standard protocol in the pre-surgical evaluation, we propose to include these specific psychological tests and machine learning tools to improve the selection of candidates for epilepsy surgery.

An evidence-based decision assistance model for predicting training outcome in juvenile guide dogs.

Science.gov (United States)

Harvey, Naomi D; Craigon, Peter J; Blythe, Simon A; England, Gary C W; Asher, Lucy

2017-01-01

Working dog organisations, such as Guide Dogs, need to regularly assess the behaviour of the dogs they train. In this study we developed a questionnaire-style behaviour assessment completed by training supervisors of juvenile guide dogs aged 5, 8 and 12 months old (n = 1,401), and evaluated aspects of its reliability and validity. Specifically, internal reliability, temporal consistency, construct validity, predictive criterion validity (comparing against later training outcome) and concurrent criterion validity (comparing against a standardised behaviour test) were evaluated. Thirty-nine questions were sourced either from previously published literature or created to meet requirements identified via Guide Dogs staff surveys and staff feedback. Internal reliability analyses revealed seven reliable and interpretable trait scales named according to the questions within them as: Adaptability; Body Sensitivity; Distractibility; Excitability; General Anxiety; Trainability and Stair Anxiety. Intra-individual temporal consistency of the scale scores between 5-8, 8-12 and 5-12 months was high. All scales excepting Body Sensitivity showed some degree of concurrent criterion validity. Predictive criterion validity was supported for all seven scales, since associations were found with training outcome, at at-least one age. Thresholds of z-scores on the scales were identified that were able to distinguish later training outcome by identifying 8.4% of all dogs withdrawn for behaviour and 8.5% of all qualified dogs, with 84% and 85% specificity. The questionnaire assessment was reliable and could detect traits that are consistent within individuals over time, despite juvenile dogs undergoing development during the study period. By applying thresholds to scores produced from the questionnaire this assessment could prove to be a highly valuable decision-making tool for Guide Dogs. This is the first questionnaire-style assessment of juvenile dogs that has shown value in predicting

Neural Fuzzy Inference System-Based Weather Prediction Model and Its Precipitation Predicting Experiment

Directory of Open Access Journals (Sweden)

Jing Lu

2014-11-01

Full Text Available We propose a weather prediction model in this article based on neural network and fuzzy inference system (NFIS-WPM, and then apply it to predict daily fuzzy precipitation given meteorological premises for testing. The model consists of two parts: the first part is the “fuzzy rule-based neural network”, which simulates sequential relations among fuzzy sets using artificial neural network; and the second part is the “neural fuzzy inference system”, which is based on the first part, but could learn new fuzzy rules from the previous ones according to the algorithm we proposed. NFIS-WPM (High Pro and NFIS-WPM (Ave are improved versions of this model. It is well known that the need for accurate weather prediction is apparent when considering the benefits. However, the excessive pursuit of accuracy in weather prediction makes some of the “accurate” prediction results meaningless and the numerical prediction model is often complex and time-consuming. By adapting this novel model to a precipitation prediction problem, we make the predicted outcomes of precipitation more accurate and the prediction methods simpler than by using the complex numerical forecasting model that would occupy large computation resources, be time-consuming and which has a low predictive accuracy rate. Accordingly, we achieve more accurate predictive precipitation results than by using traditional artificial neural networks that have low predictive accuracy.

Phototherapy of the newborn: a predictive model for the outcome.

Science.gov (United States)

Ossamu Osaku, Nelson; Silverio Lopes, Heitor

2005-01-01

Jaundice in one of the most common problems of the newborn. In most cases, jaundice is considered a physiological transient situation, but sometimes it can lead to death or serious injuries for the survivors. For decades, phototherapy has been used as the main method for prevention and treatment of hyperbilirubinaemia of the newborn. This work aims at finding a predictive model for the decrement of blood bilirubin followed conventional phototherapy. Data from 90 patients were collected and used in the multiple regression method. A rigorous statistical analysis was done in order to guarantee a correct and valid model. The obtained model was able to explain 78% of the variation of the dependent variable We found that it is possible to predict the total sugar bilirubin of the patient under phototherapy by knowing its birth weight, bilirubin level at the beginning of treatment, duration of exposition, and irradiance. Besides, it is possible to infer the time necessary for a given decrement of bilirubin, under approximately constant irradiance.

Outcome Prediction after Radiotherapy with Medical Big Data.

Science.gov (United States)

Magome, Taiki

2016-01-01

Data science is becoming more important in many fields. In medical physics field, we are facing huge data every day. Treatment outcomes after radiation therapy are determined by complex interactions between clinical, biological, and dosimetrical factors. A key concept of recent radiation oncology research is to predict the outcome based on medical big data for personalized medicine. Here, some reports, which are analyzing medical databases with machine learning techniques, were reviewed and feasibility of outcome prediction after radiation therapy was discussed. In addition, some strategies for saving manual labors to analyze huge data in medical physics were discussed.

Presurgery resting-state local graph-theory measures predict neurocognitive outcomes after brain surgery in temporal lobe epilepsy.

Science.gov (United States)

Doucet, Gaelle E; Rider, Robert; Taylor, Nathan; Skidmore, Christopher; Sharan, Ashwini; Sperling, Michael; Tracy, Joseph I

2015-04-01

This study determined the ability of resting-state functional connectivity (rsFC) graph-theory measures to predict neurocognitive status postsurgery in patients with temporal lobe epilepsy (TLE) who underwent anterior temporal lobectomy (ATL). A presurgical resting-state functional magnetic resonance imaging (fMRI) condition was collected in 16 left and 16 right TLE patients who underwent ATL. In addition, patients received neuropsychological testing pre- and postsurgery in verbal and nonverbal episodic memory, language, working memory, and attention domains. Regarding the functional data, we investigated three graph-theory properties (local efficiency, distance, and participation), measuring segregation, integration and centrality, respectively. These measures were only computed in regions of functional relevance to the ictal pathology, or the cognitive domain. Linear regression analyses were computed to predict the change in each neurocognitive domain. Our analyses revealed that cognitive outcome was successfully predicted with at least 68% of the variance explained in each model, for both TLE groups. The only model not significantly predictive involved nonverbal episodic memory outcome in right TLE. Measures involving the healthy hippocampus were the most common among the predictors, suggesting that enhanced integration of this structure with the rest of the brain may improve cognitive outcomes. Regardless of TLE group, left inferior frontal regions were the best predictors of language outcome. Working memory outcome was predicted mostly by right-sided regions, in both groups. Overall, the results indicated our integration measure was the most predictive of neurocognitive outcome. In contrast, our segregation measure was the least predictive. This study provides evidence that presurgery rsFC measures may help determine neurocognitive outcomes following ATL. The results have implications for refining our understanding of compensatory reorganization and predicting

Validity of a simple Internet-based outcome-prediction tool in patients with total hip replacement: a pilot study.

Science.gov (United States)

Stöckli, Cornel; Theiler, Robert; Sidelnikov, Eduard; Balsiger, Maria; Ferrari, Stephen M; Buchzig, Beatus; Uehlinger, Kurt; Riniker, Christoph; Bischoff-Ferrari, Heike A

2014-04-01

We developed a user-friendly Internet-based tool for patients undergoing total hip replacement (THR) due to osteoarthritis to predict their pain and function after surgery. In the first step, the key questions were identified by statistical modelling in a data set of 375 patients undergoing THR. Based on multiple regression, we identified the two most predictive WOMAC questions for pain and the three most predictive WOMAC questions for functional outcome, while controlling for comorbidity, body mass index, age, gender and specific comorbidities relevant to the outcome. In the second step, a pilot study was performed to validate the resulting tool against the full WOMAC questionnaire among 108 patients undergoing THR. The mean difference between observed (WOMAC) and model-predicted value was -1.1 points (95% confidence interval, CI -3.8, 1.5) for pain and -2.5 points (95% CI -5.3, 0.3) for function. The model-predicted value was within 20% of the observed value in 48% of cases for pain and in 57% of cases for function. The tool demonstrated moderate validity, but performed weakly for patients with extreme levels of pain and extreme functional limitations at 3 months post surgery. This may have been partly due to early complications after surgery. However, the outcome-prediction tool may be useful in helping patients to become better informed about the realistic outcome of their THR.

Artificial Neural Network System to Predict the Postoperative Outcome of Percutaneous Nephrolithotomy.

Science.gov (United States)

Aminsharifi, Alireza; Irani, Dariush; Pooyesh, Shima; Parvin, Hamid; Dehghani, Sakineh; Yousofi, Khalilolah; Fazel, Ebrahim; Zibaie, Fatemeh

2017-05-01

To construct, train, and apply an artificial neural network (ANN) system for prediction of different outcome variables of percutaneous nephrolithotomy (PCNL). We calculated predictive accuracy, sensitivity, and precision for each outcome variable. During the study period, all adult patients who underwent PCNL at our institute were enrolled in the study. Preoperative and postoperative variables were recorded, and stone-free status was assessed perioperatively with computed tomography scans. MATLAB software was used to design and train the network in a feed forward back-propagation error adjustment scheme. Preoperative and postoperative data from 200 patients (training set) were used to analyze the effect and relative relevance of preoperative values on postoperative parameters. The validated adequately trained ANN was used to predict postoperative outcomes in the subsequent 254 adult patients (test set) whose preoperative values were serially fed into the system. To evaluate system accuracy in predicting each postoperative variable, predicted values were compared with actual outcomes. Two hundred fifty-four patients (155 [61%] males) were considered the test set. Mean stone burden was 6702.86 ± 381.6 mm 3 . Overall stone-free rate was 76.4%. Fifty-four out of 254 patients (21.3%) required ancillary procedures (shockwave lithotripsy 5.9%, transureteral lithotripsy 10.6%, and repeat PCNL 4.7%). The accuracy and sensitivity of the system in predicting different postoperative variables ranged from 81.0% to 98.2%. As a complex nonlinear mathematical model, our ANN system is an interconnected data mining tool, which prospectively analyzes and "learns" the relationships between variables. The accuracy and sensitivity of the system for predicting the stone-free rate, the need for blood transfusion, and post-PCNL ancillary procedures ranged from 81.0% to 98.2%.The stone burden and the stone morphometry were among the most significant preoperative characteristics that

A simple solution for model comparison in bold imaging: the special case of reward prediction error and reward outcomes.

Science.gov (United States)

Erdeniz, Burak; Rohe, Tim; Done, John; Seidler, Rachael D

2013-01-01

Conventional neuroimaging techniques provide information about condition-related changes of the BOLD (blood-oxygen-level dependent) signal, indicating only where and when the underlying cognitive processes occur. Recently, with the help of a new approach called "model-based" functional neuroimaging (fMRI), researchers are able to visualize changes in the internal variables of a time varying learning process, such as the reward prediction error or the predicted reward value of a conditional stimulus. However, despite being extremely beneficial to the imaging community in understanding the neural correlates of decision variables, a model-based approach to brain imaging data is also methodologically challenging due to the multicollinearity problem in statistical analysis. There are multiple sources of multicollinearity in functional neuroimaging including investigations of closely related variables and/or experimental designs that do not account for this. The source of multicollinearity discussed in this paper occurs due to correlation between different subjective variables that are calculated very close in time. Here, we review methodological approaches to analyzing such data by discussing the special case of separating the reward prediction error signal from reward outcomes.

Do personality traits predict outcome of psychodynamically oriented psychosomatic inpatient treatment beyond initial symptoms?

Science.gov (United States)

Steinert, Christiane; Klein, Susanne; Leweke, Frank; Leichsenring, Falk

2015-03-01

Whether personality characteristics have an impact on treatment outcome is an important question in psychotherapy research. One of the most common approaches for the description of personality is the five-factor model of personality. Only few studies investigated whether patient personality as measured with the NEO-Five-Factor Inventory (NEO-FFI, Costa & McCrae [1992b]. Revised NEO-PI-R and NEO-FFI. Professional manual. Odessa, FL: Psychological Assessment Recources) predicts outcome. Results were inconsistent. Studies reporting personality to be predictive of outcome did not control for baseline symptoms, while studies controlling initial symptoms could not support these findings. We hypothesized that after taking into account baseline symptoms, the NEO-FFI would not predict outcome and tested this in a large sample of inpatients at a psychosomatic clinic. Naturalistic, non-controlled study using patients' data for multiple regression analysis to identify predictors of outcome. Data of 254 inpatients suffering primarily from depressive, anxiety, stress, and somatoform disorders were analysed. Personality was assessed at the beginning of therapy. For psychotherapy outcome, changes in anxiety and depression (Hospital Anxiety and Depression Scale; HADS), overall psychopathology (Symptom Checklist-90-R Global Severity Index [GSI]), and interpersonal problems (Inventory of Interpersonal Problems; IIP) were measured. The treatment resulted in significant decreases on all outcome measures corresponding to moderate to large effect sizes (HADS: d = 1.03; GSI: d = 0.90; IIP: d = 0.38). Consistent with our hypothesis, none of the personality domains predicted outcome when baseline symptoms were controlled for. Personality assessment at baseline does not seem to have an added value in the prediction of inpatient psychotherapy outcome beyond initial symptoms. Clinical implications Personality dimensions overlap with symptomatic distress. Rather than serve as predictors of

Massive Predictive Modeling using Oracle R Enterprise

CERN Multimedia

CERN. Geneva

2014-01-01

R is fast becoming the lingua franca for analyzing data via statistics, visualization, and predictive analytics. For enterprise-scale data, R users have three main concerns: scalability, performance, and production deployment. Oracle's R-based technologies - Oracle R Distribution, Oracle R Enterprise, Oracle R Connector for Hadoop, and the R package ROracle - address these concerns. In this talk, we introduce Oracle's R technologies, highlighting how each enables R users to achieve scalability and performance while making production deployment of R results a natural outcome of the data analyst/scientist efforts. The focus then turns to Oracle R Enterprise with code examples using the transparency layer and embedded R execution, targeting massive predictive modeling. One goal behind massive predictive modeling is to build models per entity, such as customers, zip codes, simulations, in an effort to understand behavior and tailor predictions at the entity level. Predictions...

Predictive Models and Computational Toxicology (II IBAMTOX)

Science.gov (United States)

EPA’s ‘virtual embryo’ project is building an integrative systems biology framework for predictive models of developmental toxicity. One schema involves a knowledge-driven adverse outcome pathway (AOP) framework utilizing information from public databases, standardized ontologies...

How adverse outcome pathways can aid the development and use of computational prediction models for regulatory toxicology

Science.gov (United States)

Efforts are underway to transform regulatory toxicology and chemical safety assessment from a largely empirical science based on direct observation of apical toxicity outcomes in whole organism toxicity tests to a predictive one in which outcomes and risk are inferred from accumu...

Prediction of outcome in patients with low back pain

DEFF Research Database (Denmark)

Kongsted, Alice; Andersen, Cathrine Hedegaard; Mørk Hansen, Martin

2016-01-01

The clinical course of low back pain (LBP) cannot be accurately predicted by existing prediction tools. Therefore clinicians rely largely on their experience and clinical judgement. The objectives of this study were to investigate 1) which patient characteristics were associated with chiropractors...... intensity (0-10) and disability (RMDQ) after 2-weeks, 3-months, and 12-months. The course of LBP in 859 patients was predicted to be short (54%), prolonged (36%), or chronic (7%). Clinicians' expectations were most strongly associated with education, LBP history, radiating pain, and neurological signs......' expectations of outcome from a LBP episode, 2) if clinicians' expectations related to outcome, 3) how accurate clinical predictions were as compared to those of the STarT Back Screening Tool (SBT), and 4) if accuracy was improved by combining clinicians' expectations and the SBT. Outcomes were measured as LBP...

Discrimination measures for survival outcomes: connection between the AUC and the predictiveness curve.

Science.gov (United States)

Viallon, Vivian; Latouche, Aurélien

2011-03-01

Finding out biomarkers and building risk scores to predict the occurrence of survival outcomes is a major concern of clinical epidemiology, and so is the evaluation of prognostic models. In this paper, we are concerned with the estimation of the time-dependent AUC--area under the receiver-operating curve--which naturally extends standard AUC to the setting of survival outcomes and enables to evaluate the discriminative power of prognostic models. We establish a simple and useful relation between the predictiveness curve and the time-dependent AUC--AUC(t). This relation confirms that the predictiveness curve is the key concept for evaluating calibration and discrimination of prognostic models. It also highlights that accurate estimates of the conditional absolute risk function should yield accurate estimates for AUC(t). From this observation, we derive several estimators for AUC(t) relying on distinct estimators of the conditional absolute risk function. An empirical study was conducted to compare our estimators with the existing ones and assess the effect of model misspecification--when estimating the conditional absolute risk function--on the AUC(t) estimation. We further illustrate the methodology on the Mayo PBC and the VA lung cancer data sets. Copyright © 2011 WILEY-VCH Verlag GmbH & Co. KGaA, Weinheim.

Semen molecular and cellular features: these parameters can reliably predict subsequent ART outcome in a goat model

Directory of Open Access Journals (Sweden)

Mereu Paolo

2009-11-01

Full Text Available Abstract Currently, the assessment of sperm function in a raw or processed semen sample is not able to reliably predict sperm ability to withstand freezing and thawing procedures and in vivo fertility and/or assisted reproductive biotechnologies (ART outcome. The aim of the present study was to investigate which parameters among a battery of analyses could predict subsequent spermatozoa in vitro fertilization ability and hence blastocyst output in a goat model. Ejaculates were obtained by artificial vagina from 3 adult goats (Capra hircus aged 2 years (A, B and C. In order to assess the predictive value of viability, computer assisted sperm analyzer (CASA motility parameters and ATP intracellular concentration before and after thawing and of DNA integrity after thawing on subsequent embryo output after an in vitro fertility test, a logistic regression analysis was used. Individual differences in semen parameters were evident for semen viability after thawing and DNA integrity. Results of IVF test showed that spermatozoa collected from A and B lead to higher cleavage rates (0

Joint hierarchical Gaussian process model with application to personalized prediction in medical monitoring.

Science.gov (United States)

Duan, Leo L; Wang, Xia; Clancy, John P; Szczesniak, Rhonda D

2018-01-01

A two-level Gaussian process (GP) joint model is proposed to improve personalized prediction of medical monitoring data. The proposed model is applied to jointly analyze multiple longitudinal biomedical outcomes, including continuous measurements and binary outcomes, to achieve better prediction in disease progression. At the population level of the hierarchy, two independent GPs are used to capture the nonlinear trends in both the continuous biomedical marker and the binary outcome, respectively; at the individual level, a third GP, which is shared by the longitudinal measurement model and the longitudinal binary model, induces the correlation between these two model components and strengthens information borrowing across individuals. The proposed model is particularly advantageous in personalized prediction. It is applied to the motivating clinical data on cystic fibrosis disease progression, for which lung function measurements and onset of acute respiratory events are monitored jointly throughout each patient's clinical course. The results from both the simulation studies and the cystic fibrosis data application suggest that the inclusion of the shared individual-level GPs under the joint model framework leads to important improvements in personalized disease progression prediction.

A Hierarchical Bayesian Model for the Identification of PET Markers Associated to the Prediction of Surgical Outcome after Anterior Temporal Lobe Resection

Directory of Open Access Journals (Sweden)

Sharon Chiang

2017-12-01

Full Text Available We develop an integrative Bayesian predictive modeling framework that identifies individual pathological brain states based on the selection of fluoro-deoxyglucose positron emission tomography (PET imaging biomarkers and evaluates the association of those states with a clinical outcome. We consider data from a study on temporal lobe epilepsy (TLE patients who subsequently underwent anterior temporal lobe resection. Our modeling framework looks at the observed profiles of regional glucose metabolism in PET as the phenotypic manifestation of a latent individual pathologic state, which is assumed to vary across the population. The modeling strategy we adopt allows the identification of patient subgroups characterized by latent pathologies differentially associated to the clinical outcome of interest. It also identifies imaging biomarkers characterizing the pathological states of the subjects. In the data application, we identify a subgroup of TLE patients at high risk for post-surgical seizure recurrence after anterior temporal lobe resection, together with a set of discriminatory brain regions that can be used to distinguish the latent subgroups. We show that the proposed method achieves high cross-validated accuracy in predicting post-surgical seizure recurrence.

Use of artificial neural networks to predict biological outcomes for patients receiving radical radiotherapy of the prostate

International Nuclear Information System (INIS)

Gulliford, Sarah L.; Webb, Steve; Rowbottom, Carl G.; Corne, David W.; Dearnaley, David P.

2004-01-01

Background and purpose: This paper discusses the application of artificial neural networks (ANN) in predicting biological outcomes following prostate radiotherapy. A number of model-based methods have been developed to correlate the dose distributions calculated for a patient receiving radiotherapy and the radiobiological effect this will produce. Most widely used are the normal tissue complication probability and tumour control probability models. An alternative method for predicting specific examples of tumour control and normal tissue complications is to use an ANN. One of the advantages of this method is that there is no need for a priori information regarding the relationship between the data being correlated. Patients and methods: A set of retrospective clinical data from patients who received radical prostate radiotherapy was used to train ANNs to predict specific biological outcomes by learning the relationship between the treatment plan prescription, dose distribution and the corresponding biological effect. The dose and volume were included as a differential dose-volume histogram in order to provide a holistic description of the available data. Results: It was shown that the ANNs were able to predict biochemical control and specific bladder and rectum complications with sensitivity and specificity of above 55% when the outcomes were dichotomised. It was also possible to analyse information from the ANNs to investigate the effect of individual treatment parameters on the outcome. Conclusion: ANNs have been shown to learn something of the complex relationship between treatment parameters and outcome which, if developed further, may prove to be a useful tool in predicting biological outcomes

The Role of Teachers' Support in Predicting Students' Motivation and Achievement Outcomes in Physical Education

Science.gov (United States)

Zhang, Tao; Solmon, Melinda A.; Gu, Xiangli

2012-01-01

Examining how teachers' beliefs and behaviors predict students' motivation and achievement outcomes in physical education is an area of increasing research interest. Guided by the expectancy-value model and self-determination theory, the major purpose of this study was to examine the predictive strength of teachers' autonomy, competence, and…

The Best Prediction Model for Trauma Outcomes of the Current Korean Population: a Comparative Study of Three Injury Severity Scoring Systems

Directory of Open Access Journals (Sweden)

Kyoungwon Jung

2016-08-01

Full Text Available Background: Injury severity scoring systems that quantify and predict trauma outcomes have not been established in Korea. This study was designed to determine the best system for use in the Korean trauma population. Methods: We collected and analyzed the data from trauma patients admitted to our institution from January 2010 to December 2014. Injury Severity Score (ISS, Revised Trauma Score (RTS, and Trauma and Injury Severity Score (TRISS were calculated based on the data from the enrolled patients. Area under the receiver operating characteristic (ROC curve (AUC for the prediction ability of each scoring system was obtained, and a pairwise comparison of ROC curves was performed. Additionally, the cut-off values were estimated to predict mortality, and the corresponding accuracy, positive predictive value, and negative predictive value were obtained. Results: A total of 7,120 trauma patients (6,668 blunt and 452 penetrating injuries were enrolled in this study. The AUCs of ISS, RTS, and TRISS were 0.866, 0.894, and 0.942, respectively, and the prediction ability of the TRISS was significantly better than the others (p < 0.001, respectively. The cut-off value of the TRISS was 0.9082, with a sensitivity of 81.9% and specificity of 92.0%; mortality was predicted with an accuracy of 91.2%; its positive predictive value was the highest at 46.8%. Conclusions: The results of our study were based on the data from one institution and suggest that the TRISS is the best prediction model of trauma outcomes in the current Korean population. Further study is needed with more data from multiple centers in Korea.

Multi-model analysis in hydrological prediction

Science.gov (United States)

Lanthier, M.; Arsenault, R.; Brissette, F.

2017-12-01

Hydrologic modelling, by nature, is a simplification of the real-world hydrologic system. Therefore ensemble hydrological predictions thus obtained do not present the full range of possible streamflow outcomes, thereby producing ensembles which demonstrate errors in variance such as under-dispersion. Past studies show that lumped models used in prediction mode can return satisfactory results, especially when there is not enough information available on the watershed to run a distributed model. But all lumped models greatly simplify the complex processes of the hydrologic cycle. To generate more spread in the hydrologic ensemble predictions, multi-model ensembles have been considered. In this study, the aim is to propose and analyse a method that gives an ensemble streamflow prediction that properly represents the forecast probabilities and reduced ensemble bias. To achieve this, three simple lumped models are used to generate an ensemble. These will also be combined using multi-model averaging techniques, which generally generate a more accurate hydrogram than the best of the individual models in simulation mode. This new predictive combined hydrogram is added to the ensemble, thus creating a large ensemble which may improve the variability while also improving the ensemble mean bias. The quality of the predictions is then assessed on different periods: 2 weeks, 1 month, 3 months and 6 months using a PIT Histogram of the percentiles of the real observation volumes with respect to the volumes of the ensemble members. Initially, the models were run using historical weather data to generate synthetic flows. This worked for individual models, but not for the multi-model and for the large ensemble. Consequently, by performing data assimilation at each prediction period and thus adjusting the initial states of the models, the PIT Histogram could be constructed using the observed flows while allowing the use of the multi-model predictions. The under-dispersion has been

Improving Predictive Modeling in Pediatric Drug Development: Pharmacokinetics, Pharmacodynamics, and Mechanistic Modeling

Energy Technology Data Exchange (ETDEWEB)

Slikker, William; Young, John F.; Corley, Rick A.; Dorman, David C.; Conolly, Rory B.; Knudsen, Thomas; Erstad, Brian L.; Luecke, Richard H.; Faustman, Elaine M.; Timchalk, Chuck; Mattison, Donald R.

2005-07-26

A workshop was conducted on November 18?19, 2004, to address the issue of improving predictive models for drug delivery to developing humans. Although considerable progress has been made for adult humans, large gaps remain for predicting pharmacokinetic/pharmacodynamic (PK/PD) outcome in children because most adult models have not been tested during development. The goals of the meeting included a description of when, during development, infants/children become adultlike in handling drugs. The issue of incorporating the most recent advances into the predictive models was also addressed: both the use of imaging approaches and genomic information were considered. Disease state, as exemplified by obesity, was addressed as a modifier of drug pharmacokinetics and pharmacodynamics during development. Issues addressed in this workshop should be considered in the development of new predictive and mechanistic models of drug kinetics and dynamics in the developing human.

Predictive Risk Modelling to Prevent Child Maltreatment and Other Adverse Outcomes for Service Users: Inside the 'Black Box' of Machine Learning.

Science.gov (United States)

Gillingham, Philip

2016-06-01

Recent developments in digital technology have facilitated the recording and retrieval of administrative data from multiple sources about children and their families. Combined with new ways to mine such data using algorithms which can 'learn', it has been claimed that it is possible to develop tools that can predict which individual children within a population are most likely to be maltreated. The proposed benefit is that interventions can then be targeted to the most vulnerable children and their families to prevent maltreatment from occurring. As expertise in predictive modelling increases, the approach may also be applied in other areas of social work to predict and prevent adverse outcomes for vulnerable service users. In this article, a glimpse inside the 'black box' of predictive tools is provided to demonstrate how their development for use in social work may not be straightforward, given the nature of the data recorded about service users and service activity. The development of predictive risk modelling (PRM) in New Zealand is focused on as an example as it may be the first such tool to be applied as part of ongoing reforms to child protection services.

Development of a new risk model for predicting cardiovascular events among hemodialysis patients: Population-based hemodialysis patients from the Japan Dialysis Outcome and Practice Patterns Study (J-DOPPS.

Directory of Open Access Journals (Sweden)

Yukiko Matsubara

Full Text Available Cardiovascular (CV events are the primary cause of death and becoming bedridden among hemodialysis (HD patients. The Framingham risk score (FRS is useful for predicting incidence of CV events in the general population, but is considerd to be unsuitable for the prediction of the incidence of CV events in HD patients, given their characteristics due to atypical relationships between conventional risk factors and outcomes. We therefore aimed to develop a new prognostic prediction model for prevention and early detection of CV events among hemodialysis patients.We enrolled 3,601 maintenance HD patients based on their data from the Japan Dialysis Outcomes and Practice Patterns Study (J-DOPPS, phases 3 and 4. We longitudinaly assessed the association between several potential candidate predictors and composite CV events in the year after study initiation. Potential candidate predictors included the component factors of FRS and other HD-specific risk factors. We used multivariable logistic regression with backward stepwise selection to develop our new prediction model and generated a calibration plot. Additinially, we performed bootstrapping to assess the internal validity.We observed 328 composite CV events during 1-year follow-up. The final prediction model contained six variables: age, diabetes status, history of CV events, dialysis time per session, and serum phosphorus and albumin levels. The new model showed significantly better discrimination than the FRS, in both men (c-statistics: 0.76 for new model, 0.64 for FRS and women (c-statistics: 0.77 for new model, 0.60 for FRS. Additionally, we confirmed the consistency between the observed results and predicted results using the calibration plot. Further, we found similar discrimination and calibration to the derivation model in the bootstrapping cohort.We developed a new risk model consisting of only six predictors. Our new model predicted CV events more accurately than the FRS.

An antenatal prediction model for adverse birth outcomes in an urban population: The contribution of medical and non-medical risks.

Science.gov (United States)

Posthumus, A G; Birnie, E; van Veen, M J; Steegers, E A P; Bonsel, G J

2016-07-01

in the Netherlands the perinatal mortality rate is high compared to other European countries. Around eighty percent of perinatal mortality cases is preceded by being small for gestational age (SGA), preterm birth and/or having a low Apgar-score at 5 minutes after birth. Current risk detection in pregnancy focusses primarily on medical risks. However, non-medical risk factors may be relevant too. Both non-medical and medical risk factors are incorporated in the Rotterdam Reproductive Risk Reduction (R4U) scorecard. We investigated the associations between R4U risk factors and preterm birth, SGA and a low Apgar score. a prospective cohort study under routine practice conditions. six midwifery practices and two hospitals in Rotterdam, the Netherlands. 836 pregnant women. the R4U scorecard was filled out at the booking visit. after birth, the follow-up data on pregnancy outcomes were collected. Multivariate logistic regression was used to fit models for the prediction of any adverse outcome (preterm birth, SGA and/or a low Apgar score), stratified for ethnicity and socio-economic status (SES). factors predicting any adverse outcome for Western women were smoking during the first trimester and over-the-counter medication. For non-Western women risk factors were teenage pregnancy, advanced maternal age and an obstetric history of SGA. Risk factors for high SES women were low family income, no daily intake of vegetables and a history of preterm birth. For low SES women risk factors appeared to be low family income, non-Western ethnicity, smoking during the first trimester and a history of SGA. the presence of both medical and non-medical risk factors early in pregnancy predict the occurrence of adverse outcomes at birth. Furthermore the risk profiles for adverse outcomes differed according to SES and ethnicity. to optimise effective risk selection, both medical and non-medical risk factors should be taken into account in midwifery and obstetric care at the booking visit

Intra- and interspecies gene expression models for predicting drug response in canine osteosarcoma.

Science.gov (United States)

Fowles, Jared S; Brown, Kristen C; Hess, Ann M; Duval, Dawn L; Gustafson, Daniel L

2016-02-19

Genomics-based predictors of drug response have the potential to improve outcomes associated with cancer therapy. Osteosarcoma (OS), the most common primary bone cancer in dogs, is commonly treated with adjuvant doxorubicin or carboplatin following amputation of the affected limb. We evaluated the use of gene-expression based models built in an intra- or interspecies manner to predict chemosensitivity and treatment outcome in canine OS. Models were built and evaluated using microarray gene expression and drug sensitivity data from human and canine cancer cell lines, and canine OS tumor datasets. The "COXEN" method was utilized to filter gene signatures between human and dog datasets based on strong co-expression patterns. Models were built using linear discriminant analysis via the misclassification penalized posterior algorithm. The best doxorubicin model involved genes identified in human lines that were co-expressed and trained on canine OS tumor data, which accurately predicted clinical outcome in 73 % of dogs (p = 0.0262, binomial). The best carboplatin model utilized canine lines for gene identification and model training, with canine OS tumor data for co-expression. Dogs whose treatment matched our predictions had significantly better clinical outcomes than those that didn't (p = 0.0006, Log Rank), and this predictor significantly associated with longer disease free intervals in a Cox multivariate analysis (hazard ratio = 0.3102, p = 0.0124). Our data show that intra- and interspecies gene expression models can successfully predict response in canine OS, which may improve outcome in dogs and serve as pre-clinical validation for similar methods in human cancer research.

Outcome prediction in home- and community-based brain injury rehabilitation using the Mayo-Portland Adaptability Inventory.

Science.gov (United States)

Malec, James F; Parrot, Devan; Altman, Irwin M; Swick, Shannon

2015-01-01

The objective of the study was to develop statistical formulas to predict levels of community participation on discharge from post-hospital brain injury rehabilitation using retrospective data analysis. Data were collected from seven geographically distinct programmes in a home- and community-based brain injury rehabilitation provider network. Participants were 642 individuals with post-traumatic brain injury. Interventions consisted of home- and community-based brain injury rehabilitation. The main outcome measure was the Mayo-Portland Adaptability Inventory (MPAI-4) Participation Index. Linear discriminant models using admission MPAI-4 Participation Index score and log chronicity correctly predicted excellent (no to minimal participation limitations), very good (very mild participation limitations), good (mild participation limitations), and limited (significant participation limitations) outcome levels at discharge. Predicting broad outcome categories for post-hospital rehabilitation programmes based on admission assessment data appears feasible and valid. Equations to provide patients and families with probability statements on admission about expected levels of outcome are provided. It is unknown to what degree these prediction equations can be reliably applied and valid in other settings.

Comparison of two ordinal prediction models

DEFF Research Database (Denmark)

Kattan, Michael W; Gerds, Thomas A

2015-01-01

system (i.e. old or new), such as the level of evidence for one or more factors included in the system or the general opinions of expert clinicians. However, given the major objective of estimating prognosis on an ordinal scale, we argue that the rival staging system candidates should be compared...... on their ability to predict outcome. We sought to outline an algorithm that would compare two rival ordinal systems on their predictive ability. RESULTS: We devised an algorithm based largely on the concordance index, which is appropriate for comparing two models in their ability to rank observations. We...... demonstrate our algorithm with a prostate cancer staging system example. CONCLUSION: We have provided an algorithm for selecting the preferred staging system based on prognostic accuracy. It appears to be useful for the purpose of selecting between two ordinal prediction models....

Outcome manipulation in corporate prediction markets

DEFF Research Database (Denmark)

Ottaviani, Marco; Sørensen, Peter Norman

2007-01-01

This paper presents a framework for applying prediction markets to corporate decision-making. The analysis is motivated by the recent surge of interest in markets as information aggregation devices and their potential use within firms. We characterize the amount of outcome manipulation that results...

Can We Predict Functional Outcome in Neonates with Hypoxic Ischemic Encephalopathy by the Combination of Neuroimaging and Electroencephalography?

Science.gov (United States)

Nanavati, Tania; Seemaladinne, Nirupama; Regier, Michael; Yossuck, Panitan; Pergami, Paola

2015-01-01

Background Neonatal hypoxic ischemic encephalopathy (HIE) is a major cause of mortality, morbidity, and long-term neurological deficits. Despite the availability of neuroimaging and neurophysiological testing, tools for accurate early diagnosis and prediction of developmental outcome are still lacking. The goal of this study was to determine if combined use of magnetic resonance imaging (MRI) and electroencephalography (EEG) findings could support outcome prediction. Methods We retrospectively reviewed records of 17 HIE neonates, classified brain MRI and EEG findings based on severity, and assessed clinical outcome up to 48 months. We determined the relation between MRI/EEG findings and clinical outcome. Results We demonstrated a significant relationship between MRI findings and clinical outcome (Fisher’s exact test, p = 0.017). EEG provided no additional information about the outcome beyond that contained in the MRI score. The statistical model for outcome prediction based on random forests suggested that EEG readings at 24 hours and 72 hours could be important variables for outcome prediction, but this needs to be investigated further. Conclusion Caution should be used when discussing prognosis for neonates with mild-to-moderate HIE based on early MR imaging and EEG findings. A robust, quantitative marker of HIE severity that allows for accurate prediction of long-term outcome, particularly for mild-to-moderate cases, is still needed. PMID:25862075

PREDICTING THE MATCH OUTCOME IN ONE DAY INTERNATIONAL CRICKET MATCHES, WHILE THE GAME IS IN PROGRESS

Directory of Open Access Journals (Sweden)

Michael Bailey

2006-12-01

Full Text Available Millions of dollars are wagered on the outcome of one day international (ODI cricket matches, with a large percentage of bets occurring after the game has commenced. Using match information gathered from all 2200 ODI matches played prior to January 2005, a range of variables that could independently explain statistically significant proportions of variation associated with the predicted run totals and match outcomes were created. Such variables include home ground advantage, past performances, match experience, performance at the specific venue, performance against the specific opposition, experience at the specific venue and current form. Using a multiple linear regression model, prediction variables were numerically weighted according to statistical significance and used to predict the match outcome. With the use of the Duckworth-Lewis method to determine resources remaining, at the end of each completed over, the predicted run total of the batting team could be updated to provide a more accurate prediction of the match outcome. By applying this prediction approach to a holdout sample of matches, the efficiency of the "in the run" wagering market could be assessed. Preliminary results suggest that the market is prone to overreact to events occurring throughout the course of the match, thus creating brief inefficiencies in the wagering market

Prediction of processing tomato peeling outcomes

Science.gov (United States)

Peeling outcomes of processing tomatoes were predicted using multivariate analysis of Magnetic Resonance (MR) images. Tomatoes were obtained from a whole-peel production line. Each fruit was imaged using a 7 Tesla MR system, and a multivariate data set was created from 28 different images. After ...

Predicting outcome of acute kidney transplant rejection using

NARCIS (Netherlands)

Rekers, Niels Vincent

2014-01-01

Acute kidney transplant rejection is an important risk factors for adverse graft outcome. Once diagnosed, it remains difficult to predict the risk of graft loss and the response to anti-rejection treatment. The aim of this thesis was to identify biomarkers during acute rejection, which predict the

Consciousness Indexing and Outcome Prediction with Resting-State EEG in Severe Disorders of Consciousness.

Science.gov (United States)

Stefan, Sabina; Schorr, Barbara; Lopez-Rolon, Alex; Kolassa, Iris-Tatjana; Shock, Jonathan P; Rosenfelder, Martin; Heck, Suzette; Bender, Andreas

2018-04-17

We applied the following methods to resting-state EEG data from patients with disorders of consciousness (DOC) for consciousness indexing and outcome prediction: microstates, entropy (i.e. approximate, permutation), power in alpha and delta frequency bands, and connectivity (i.e. weighted symbolic mutual information, symbolic transfer entropy, complex network analysis). Patients with unresponsive wakefulness syndrome (UWS) and patients in a minimally conscious state (MCS) were classified into these two categories by fitting and testing a generalised linear model. We aimed subsequently to develop an automated system for outcome prediction in severe DOC by selecting an optimal subset of features using sequential floating forward selection (SFFS). The two outcome categories were defined as UWS or dead, and MCS or emerged from MCS. Percentage of time spent in microstate D in the alpha frequency band performed best at distinguishing MCS from UWS patients. The average clustering coefficient obtained from thresholding beta coherence performed best at predicting outcome. The optimal subset of features selected with SFFS consisted of the frequency of microstate A in the 2-20 Hz frequency band, path length obtained from thresholding alpha coherence, and average path length obtained from thresholding alpha coherence. Combining these features seemed to afford high prediction power. Python and MATLAB toolboxes for the above calculations are freely available under the GNU public license for non-commercial use ( https://qeeg.wordpress.com ).

FERAL : Network-based classifier with application to breast cancer outcome prediction

NARCIS (Netherlands)

Allahyar, A.; De Ridder, J.

2015-01-01

Motivation: Breast cancer outcome prediction based on gene expression profiles is an important strategy for personalize patient care. To improve performance and consistency of discovered markers of the initial molecular classifiers, network-based outcome prediction methods (NOPs) have been proposed.

EVALUATING RISK-PREDICTION MODELS USING DATA FROM ELECTRONIC HEALTH RECORDS.

Science.gov (United States)

Wang, L E; Shaw, Pamela A; Mathelier, Hansie M; Kimmel, Stephen E; French, Benjamin

2016-03-01

The availability of data from electronic health records facilitates the development and evaluation of risk-prediction models, but estimation of prediction accuracy could be limited by outcome misclassification, which can arise if events are not captured. We evaluate the robustness of prediction accuracy summaries, obtained from receiver operating characteristic curves and risk-reclassification methods, if events are not captured (i.e., "false negatives"). We derive estimators for sensitivity and specificity if misclassification is independent of marker values. In simulation studies, we quantify the potential for bias in prediction accuracy summaries if misclassification depends on marker values. We compare the accuracy of alternative prognostic models for 30-day all-cause hospital readmission among 4548 patients discharged from the University of Pennsylvania Health System with a primary diagnosis of heart failure. Simulation studies indicate that if misclassification depends on marker values, then the estimated accuracy improvement is also biased, but the direction of the bias depends on the direction of the association between markers and the probability of misclassification. In our application, 29% of the 1143 readmitted patients were readmitted to a hospital elsewhere in Pennsylvania, which reduced prediction accuracy. Outcome misclassification can result in erroneous conclusions regarding the accuracy of risk-prediction models.

Predicting Adverse Health Outcomes in Long-Term Survivors of a Childhood Cancer

Directory of Open Access Journals (Sweden)

Chaya S. Moskowitz

2014-07-01

Full Text Available More than 80% of children and young adults diagnosed with invasive cancer will survive five or more years beyond their cancer diagnosis. This population has an increased risk for serious illness- and treatment-related morbidity and premature mortality. A number of these adverse health outcomes, such as cardiovascular disease and some second primary neoplasms, either have modifiable risk factors or can be successfully treated if detected early. Absolute risk models that project a personalized risk of developing a health outcome can be useful in patient counseling, in designing intervention studies, in forming prevention strategies, and in deciding upon surveillance programs. Here, we review existing absolute risk prediction models that are directly applicable to survivors of a childhood cancer, discuss the concepts and interpretation of absolute risk models, and examine ways in which these models can be used applied in clinical practice and public health.

[Encopresis--predictive factors and outcome].

Science.gov (United States)

Mehler-Wex, Claudia; Scheuerpflug, Peter; Peschke, Nicole; Roth, Michael; Reitzle, Karl; Warnke, Andreas

2005-10-01

comparison of diagnostic, clinical and therapeutic features and their predictive value for the outcome of encopresis in children and adolescents. 85 children and adolescents (aged 9.6 +/- 3.2 years) with severe encopresis (ICD 10: F98.1) were investigated during inpatient treatment and 35 of them again 5.5 +/- 1.8 years later. Mentally retarded patients were excluded. Inpatient therapy consisted of treating constipation and/or stool regulation by means of laxatives, behavioural approaches, and the specific therapy of comorbid psychiatric disorders. During inpatient treatment 22% of the patients experienced total remission, 8% an unchanged persistence of symptoms. Of the 35 patients studied at follow-up 5.5 years later, 40% were symptom-free. As main result, prognostic outcome depended significantly on sufficient treatment of obstipation. Another important factor was the specific therapeutic approach to psychiatric comorbidity, especially to ADHD. The outcome for patients with comorbid ICD 10: F43 was significantly better than for the other patients. Those who were symptom-free at discharge had significantly better long-term outcomes. Decisive to the success of encopresis treatment were the stool regulation and the specific therapy of associated psychiatric illnesses, in particular of ADHD. Inpatient treatment revealed significantly better long-term outcomes where total remission had been achieved by the time of discharge from hospital.

Outcomes-Balanced Framework for Emergency Management: A Predictive Model for Preparedness

Science.gov (United States)

2013-09-01

Management Total Quality Management (TQM) was developed by W. Edwards Deming in the post-World War II reconstruction period in Japan. It ushered in a...FIGURES Figure 1. From Total Quality Management Principles ....................................................30 Figure 2. Outcomes Logic Model (After...THIRA Threat and Hazard Identification and Risk Assessment TQM Total Quality Management UTL Universal Task List xiv ACKNOWLEDGMENTS German

Development and validation of risk models to predict outcomes following in-hospital cardiac arrest attended by a hospital-based resuscitation team.

Science.gov (United States)

Harrison, David A; Patel, Krishna; Nixon, Edel; Soar, Jasmeet; Smith, Gary B; Gwinnutt, Carl; Nolan, Jerry P; Rowan, Kathryn M

2014-08-01

The National Cardiac Arrest Audit (NCAA) is the UK national clinical audit for in-hospital cardiac arrest. To make fair comparisons among health care providers, clinical indicators require case mix adjustment using a validated risk model. The aim of this study was to develop and validate risk models to predict outcomes following in-hospital cardiac arrest attended by a hospital-based resuscitation team in UK hospitals. Risk models for two outcomes-return of spontaneous circulation (ROSC) for greater than 20min and survival to hospital discharge-were developed and validated using data for in-hospital cardiac arrests between April 2011 and March 2013. For each outcome, a full model was fitted and then simplified by testing for non-linearity, combining categories and stepwise reduction. Finally, interactions between predictors were considered. Models were assessed for discrimination, calibration and accuracy. 22,479 in-hospital cardiac arrests in 143 hospitals were included (14,688 development, 7791 validation). The final risk model for ROSC>20min included: age (non-linear), sex, prior length of stay in hospital, reason for attendance, location of arrest, presenting rhythm, and interactions between presenting rhythm and location of arrest. The model for hospital survival included the same predictors, excluding sex. Both models had acceptable performance across the range of measures, although discrimination for hospital mortality exceeded that for ROSC>20min (c index 0.81 versus 0.72). Validated risk models for ROSC>20min and hospital survival following in-hospital cardiac arrest have been developed. These models will strengthen comparative reporting in NCAA and support local quality improvement. Copyright © 2014 The Authors. Published by Elsevier Ireland Ltd.. All rights reserved.

Review of the quality of total mesorectal excision does not improve the prediction of outcome.

Science.gov (United States)

Demetter, P; Jouret-Mourin, A; Silversmit, G; Vandendael, T; Sempoux, C; Hoorens, A; Nagy, N; Cuvelier, C; Van Damme, N; Penninckx, F

2016-09-01

A fair to moderate concordance in grading of the total mesorectal excision (TME) surgical specimen by local pathologists and a central review panel has been observed in the PROCARE (Project on Cancer of the Rectum) project. The aim of the present study was to evaluate the difference, if any, in the accuracy of predicting the oncological outcome through TME grading by local pathologists or by the review panel. The quality of the TME specimen was reviewed for 482 surgical specimens registered on a prospective database between 2006 and 2011. Patients with a Stage IV tumour, with unknown incidence date or without follow-up information were excluded, resulting in a study population of 383 patients. Quality assessment of the specimen was based on three grades including mesorectal resection (MRR), intramesorectal resection (IMR) and muscularis propria resection (MPR). Using univariable Cox regression models, local and review panel histopathological gradings of the quality of TME were assessed as predictors of local recurrence, distant metastasis and disease-free and overall survival. Differences in the predictions between local and review grading were determined. Resection planes were concordant in 215 (56.1%) specimens. Downgrading from MRR to MPR was noted in 23 (6.0%). There were no significant differences in the prediction error between the two models; local and central review TME grading predicted the outcome equally well. Any difference in grading of the TME specimen between local histopathologists and the review panel had no significant impact on the prediction of oncological outcome for this patient cohort. Grading of the quality of TME as reported by local histopathologists can therefore be used for outcome analysis. Quality control of TME grading is not warranted provided the histopathologist is adequately trained. Colorectal Disease © 2016 The Association of Coloproctology of Great Britain and Ireland.

Measure of functional independence dominates discharge outcome prediction after inpatient rehabilitation for stroke.

Science.gov (United States)

Brown, Allen W; Therneau, Terry M; Schultz, Billie A; Niewczyk, Paulette M; Granger, Carl V

2015-04-01

Identifying clinical data acquired at inpatient rehabilitation admission for stroke that accurately predict key outcomes at discharge could inform the development of customized plans of care to achieve favorable outcomes. The purpose of this analysis was to use a large comprehensive national data set to consider a wide range of clinical elements known at admission to identify those that predict key outcomes at rehabilitation discharge. Sample data were obtained from the Uniform Data System for Medical Rehabilitation data set with the diagnosis of stroke for the years 2005 through 2007. This data set includes demographic, administrative, and medical variables collected at admission and discharge and uses the FIM (functional independence measure) instrument to assess functional independence. Primary outcomes of interest were functional independence measure gain, length of stay, and discharge to home. The sample included 148,367 people (75% white; mean age, 70.6±13.1 years; 97% with ischemic stroke) admitted to inpatient rehabilitation a mean of 8.2±12 days after symptom onset. The total functional independence measure score, the functional independence measure motor subscore, and the case-mix group were equally the strongest predictors for any of the primary outcomes. The most clinically relevant 3-variable model used the functional independence measure motor subscore, age, and walking distance at admission (r(2)=0.107). No important additional effect for any other variable was detected when added to this model. This analysis shows that a measure of functional independence in motor performance and age at rehabilitation hospital admission for stroke are predominant predictors of outcome at discharge in a uniquely large US national data set. © 2015 American Heart Association, Inc.

Do patient characteristics predict outcome in the outpatient treatment of chronic tinnitus?

Science.gov (United States)

Kröner-Herwig, Birgit; Zachriat, Claudia; Weigand, Doreen

2006-12-06

Various patient characteristics were assessed before offering a treatment to reduce tinnitus related distress to 57 individuals suffering from chronic idiopathic tinnitus. Patients were randomly assigned to a cognitive-behavioral tinnitus coping training (TCT) and a habituation-based training (HT) modelled after Tinnitus Retraining Therapy (TRT) as conceived by Jastreboff. Both trainings were conducted in groups. It was hypothesized that comorbidity regarding mental disorders or psychopathological symptoms (DSM-IV diagnoses, SCL-90R score) and a high level of dysfunctional cognitions relating to tinnitus would have a negative effect on therapy outcome while both trainings proved to be highly efficacious for the average patient. Also further patient features (assessed at baseline) were explored as potential predictors of outcome. None of the hypotheses was corroborated by the data. On the contrary, a higher number of diagnoses was associated with better outcome (statistical trend) and a higher extent of annoyance and interference led to a larger positive change in patients if treated by TCT. No predictor could be identified for long-term success (follow-up ≥18 months) except regarding education. The higher the educational level, the larger was the improvement in HT patients. It is concluded that therapy outcome of TCT and HT can not reliably be predicted by patient characteristics and that early variables of the therapeutic process should be analysed as potentially predicting subsequent therapeutic outcome.

The prediction of intelligence in preschool children using alternative models to regression.

Science.gov (United States)

Finch, W Holmes; Chang, Mei; Davis, Andrew S; Holden, Jocelyn E; Rothlisberg, Barbara A; McIntosh, David E

2011-12-01

Statistical prediction of an outcome variable using multiple independent variables is a common practice in the social and behavioral sciences. For example, neuropsychologists are sometimes called upon to provide predictions of preinjury cognitive functioning for individuals who have suffered a traumatic brain injury. Typically, these predictions are made using standard multiple linear regression models with several demographic variables (e.g., gender, ethnicity, education level) as predictors. Prior research has shown conflicting evidence regarding the ability of such models to provide accurate predictions of outcome variables such as full-scale intelligence (FSIQ) test scores. The present study had two goals: (1) to demonstrate the utility of a set of alternative prediction methods that have been applied extensively in the natural sciences and business but have not been frequently explored in the social sciences and (2) to develop models that can be used to predict premorbid cognitive functioning in preschool children. Predictions of Stanford-Binet 5 FSIQ scores for preschool-aged children is used to compare the performance of a multiple regression model with several of these alternative methods. Results demonstrate that classification and regression trees provided more accurate predictions of FSIQ scores than does the more traditional regression approach. Implications of these results are discussed.

Development and validation of outcome prediction models for aneurysmal subarachnoid haemorrhage : The SAHIT multinational cohort study

NARCIS (Netherlands)

Jaja, Blessing N R; Saposnik, Gustavo; Lingsma, Hester F.; Macdonald, Erin; Thorpe, Kevin E.; Mamdani, Muhammed; Steyerberg, Ewout W.; Molyneux, Andrew; Manoel, Airton Leonardo De Oliveira; Schatlo, Bawarjan; Hanggi, Daniel; Hasan, David M.; Wong, George K C; Etminan, Nima; Fukuda, Hitoshi; Torner, James C.; Schaller, Karl L.; Suarez, Jose I.; Stienen, Martin N.; Vergouwen, Mervyn D.I.; Rinkel, Gabriel J.E.; Spears, Julian; Cusimano, Michael D.; Todd, Michael; Le Roux, Peter; Kirkpatrick, Peter J.; Pickard, John; Van Den Bergh, Walter M.; Murray, Gordon D; Johnston, S. Claiborne; Yamagata, Sen; Mayer, Stephan A.; Schweizer, Tom A.; Macdonald, R. Loch

2018-01-01

Objective To develop and validate a set of practical prediction tools that reliably estimate the outcome of subarachnoid haemorrhage from ruptured intracranial aneurysms (SAH). Design Cohort study with logistic regression analysis to combine predictors and treatment modality. Setting Subarachnoid

[Predictive factors of the outcomes of prenatal hydronephrosis.

Science.gov (United States)

Bragagnini, Paolo; Estors, Blanca; Delgado, Reyes; Rihuete, Miguel Ángel; Gracia, Jesús

2016-12-01

To determine prenatal and postnatal independent predictors of poor outcome, spontaneous resolution, or the need for surgery in patients with prenatal hydronephrosis. We performed a retrospective study of patients with prenatal hydronephrosis. The renal pelvis APD was measured in the third prenatal trimester ultrasound, as well as in the first and second postnatal ultrasound. Other variables were taken into account, both prenatal and postnatal. For statistical analysis we used Student t-test, chi-square test, survival analysis, logrank test, and ROC curves. We included 218 patients with 293 renal units (RU). Of these, 147/293 (50.2%) RU were operated. 76/293 (25.9%) RU had spontaneous resolution and other 76/293 (25.9%) RU had poor outcome. As risk factors for surgery we found low birth weight (OR 3.84; 95% CI 1.24-11.84), prematurity (OR 4.17; 95% CI 1.35-12.88), duplication (OR 4.99; 95% CI 2.21-11.23) and the presence of nephrourological underlying pathology (OR 53.54; 95% CI 26.23-109.27). For the non-spontaneous resolution, we found as risk factors the alterations of amniotic fluid volume (RR 1.46; 95% CI 1.33-1.60) as well as the underlying nephrourological pathology and duplication. In the poor outcome, we found as risk factors the alterations of amniotic fluid volume (OR 4.54; 95% CI 1.31-15.62), the presence of nephrourological pathology (OR 4.81 95% CI 2.60-8.89) and RU that was operated (OR 4.23, 95% CI 2.35-7.60). The APD of the renal pelvis in all three ultrasounds were reliable for surgery prediction (area under the curve 0.65; 0.82; 0.71) or spontaneous resolution (area under the curve 0.80; 0.91; 0.80), only the first postnatal ultrasound has predictive value in the poor outcome (area under the curve 0.73). The higher sensitivity and specificity of the APD as predictor value was on the first postnatal ultrasound, 14.60 mm for surgery; 11.35 mm for spontaneous resolution and 15.50 mm for poor outcome. The higher APD in the renal pelvis in any of the

Comparison of Simple Versus Performance-Based Fall Prediction Models

Directory of Open Access Journals (Sweden)

Shekhar K. Gadkaree BS

2015-05-01

Full Text Available Objective: To compare the predictive ability of standard falls prediction models based on physical performance assessments with more parsimonious prediction models based on self-reported data. Design: We developed a series of fall prediction models progressing in complexity and compared area under the receiver operating characteristic curve (AUC across models. Setting: National Health and Aging Trends Study (NHATS, which surveyed a nationally representative sample of Medicare enrollees (age ≥65 at baseline (Round 1: 2011-2012 and 1-year follow-up (Round 2: 2012-2013. Participants: In all, 6,056 community-dwelling individuals participated in Rounds 1 and 2 of NHATS. Measurements: Primary outcomes were 1-year incidence of “ any fall ” and “ recurrent falls .” Prediction models were compared and validated in development and validation sets, respectively. Results: A prediction model that included demographic information, self-reported problems with balance and coordination, and previous fall history was the most parsimonious model that optimized AUC for both any fall (AUC = 0.69, 95% confidence interval [CI] = [0.67, 0.71] and recurrent falls (AUC = 0.77, 95% CI = [0.74, 0.79] in the development set. Physical performance testing provided a marginal additional predictive value. Conclusion: A simple clinical prediction model that does not include physical performance testing could facilitate routine, widespread falls risk screening in the ambulatory care setting.

Long-term outcomes following laparoscopic adjustable gastric banding: postoperative psychological sequelae predict outcome at 5-year follow-up.

Science.gov (United States)

Scholtz, Samantha; Bidlake, Louise; Morgan, John; Fiennes, Alberic; El-Etar, Ashraf; Lacey, John Hubert; McCluskey, Sara

2007-09-01

NICE guidelines state that patients with psychological contra-indications should not be considered for bariatric surgery, including Laparoscopic Adjustable Gastric Banding (LAGB) surgery as treatment of morbid obesity, although no consistent correlation between psychiatric illness and long-term outcome in LAGB has been established. This is to our knowledge the first study to evaluate long-term outcomes in LAGB for a full range of DSM-IV defined psychiatric and eating disorders, and forms part of a research portfolio developed by the authors aimed at defining psychological predictors of bariatric surgery in the short-, medium- and long-term. Case notes of 37 subjects operated on between April 1997 and June 2000, who had undergone structured clinical interview during pre-surgical assessment to yield diagnoses of mental and eating disorders according to DSM-IV criteria were analyzed according to a set of operationally defined criteria. Statistical analysis was carried out to compare those with a poor outcome and those considered to have a good outcome in terms of psychiatric profile. In this group of mainly female, Caucasian subjects, ranging in age from 27 to 60 years, one-third were diagnosed with a mental disorder according to DSM-IV criteria. The development of postoperative DSM-IV defined binge eating disorder (BED) or depression strongly predicted poor surgical outcome, but pre-surgical psychiatric factors alone did not. Although pre-surgical psychiatric assessment alone cannot predict outcome, an absence of preoperative psychiatric illness should not reassure surgeons who should be mindful of postoperative psychiatric sequelae, particularly BED. The importance of providing an integrated biopsychosocial model of care in bariatric teams is highlighted.

ASTRAL, DRAGON and SEDAN scores predict stroke outcome more accurately than physicians.

Science.gov (United States)

Ntaios, G; Gioulekas, F; Papavasileiou, V; Strbian, D; Michel, P

2016-11-01

ASTRAL, SEDAN and DRAGON scores are three well-validated scores for stroke outcome prediction. Whether these scores predict stroke outcome more accurately compared with physicians interested in stroke was investigated. Physicians interested in stroke were invited to an online anonymous survey to provide outcome estimates in randomly allocated structured scenarios of recent real-life stroke patients. Their estimates were compared to scores' predictions in the same scenarios. An estimate was considered accurate if it was within 95% confidence intervals of actual outcome. In all, 244 participants from 32 different countries responded assessing 720 real scenarios and 2636 outcomes. The majority of physicians' estimates were inaccurate (1422/2636, 53.9%). 400 (56.8%) of physicians' estimates about the percentage probability of 3-month modified Rankin score (mRS) > 2 were accurate compared with 609 (86.5%) of ASTRAL score estimates (P DRAGON score estimates (P DRAGON score estimates (P DRAGON and SEDAN scores predict outcome of acute ischaemic stroke patients with higher accuracy compared to physicians interested in stroke. © 2016 EAN.

Predictability of motor outcome according to the time of diffusion tensor imaging in patients with cerebral infarct

Energy Technology Data Exchange (ETDEWEB)

Kwon, Yong Hyun [Yeungnam College of Science and Technology, Department of Physical Therapy, Taegu (Korea, Republic of); Jeoung, Yong Jae [Yeungnam University, Department of Physical Medicine and Rehabilitation, College of Medicine, Taegu (Korea, Republic of); Lee, Jun [Yeungnam University, Department of Neurology, College of Medicine, Taegu (Korea, Republic of); Son, Su Min; Jang, Sung Ho [Yeungnam University 317-1, Department of Physical Medicine and Rehabilitation, College of Medicine, Taegu (Korea, Republic of); Kim, Saeyoon [Yeungnam University, Department of Pediatrics, College of Medicine, Taegu (Korea, Republic of); Kim, Chulseung [Medical Devices Clinical Trial Center of Yeungnam University Hospital, Taegu (Korea, Republic of)

2012-07-15

Predictability of diffusion tensor imaging tractography (DTT) for motor outcome can differ according to the time of DTT. We attempted to compare the predictability for motor outcome according to the time of diffusion tensor imaging (DTI) by analyzing the corticospinal tract (CST) integrity on DTT in patients with corona radiata (CR) infarct. Seventy-one consecutive hemiparetic patients with CR infarct were recruited. Motor function of the affected extremities was measured twice: at onset and at 6 months from onset. According to the time of DTI, patients were classified into two groups: the early scanning group (ES group) within 14 days since stroke onset; and the late scanning group (LS group) 15-28 days. Motor outcome was compared with the CST integrity on DTT. Motor prognosis was predicted from scan time of DTI and the CST integrity on DTT in the logistic regression model. According to separate regression analysis, the CST integrity of the late group was found to predict MI score (OR = 14.000, 95% CI = 3.194-61.362, p < 0.05), whereas the CST integrity of the early group was not found to predict MI score. In terms of both positive and negative predictabilities, we found that predictability of DTT for motor outcome was better in patients who were scanned later (15-28 days after onset) than in patients who were scanned earlier (1-14 days after onset). (orig.)

Predictability of motor outcome according to the time of diffusion tensor imaging in patients with cerebral infarct

International Nuclear Information System (INIS)

Kwon, Yong Hyun; Jeoung, Yong Jae; Lee, Jun; Son, Su Min; Jang, Sung Ho; Kim, Saeyoon; Kim, Chulseung

2012-01-01

Predictability of diffusion tensor imaging tractography (DTT) for motor outcome can differ according to the time of DTT. We attempted to compare the predictability for motor outcome according to the time of diffusion tensor imaging (DTI) by analyzing the corticospinal tract (CST) integrity on DTT in patients with corona radiata (CR) infarct. Seventy-one consecutive hemiparetic patients with CR infarct were recruited. Motor function of the affected extremities was measured twice: at onset and at 6 months from onset. According to the time of DTI, patients were classified into two groups: the early scanning group (ES group) within 14 days since stroke onset; and the late scanning group (LS group) 15-28 days. Motor outcome was compared with the CST integrity on DTT. Motor prognosis was predicted from scan time of DTI and the CST integrity on DTT in the logistic regression model. According to separate regression analysis, the CST integrity of the late group was found to predict MI score (OR = 14.000, 95% CI = 3.194-61.362, p < 0.05), whereas the CST integrity of the early group was not found to predict MI score. In terms of both positive and negative predictabilities, we found that predictability of DTT for motor outcome was better in patients who were scanned later (15-28 days after onset) than in patients who were scanned earlier (1-14 days after onset). (orig.)

Neurophysiological prediction of neurological good and poor outcome in post-anoxic coma.

Science.gov (United States)

Grippo, A; Carrai, R; Scarpino, M; Spalletti, M; Lanzo, G; Cossu, C; Peris, A; Valente, S; Amantini, A

2017-06-01

Investigation of the utility of association between electroencephalogram (EEG) and somatosensory-evoked potentials (SEPs) for the prediction of neurological outcome in comatose patients resuscitated after cardiac arrest (CA) treated with therapeutic hypothermia, according to different recording times after CA. Glasgow Coma Scale, EEG and SEPs performed at 12, 24 and 48-72 h after CA were assessed in 200 patients. Outcome was evaluated by Cerebral Performance Category 6 months after CA. Within 12 h after CA, grade 1 EEG predicted good outcome and bilaterally absent (BA) SEPs predicted poor outcome. Because grade 1 EEG and BA-SEPs were never found in the same patient, the recording of both EEG and SEPs allows us to correctly prognosticate a greater number of patients with respect to the use of a single test within 12 h after CA. At 48-72 h after CA, both grade 2 EEG and BA-SEPs predicted poor outcome with FPR=0.0%. When these neurophysiological patterns are both present in the same patient, they confirm and strengthen their prognostic value, but because they also occurred independently in eight patients, poor outcome is predictable in a greater number of patients. The combination of EEG/SEP findings allows prediction of good and poor outcome (within 12 h after CA) and of poor outcome (after 48-72 h). Recording of EEG and SEPs in the same patients allows always an increase in the number of cases correctly classified, and an increase of the reliability of prognostication in a single patient due to concordance of patterns. © 2016 John Wiley & Sons A/S. Published by John Wiley & Sons Ltd.

Androgen receptor profiling predicts prostate cancer outcome

NARCIS (Netherlands)

S. Stelloo (Suzan); E. Nevedomskaya (Ekaterina); H.G. van der Poel (Henk G.); J. de Jong (Jeroen); G.J.H.L. Leenders (Geert); G.W. Jenster (Guido); L. Wessels (Lodewyk); A.M. Bergman (Andries); W. Zwart (Wilbert)

2015-01-01

textabstractProstate cancer is the second most prevalent malignancy in men. Biomarkers for outcome prediction are urgently needed, so that high-risk patients could be monitored more closely postoperatively. To identify prognostic markers and to determine causal players in prostate cancer

Validation of Clinical Prediction Models: Theory and Applications in Testicular Germ Cell Cancer

NARCIS (Netherlands)

Y. Vergouwe (Yvonne)

2003-01-01

textabstractlinical prediction models combine patient characteristics to predict the probability of having a certain disease (diagnosis) or the probability that a particular disease state will occur (prognosis). The predicted probability of the diagnostic or prognostic outcome may assist the

Perceived Masculinity Predicts U.S. Supreme Court Outcomes

Science.gov (United States)

2016-01-01

Previous studies suggest a significant role of language in the court room, yet none has identified a definitive correlation between vocal characteristics and court outcomes. This paper demonstrates that voice-based snap judgments based solely on the introductory sentence of lawyers arguing in front of the Supreme Court of the United States predict outcomes in the Court. In this study, participants rated the opening statement of male advocates arguing before the Supreme Court between 1998 and 2012 in terms of masculinity, attractiveness, confidence, intelligence, trustworthiness, and aggressiveness. We found significant correlation between vocal characteristics and court outcomes and the correlation is specific to perceived masculinity even when judgment of masculinity is based only on less than three seconds of exposure to a lawyer’s speech sample. Specifically, male advocates are more likely to win when they are perceived as less masculine. No other personality dimension predicts court outcomes. While this study does not aim to establish any causal connections, our findings suggest that vocal characteristics may be relevant in even as solemn a setting as the Supreme Court of the United States. PMID:27737008

Perceived Masculinity Predicts U.S. Supreme Court Outcomes.

Directory of Open Access Journals (Sweden)

Daniel Chen

Full Text Available Previous studies suggest a significant role of language in the court room, yet none has identified a definitive correlation between vocal characteristics and court outcomes. This paper demonstrates that voice-based snap judgments based solely on the introductory sentence of lawyers arguing in front of the Supreme Court of the United States predict outcomes in the Court. In this study, participants rated the opening statement of male advocates arguing before the Supreme Court between 1998 and 2012 in terms of masculinity, attractiveness, confidence, intelligence, trustworthiness, and aggressiveness. We found significant correlation between vocal characteristics and court outcomes and the correlation is specific to perceived masculinity even when judgment of masculinity is based only on less than three seconds of exposure to a lawyer's speech sample. Specifically, male advocates are more likely to win when they are perceived as less masculine. No other personality dimension predicts court outcomes. While this study does not aim to establish any causal connections, our findings suggest that vocal characteristics may be relevant in even as solemn a setting as the Supreme Court of the United States.

A survey on computational intelligence approaches for predictive modeling in prostate cancer

OpenAIRE

Cosma, G; Brown, D; Archer, M; Khan, M; Pockley, AG

2017-01-01

Predictive modeling in medicine involves the development of computational models which are capable of analysing large amounts of data in order to predict healthcare outcomes for individual patients. Computational intelligence approaches are suitable when the data to be modelled are too complex forconventional statistical techniques to process quickly and eciently. These advanced approaches are based on mathematical models that have been especially developed for dealing with the uncertainty an...

PREDICT-CP: study protocol of implementation of comprehensive surveillance to predict outcomes for school-aged children with cerebral palsy.

Science.gov (United States)

Boyd, Roslyn N; Davies, Peter Sw; Ziviani, Jenny; Trost, Stewart; Barber, Lee; Ware, Robert; Rose, Stephen; Whittingham, Koa; Sakzewski, Leanne; Bell, Kristie; Carty, Christopher; Obst, Steven; Benfer, Katherine; Reedman, Sarah; Edwards, Priya; Kentish, Megan; Copeland, Lisa; Weir, Kelly; Davenport, Camilla; Brooks, Denise; Coulthard, Alan; Pelekanos, Rebecca; Guzzetta, Andrea; Fiori, Simona; Wynter, Meredith; Finn, Christine; Burgess, Andrea; Morris, Kym; Walsh, John; Lloyd, Owen; Whitty, Jennifer A; Scuffham, Paul A

2017-07-12

Cerebral palsy (CP) remains the world's most common childhood physical disability with total annual costs of care and lost well-being of $A3.87b. The PREDICT-CP (NHMRC 1077257 Partnership Project: Comprehensive surveillance to PREDICT outcomes for school age children with CP) study will investigate the influence of brain structure, body composition, dietary intake, oropharyngeal function, habitual physical activity, musculoskeletal development (hip status, bone health) and muscle performance on motor attainment, cognition, executive function, communication, participation, quality of life and related health resource use costs. The PREDICT-CP cohort provides further follow-up at 8-12 years of two overlapping preschool-age cohorts examined from 1.5 to 5 years (NHMRC 465128 motor and brain development; NHMRC 569605 growth, nutrition and physical activity). This population-based cohort study undertakes state-wide surveillance of 245 children with CP born in Queensland (birth years 2006-2009). Children will be classified for Gross Motor Function Classification System; Manual Ability Classification System, Communication Function Classification System and Eating and Drinking Ability Classification System. Outcomes include gross motor function, musculoskeletal development (hip displacement, spasticity, muscle contracture), upper limb function, communication difficulties, oropharyngeal dysphagia, dietary intake and body composition, participation, parent-reported and child-reported quality of life and medical and allied health resource use. These detailed phenotypical data will be compared with brain macrostructure and microstructure using 3 Tesla MRI (3T MRI). Relationships between brain lesion severity and outcomes will be analysed using multilevel mixed-effects models. The PREDICT-CP protocol is a prospectively registered and ethically accepted study protocol. The study combines data at 1.5-5 then 8-12 years of direct clinical assessment to enable prediction of outcomes

A new pathological scoring system by the Japanese classification to predict renal outcome in diabetic nephropathy.

Science.gov (United States)

Hoshino, Junichi; Furuichi, Kengo; Yamanouchi, Masayuki; Mise, Koki; Sekine, Akinari; Kawada, Masahiro; Sumida, Keiichi; Hiramatsu, Rikako; Hasegawa, Eiko; Hayami, Noriko; Suwabe, Tatsuya; Sawa, Naoki; Hara, Shigeko; Fujii, Takeshi; Ohashi, Kenichi; Kitagawa, Kiyoki; Toyama, Tadashi; Shimizu, Miho; Takaichi, Kenmei; Ubara, Yoshifumi; Wada, Takashi

2018-01-01

The impact of the newly proposed pathological classification by the Japan Renal Pathology Society (JRPS) on renal outcome is unclear. So we evaluated that impact and created a new pathological scoring to predict outcome using this classification. A multicenter cohort of 493 biopsy-proven Japanese patients with diabetic nephropathy (DN) were analyzed. The association between each pathological factor-Tervaert' and JRPS classifications-and renal outcome (dialysis initiation or 50% eGFR decline) was estimated by adjusted Cox regression. The overall pathological risk score (J-score) was calculated, whereupon its predictive ability for 10-year risk of renal outcome was evaluated. The J-scores of diffuse lesion classes 2 or 3, GBM doubling class 3, presence of mesangiolysis, polar vasculosis, and arteriolar hyalinosis were, respectively, 1, 2, 4, 1, and 2. The scores of IFTA classes 1, 2, and 3 were, respectively, 3, 4, and 4, and those of interstitial inflammation classes 1, 2, and 3 were 5, 5, and 4 (J-score range, 0-19). Renal survival curves, when dividing into four J-score grades (0-5, 6-10, 11-15, and 16-19), were significantly different from each other (prenal outcome. Ability to predict 10-year renal outcome was improved when the J-score was added to the basic model: c-statistics from 0.661 to 0.685; category-free net reclassification improvement, 0.154 (-0.040, 0.349, p = 0.12); and integrated discrimination improvement, 0.015 (0.003, 0.028, p = 0.02). Mesangiolysis, polar vasculosis, and doubling of GBM-features of the JRPS system-were significantly associated with renal outcome. Prediction of DN patients' renal outcome was better with the J-score than without it.

Adjusting a cancer mortality-prediction model for disease status-related eligibility criteria

Directory of Open Access Journals (Sweden)

Kimmel Marek

2011-05-01

Full Text Available Abstract Background Volunteering participants in disease studies tend to be healthier than the general population partially due to specific enrollment criteria. Using modeling to accurately predict outcomes of cohort studies enrolling volunteers requires adjusting for the bias introduced in this way. Here we propose a new method to account for the effect of a specific form of healthy volunteer bias resulting from imposing disease status-related eligibility criteria, on disease-specific mortality, by explicitly modeling the length of the time interval between the moment when the subject becomes ineligible for the study, and the outcome. Methods Using survival time data from 1190 newly diagnosed lung cancer patients at MD Anderson Cancer Center, we model the time from clinical lung cancer diagnosis to death using an exponential distribution to approximate the length of this interval for a study where lung cancer death serves as the outcome. Incorporating this interval into our previously developed lung cancer risk model, we adjust for the effect of disease status-related eligibility criteria in predicting the number of lung cancer deaths in the control arm of CARET. The effect of the adjustment using the MD Anderson-derived approximation is compared to that based on SEER data. Results Using the adjustment developed in conjunction with our existing lung cancer model, we are able to accurately predict the number of lung cancer deaths observed in the control arm of CARET. Conclusions The resulting adjustment was accurate in predicting the lower rates of disease observed in the early years while still maintaining reasonable prediction ability in the later years of the trial. This method could be used to adjust for, or predict the duration and relative effect of any possible biases related to disease-specific eligibility criteria in modeling studies of volunteer-based cohorts.

Prediction of Clinical Outcome After Acute Ischemic Stroke: The Value of Repeated Noncontrast Computed Tomography, Computed Tomographic Angiography, and Computed Tomographic Perfusion.

Science.gov (United States)

Dankbaar, Jan W; Horsch, Alexander D; van den Hoven, Andor F; Kappelle, L Jaap; van der Schaaf, Irene C; van Seeters, Tom; Velthuis, Birgitta K

2017-09-01

Early prediction of outcome in acute ischemic stroke is important for clinical management. This study aimed to compare the relationship between early follow-up multimodality computed tomographic (CT) imaging and clinical outcome at 90 days in a large multicenter stroke study. From the DUST study (Dutch Acute Stroke Study), patients were selected with (1) anterior circulation occlusion on CT angiography (CTA) and ischemic deficit on CT perfusion (CTP) on admission, and (2) day 3 follow-up noncontrast CT, CTP, and CTA. Follow-up infarct volume on noncontrast CT, poor recanalization on CTA, and poor reperfusion on CTP (mean transit time index ≤75%) were related to unfavorable outcome after 90 days defined as modified Rankin Scale 3 to 6. Four multivariable models were constructed: (1) only baseline variables (model 1), (2) model 1 with addition of infarct volume, (3) model 1 with addition of recanalization, and (4) model 1 with addition of reperfusion. Area under the curves of the receiver operating characteristic curves of the models were compared using the DeLong test. A total of 242 patients were included. Poor recanalization was found in 21%, poor reperfusion in 37%, and unfavorable outcome in 44%. The area under the curve of the receiver operating characteristic curve without follow-up imaging was 0.81, with follow-up noncontrast CT 0.85 ( P =0.02), CTA 0.86 ( P =0.01), and CTP 0.86 ( P =0.01). All 3 follow-up imaging modalities improved outcome prediction compared with no imaging. There was no difference between the imaging models. Follow-up imaging after 3 days improves outcome prediction compared with prediction based on baseline variables alone. CTA recanalization and CTP reperfusion do not outperform noncontrast CT at this time point. URL: http://www.clinicaltrials.gov. Unique identifier: NCT00880113. © 2017 American Heart Association, Inc.

Decisions on foot-and-mouth disease control informed by model prediction

DEFF Research Database (Denmark)

Hisham Beshara Halasa, Tariq; Willeberg, Preben; Christiansen, Lasse Engbo

2013-01-01

of affected herds, epidemic duration, geographical size, and costs. The first fourteen days spatial spread (FFS) was also included to support the prediction. The epidemic data were obtained from a Danish version (DTU-DADS) of the Davis Animal Disease Spread simulation model. The FFI and FFS showed good......The predictive capability of the first fortnight incidence (FFI), which is the number of detected herds within the first 14 days following detection of the disease, of the course of a foot-and-mouth disease (FMD) epidemic and its outcomes were investigated. Epidemic outcomes included the number...... correlations with the epidemic outcomes. The predictive capability of the FFI was high. This indicates that the FFI may take a part in the decision of whether or not to boost FMD control, which might prevent occurrence of a large epidemic in the face of an FMD incursion. The prediction power was improved...

A simplified donor risk index for predicting outcome after deceased donor kidney transplantation.

Science.gov (United States)

Watson, Christopher J E; Johnson, Rachel J; Birch, Rhiannon; Collett, Dave; Bradley, J Andrew

2012-02-15

We sought to determine the deceased donor factors associated with outcome after kidney transplantation and to develop a clinically applicable Kidney Donor Risk Index. Data from the UK Transplant Registry on 7620 adult recipients of adult deceased donor kidney transplants between 2000 and 2007 inclusive were analyzed. Donor factors potentially influencing transplant outcome were investigated using Cox regression, adjusting for significant recipient and transplant factors. A United Kingdom Kidney Donor Risk Index was derived from the model and validated. Donor age was the most significant factor predicting poor transplant outcome (hazard ratio for 18-39 and 60+ years relative to 40-59 years was 0.78 and 1.49, respectively, Pinformed consent.

Using acute kidney injury severity and scoring systems to predict outcome in patients with burn injury

Directory of Open Access Journals (Sweden)

George Kuo

2016-12-01

Conclusion: Our results revealed that AKI stage has considerable discriminative power for predicting mortality. Compared with other prognostic models, AKI stage is easier to use to assess outcome in patients with severe burn injury.

Early Treatment Outcome in Failure to Thrive: Predictions from a Transactional Model.

Science.gov (United States)

Drotar, Dennis

Children diagnosed with environmentally based failure to thrive early during their first year of life were seen at 12 and 18 months for assessment of psychological development (cognition, language, symbolic play, and behavior during testing). Based on a transactional model of outcome, factors reflecting biological vulnerability (wasting and…

Reliability of computerized cephalometric outcome predictions of mandibular set-back surgery

Directory of Open Access Journals (Sweden)

Stefanović Neda

2011-01-01

Full Text Available Introduction. A successful treatment outcome in dentofacial deformity patients commonly requires combined orthodontic-surgical therapy. This enables us to overcome functional, aesthetic and psychological problems. Since most patients state aesthetics as the primary motive for seeking therapy, cephalometric predictions of treatment outcome have become the essential part of treatment planning, especially in combined orthodontic-surgical cases. Objective. The aim of this study was to evaluate the validity and reliability of computerized orthognathic surgery outcome predictions generated using the Nemotec Dental Studio NX 2005 software. Methods. The sample of the study consisted of 31 patients diagnosed with mandibular prognathism who were surgically treated at the Hospital for Maxillofacial Surgery in Belgrade. Investigation was done on lateral cephalograms made before and after surgical treatment. Cephalograms were digitized and analyzed using computer software. According to measurements made on superimposed pre- and postsurgical cephalograms, the patients were retreated within the software and the predictions were assessed by measuring seven angular and three linear parameters. Prediction measurements were then compared with the actual outcome. Results. Results showed statistically significant changes between posttreatment and predicted values for parameters referring to lower lip and mentolabial sulcus position. Conclusion. Computerized cephalometric predictions for hard-tissue structures in the sagittal and vertical planes, as well as the VTO parameters, generated using the Nemotec Dental Studio NX 2005 software are reliable, while lower lip and mentolabial sulcus position predictions are not reliable enough.

Can Preoperative Psychological Assessment Predict Outcomes After Temporomandibular Joint Arthroscopy?

Science.gov (United States)

Bouloux, Gary F; Zerweck, Ashley G; Celano, Marianne; Dai, Tian; Easley, Kirk A

2015-11-01

Psychological assessment has been used successfully to predict patient outcomes after cardiothoracic and bariatric surgery. The purpose of this study was to determine whether preoperative psychological assessment could be used to predict patient outcomes after temporomandibular joint arthroscopy. Consecutive patients with temporomandibular dysfunction (TMD) who could benefit from arthroscopy were enrolled in a prospective cohort study. All patients completed the Millon Behavior Medicine Diagnostic survey before surgery. The primary predictor variable was the preoperative psychological scores. The primary outcome variable was the difference in pain between the pre- and postoperative periods. The Spearman rank correlation coefficient and the Pearson product-moment correlation were used to determine the association between psychological factors and change in pain. Univariable and multivariable analyses were performed using a mixed-effects linear model and multiple linear regression. A P value of .05 was considered significant. Eighty-six patients were enrolled in the study. Seventy-five patients completed the study and were included in the final analyses. The mean change in visual analog scale (VAS) pain score 1 month after arthroscopy was -15.4 points (95% confidence interval, -6.0 to -24.7; P psychological factors was identified with univariable correlation analyses. Multivariable analyses identified that a greater pain decrease was associated with a longer duration of preoperative symptoms (P = .054) and lower chronic anxiety (P = .064). This study has identified a weak association between chronic anxiety and the magnitude of pain decrease after arthroscopy for TMD. Further studies are needed to clarify the role of chronic anxiety in the outcome after surgical procedures for the treatment of TMD. Copyright © 2015. Published by Elsevier Inc.

Lactate Parameters Predict Clinical Outcomes in Patients with Nonvariceal Upper Gastrointestinal Bleeding.

Science.gov (United States)

Lee, Seung Hoon; Min, Yang Won; Bae, Joohwan; Lee, Hyuk; Min, Byung Hoon; Lee, Jun Haeng; Rhee, Poong Lyul; Kim, Jae J

2017-11-01

The predictive role of lactate in patients with nonvariceal upper gastrointestinal bleeding (NVUGIB) has been suggested. This study evaluated several lactate parameters in terms of predicting outcomes of bleeding patients and sought to establish a new scoring model by combining lactate parameters and the AIMS65 score. A total of 114 patients with NVUGIB who underwent serum lactate level testing at least twice and endoscopic hemostasis within 24 hours after admission were retrospectively analyzed. The associations between five lactate parameters and clinical outcomes were evaluated and the predictive power of lactate parameter combined AIMS65s (L-AIMS65s) and AIMS56 scoring was compared. The most common cause of bleeding was gastric ulcer (48.2%). Lactate clearance rate (LCR) was associated with 30-day rebleeding (odds ratio [OR], 0.931; 95% confidence interval [CI], 0.872-0.994; P = 0.033). Initial lactate (OR, 1.313; 95% CI, 1.050-1.643; P = 0.017), maximal lactate (OR, 1.277; 95% CI, 1.037-1.573; P = 0.021), and average lactate (OR, 1.535; 95% CI, 1.137-2.072; P = 0.005) levels were associated with 30-day mortality. Initial lactate (OR, 1.213; 95% CI, 1.027-1.432; P = 0.023), maximal lactate (OR, 1.271; 95% CI, 1.074-1.504; P = 0.005), and average lactate (OR, 1.501; 95% CI, 1.150-1.959; P = 0.003) levels were associated with admission over 7 days. Although L-AIMS65s showed the highest area under the curve for prediction of each outcome, differences between L-AIMS65s and AIMS65 did not reach statistical significance. In conclusion, lactate parameters have a prognostic role in patients with NVUGIB. However, they do not increase the predictive power of AIMS65 when combined. © 2017 The Korean Academy of Medical Sciences.

Predicting functional outcomes of posterior circulation acute ischemic stroke in first 36 h of stroke onset.

Science.gov (United States)

Lin, Sheng-Feng; Chen, Chin-I; Hu, Han-Hwa; Bai, Chyi-Huey

2018-04-01

Posterior circulation acute ischemic stroke constitutes one-fourth of all ischemic strokes and can be efficiently quantified using the posterior circulation Alberta stroke program early computed tomography score (PC-ASPECTS) through diffusion-weighted imaging. We investigated whether the PC-ASPECTS and National Institutes of Health Stroke Scale (NIHSS) facilitate functional outcome prediction among Chinese patients with posterior circulation acute ischemic stroke. Participants were selected from our prospective stroke registry from January 1, 2015, to December 31, 2016. The baseline NIHSS score was assessed on the first day of admission, and brain magnetic resonance imaging was performed within 36 h after stroke onset. Simple and multiple logistic regressions were conducted to determine stroke risk factors and the PC-ASPECTS. Receiver operating characteristics (ROC) curve analysis was performed to compare the NIHSS and PC-ASPECTS. Of 549 patients from our prospective stroke admission registry database, 125 (22.8%) had a diagnosis of posterior circulation acute ischemic stroke. The optimal cutoff for the PC-ASPECTS in predicting outcomes was 7. The odds ratios of the PC-ASPECTS (≤ 7 vs > 7) in predicting outcomes were 6.33 (p = 0.0002) and 8.49 (p = 0.0060) in the univariate and multivariate models, respectively, and 7.52 (p = 0.0041) in the aging group. On ROC curve analysis, the PC-ASPECTS demonstrated more reliability than the baseline NIHSS for predicting functional outcomes of minor posterior circulation stroke. In conclusion, both the PC-ASPECTS and NIHSS help clinicians predict functional outcomes. PC-ASPECTS > 7 is a helpful discriminator for achieving favorable functional outcome prediction in posterior circulation acute ischemic stroke.

Patient Similarity in Prediction Models Based on Health Data: A Scoping Review

Science.gov (United States)

Sharafoddini, Anis; Dubin, Joel A

2017-01-01

Background Physicians and health policy makers are required to make predictions during their decision making in various medical problems. Many advances have been made in predictive modeling toward outcome prediction, but these innovations target an average patient and are insufficiently adjustable for individual patients. One developing idea in this field is individualized predictive analytics based on patient similarity. The goal of this approach is to identify patients who are similar to an index patient and derive insights from the records of similar patients to provide personalized predictions.. Objective The aim is to summarize and review published studies describing computer-based approaches for predicting patients’ future health status based on health data and patient similarity, identify gaps, and provide a starting point for related future research. Methods The method involved (1) conducting the review by performing automated searches in Scopus, PubMed, and ISI Web of Science, selecting relevant studies by first screening titles and abstracts then analyzing full-texts, and (2) documenting by extracting publication details and information on context, predictors, missing data, modeling algorithm, outcome, and evaluation methods into a matrix table, synthesizing data, and reporting results. Results After duplicate removal, 1339 articles were screened in abstracts and titles and 67 were selected for full-text review. In total, 22 articles met the inclusion criteria. Within included articles, hospitals were the main source of data (n=10). Cardiovascular disease (n=7) and diabetes (n=4) were the dominant patient diseases. Most studies (n=18) used neighborhood-based approaches in devising prediction models. Two studies showed that patient similarity-based modeling outperformed population-based predictive methods. Conclusions Interest in patient similarity-based predictive modeling for diagnosis and prognosis has been growing. In addition to raw/coded health

Regional brain morphometry predicts memory rehabilitation outcome after traumatic brain injury

Directory of Open Access Journals (Sweden)

Gary E Strangman

2010-10-01

Full Text Available Cognitive deficits following traumatic brain injury (TBI commonly include difficulties with memory, attention, and executive dysfunction. These deficits are amenable to cognitive rehabilitation, but optimally selecting rehabilitation programs for individual patients remains a challenge. Recent methods for quantifying regional brain morphometry allow for automated quantification of tissue volumes in numerous distinct brain structures. We hypothesized that such quantitative structural information could help identify individuals more or less likely to benefit from memory rehabilitation. Fifty individuals with TBI of all severities who reported having memory difficulties first underwent structural MRI scanning. They then participated in a 12 session memory rehabilitation program emphasizing internal memory strategies (I-MEMS. Primary outcome measures (HVLT, RBMT were collected at the time of the MRI scan, immediately following therapy, and again at one month post-therapy. Regional brain volumes were used to predict outcome, adjusting for standard predictors (e.g., injury severity, age, education, pretest scores. We identified several brain regions that provided significant predictions of rehabilitation outcome, including the volume of the hippocampus, the lateral prefrontal cortex, the thalamus, and several subregions of the cingulate cortex. The prediction range of regional brain volumes were in some cases nearly equal in magnitude to prediction ranges provided by pretest scores on the outcome variable. We conclude that specific cerebral networks including these regions may contribute to learning during I-MEMS rehabilitation, and suggest that morphometric measures may provide substantial predictive value for rehabilitation outcome in other cognitive interventions as well.

Is demography destiny? Application of machine learning techniques to accurately predict population health outcomes from a minimal demographic dataset.

Directory of Open Access Journals (Sweden)

Wei Luo

Full Text Available For years, we have relied on population surveys to keep track of regional public health statistics, including the prevalence of non-communicable diseases. Because of the cost and limitations of such surveys, we often do not have the up-to-date data on health outcomes of a region. In this paper, we examined the feasibility of inferring regional health outcomes from socio-demographic data that are widely available and timely updated through national censuses and community surveys. Using data for 50 American states (excluding Washington DC from 2007 to 2012, we constructed a machine-learning model to predict the prevalence of six non-communicable disease (NCD outcomes (four NCDs and two major clinical risk factors, based on population socio-demographic characteristics from the American Community Survey. We found that regional prevalence estimates for non-communicable diseases can be reasonably predicted. The predictions were highly correlated with the observed data, in both the states included in the derivation model (median correlation 0.88 and those excluded from the development for use as a completely separated validation sample (median correlation 0.85, demonstrating that the model had sufficient external validity to make good predictions, based on demographics alone, for areas not included in the model development. This highlights both the utility of this sophisticated approach to model development, and the vital importance of simple socio-demographic characteristics as both indicators and determinants of chronic disease.

Is demography destiny? Application of machine learning techniques to accurately predict population health outcomes from a minimal demographic dataset.

Science.gov (United States)

Luo, Wei; Nguyen, Thin; Nichols, Melanie; Tran, Truyen; Rana, Santu; Gupta, Sunil; Phung, Dinh; Venkatesh, Svetha; Allender, Steve

2015-01-01

For years, we have relied on population surveys to keep track of regional public health statistics, including the prevalence of non-communicable diseases. Because of the cost and limitations of such surveys, we often do not have the up-to-date data on health outcomes of a region. In this paper, we examined the feasibility of inferring regional health outcomes from socio-demographic data that are widely available and timely updated through national censuses and community surveys. Using data for 50 American states (excluding Washington DC) from 2007 to 2012, we constructed a machine-learning model to predict the prevalence of six non-communicable disease (NCD) outcomes (four NCDs and two major clinical risk factors), based on population socio-demographic characteristics from the American Community Survey. We found that regional prevalence estimates for non-communicable diseases can be reasonably predicted. The predictions were highly correlated with the observed data, in both the states included in the derivation model (median correlation 0.88) and those excluded from the development for use as a completely separated validation sample (median correlation 0.85), demonstrating that the model had sufficient external validity to make good predictions, based on demographics alone, for areas not included in the model development. This highlights both the utility of this sophisticated approach to model development, and the vital importance of simple socio-demographic characteristics as both indicators and determinants of chronic disease.

Toward Big Data Analytics: Review of Predictive Models in Management of Diabetes and Its Complications.

Science.gov (United States)

Cichosz, Simon Lebech; Johansen, Mette Dencker; Hejlesen, Ole

2015-10-14

Diabetes is one of the top priorities in medical science and health care management, and an abundance of data and information is available on these patients. Whether data stem from statistical models or complex pattern recognition models, they may be fused into predictive models that combine patient information and prognostic outcome results. Such knowledge could be used in clinical decision support, disease surveillance, and public health management to improve patient care. Our aim was to review the literature and give an introduction to predictive models in screening for and the management of prevalent short- and long-term complications in diabetes. Predictive models have been developed for management of diabetes and its complications, and the number of publications on such models has been growing over the past decade. Often multiple logistic or a similar linear regression is used for prediction model development, possibly owing to its transparent functionality. Ultimately, for prediction models to prove useful, they must demonstrate impact, namely, their use must generate better patient outcomes. Although extensive effort has been put in to building these predictive models, there is a remarkable scarcity of impact studies. © 2015 Diabetes Technology Society.

Prediction of future labour market outcome in a cohort of long-term sick-listed Danes

DEFF Research Database (Denmark)

Pedersen, Jacob; Gerds, Thomas Alexander; Bjørner, Jakob

2014-01-01

BACKGROUND: Targeted interventions for the long-term sick-listed may prevent permanent exclusion from the labour force. We aimed to develop a prediction method for identifying high risk groups for continued or recurrent long-term sickness absence, unemployment, or disability among persons on long...... data set, statistical prediction methods were built using logistic regression and a discrete event simulation approach for a one year prediction horizon. Personalized risk profiles were obtained for five outcomes: employment, unemployment, recurrent sickness absence, continuous long-term sickness...... of recession (2008-2010). The accuracy of the prediction models was assessed with analyses of Receiver Operating Characteristic (ROC) curves and the Brier score in an independent validation data set. RESULTS: In comparison with a null model which ignored the predictor variables, logistic regression achieved...

The influence of ligament modelling strategies on the predictive capability of finite element models of the human knee joint.

Science.gov (United States)

Naghibi Beidokhti, Hamid; Janssen, Dennis; van de Groes, Sebastiaan; Hazrati, Javad; Van den Boogaard, Ton; Verdonschot, Nico

2017-12-08

In finite element (FE) models knee ligaments can represented either by a group of one-dimensional springs, or by three-dimensional continuum elements based on segmentations. Continuum models closer approximate the anatomy, and facilitate ligament wrapping, while spring models are computationally less expensive. The mechanical properties of ligaments can be based on literature, or adjusted specifically for the subject. In the current study we investigated the effect of ligament modelling strategy on the predictive capability of FE models of the human knee joint. The effect of literature-based versus specimen-specific optimized material parameters was evaluated. Experiments were performed on three human cadaver knees, which were modelled in FE models with ligaments represented either using springs, or using continuum representations. In spring representation collateral ligaments were each modelled with three and cruciate ligaments with two single-element bundles. Stiffness parameters and pre-strains were optimized based on laxity tests for both approaches. Validation experiments were conducted to evaluate the outcomes of the FE models. Models (both spring and continuum) with subject-specific properties improved the predicted kinematics and contact outcome parameters. Models incorporating literature-based parameters, and particularly the spring models (with the representations implemented in this study), led to relatively high errors in kinematics and contact pressures. Using a continuum modelling approach resulted in more accurate contact outcome variables than the spring representation with two (cruciate ligaments) and three (collateral ligaments) single-element-bundle representations. However, when the prediction of joint kinematics is of main interest, spring ligament models provide a faster option with acceptable outcome. Copyright © 2017 Elsevier Ltd. All rights reserved.

Early Prediction of Disease Progression in Small Cell Lung Cancer: Toward Model-Based Personalized Medicine in Oncology.

Science.gov (United States)

Buil-Bruna, Núria; Sahota, Tarjinder; López-Picazo, José-María; Moreno-Jiménez, Marta; Martín-Algarra, Salvador; Ribba, Benjamin; Trocóniz, Iñaki F

2015-06-15

Predictive biomarkers can play a key role in individualized disease monitoring. Unfortunately, the use of biomarkers in clinical settings has thus far been limited. We have previously shown that mechanism-based pharmacokinetic/pharmacodynamic modeling enables integration of nonvalidated biomarker data to provide predictive model-based biomarkers for response classification. The biomarker model we developed incorporates an underlying latent variable (disease) representing (unobserved) tumor size dynamics, which is assumed to drive biomarker production and to be influenced by exposure to treatment. Here, we show that by integrating CT scan data, the population model can be expanded to include patient outcome. Moreover, we show that in conjunction with routine medical monitoring data, the population model can support accurate individual predictions of outcome. Our combined model predicts that a change in disease of 29.2% (relative standard error 20%) between two consecutive CT scans (i.e., 6-8 weeks) gives a probability of disease progression of 50%. We apply this framework to an external dataset containing biomarker data from 22 small cell lung cancer patients (four patients progressing during follow-up). Using only data up until the end of treatment (a total of 137 lactate dehydrogenase and 77 neuron-specific enolase observations), the statistical framework prospectively identified 75% of the individuals as having a predictable outcome in follow-up visits. This included two of the four patients who eventually progressed. In all identified individuals, the model-predicted outcomes matched the observed outcomes. This framework allows at risk patients to be identified early and therapeutic intervention/monitoring to be adjusted individually, which may improve overall patient survival. ©2015 American Association for Cancer Research.

Predicting outcome from coma : man-in-the-barrel syndrome as potential pitfall

NARCIS (Netherlands)

Elting, JW; Haaxma, R; De Keyser, J; Sulter, G.

The Glasgow coma scale motor score is often used in predicting outcome after hypoxic ischemic coma. Judicious care should be exerted when using this variable in predicting outcome in patients with coma following hypotension since borderzone infarction can obscure the clinical picture. We describe a

Risk predictive modelling for diabetes and cardiovascular disease.

Science.gov (United States)

Kengne, Andre Pascal; Masconi, Katya; Mbanya, Vivian Nchanchou; Lekoubou, Alain; Echouffo-Tcheugui, Justin Basile; Matsha, Tandi E

2014-02-01

Absolute risk models or clinical prediction models have been incorporated in guidelines, and are increasingly advocated as tools to assist risk stratification and guide prevention and treatments decisions relating to common health conditions such as cardiovascular disease (CVD) and diabetes mellitus. We have reviewed the historical development and principles of prediction research, including their statistical underpinning, as well as implications for routine practice, with a focus on predictive modelling for CVD and diabetes. Predictive modelling for CVD risk, which has developed over the last five decades, has been largely influenced by the Framingham Heart Study investigators, while it is only ∼20 years ago that similar efforts were started in the field of diabetes. Identification of predictive factors is an important preliminary step which provides the knowledge base on potential predictors to be tested for inclusion during the statistical derivation of the final model. The derived models must then be tested both on the development sample (internal validation) and on other populations in different settings (external validation). Updating procedures (e.g. recalibration) should be used to improve the performance of models that fail the tests of external validation. Ultimately, the effect of introducing validated models in routine practice on the process and outcomes of care as well as its cost-effectiveness should be tested in impact studies before wide dissemination of models beyond the research context. Several predictions models have been developed for CVD or diabetes, but very few have been externally validated or tested in impact studies, and their comparative performance has yet to be fully assessed. A shift of focus from developing new CVD or diabetes prediction models to validating the existing ones will improve their adoption in routine practice.

Remote health monitoring: predicting outcome success based on contextual features for cardiovascular disease.

Science.gov (United States)

Alshurafa, Nabil; Eastwood, Jo-Ann; Pourhomayoun, Mohammad; Liu, Jason J; Sarrafzadeh, Majid

2014-01-01

Current studies have produced a plethora of remote health monitoring (RHM) systems designed to enhance the care of patients with chronic diseases. Many RHM systems are designed to improve patient risk factors for cardiovascular disease, including physiological parameters such as body mass index (BMI) and waist circumference, and lipid profiles such as low density lipoprotein (LDL) and high density lipoprotein (HDL). There are several patient characteristics that could be determining factors for a patient's RHM outcome success, but these characteristics have been largely unidentified. In this paper, we analyze results from an RHM system deployed in a six month Women's Heart Health study of 90 patients, and apply advanced feature selection and machine learning algorithms to identify patients' key baseline contextual features and build effective prediction models that help determine RHM outcome success. We introduce Wanda-CVD, a smartphone-based RHM system designed to help participants with cardiovascular disease risk factors by motivating participants through wireless coaching using feedback and prompts as social support. We analyze key contextual features that secure positive patient outcomes in both physiological parameters and lipid profiles. Results from the Women's Heart Health study show that health threat of heart disease, quality of life, family history, stress factors, social support, and anxiety at baseline all help predict patient RHM outcome success.

Hamsi scoring in the prediction of unfavorable outcomes from tuberculous meningitis

DEFF Research Database (Denmark)

Erdem, Hakan; Ozturk-Engin, Derya; Tireli, Hulya

2015-01-01

, hydrocephalus, vasculitis, immunosuppression, diabetes mellitus and neurological deficit remained in the final model. Scores 1-3 were assigned to the variables in the severity scale, which included scores of 1-6. The distribution of mortality for the scores 1-6 was 3.4, 8.2, 20.6, 31, 30 and 40.1%, respectively....... Altered consciousness, diabetes mellitus, immunosuppression, neurological deficits, hydrocephalus, and vasculitis predicted the unfavorable outcome in the scoring and the cumulative score provided a linear estimation of prognosis....

Do Patient Characteristics Predict Outcome of Psychodynamic Psychotherapy for Social Anxiety Disorder?

Directory of Open Access Journals (Sweden)

Jörg Wiltink

Full Text Available Little is known about patient characteristics as predictors for outcome in manualized short term psychodynamic psychotherapy (PDT. No study has addressed which patient variables predict outcome of PDT for social anxiety disorder.In the largest multicenter trial on psychotherapy of social anxiety (SA to date comparing cognitive therapy, PDT and wait list condition N = 230 patients were assigned to receive PDT, of which N = 166 completed treatment. Treatment outcome was assessed based on diverse parameters such as endstate functioning, remission, response, and drop-out. The relationship between patient characteristics (demographic variables, mental co-morbidity, personality, interpersonal problems and outcome was analysed using logistic and linear regressions.Pre-treatment SA predicted up to 39 percent of variance of outcome. Only few additional baseline characteristics predicted better treatment outcome (namely, lower comorbidity and interpersonal problems with a limited proportion of incremental variance (5.5 to 10 percent, while, e.g., shame, self-esteem or harm avoidance did not.We argue that the central importance of pre-treatment symptom severity for predicting outcomes should advocate alternative treatment strategies (e.g. longer treatments, combination of psychotherapy and medication in those who are most disturbed. Given the relatively small amount of variance explained by the other patient characteristics, process variables and patient-therapist interaction should additionally be taken into account in future research.Controlled-trials.com/ISRCTN53517394.

Identification of a robust gene signature that predicts breast cancer outcome in independent data sets

International Nuclear Information System (INIS)

Korkola, James E; Waldman, Frederic M; Blaveri, Ekaterina; DeVries, Sandy; Moore, Dan H II; Hwang, E Shelley; Chen, Yunn-Yi; Estep, Anne LH; Chew, Karen L; Jensen, Ronald H

2007-01-01

Breast cancer is a heterogeneous disease, presenting with a wide range of histologic, clinical, and genetic features. Microarray technology has shown promise in predicting outcome in these patients. We profiled 162 breast tumors using expression microarrays to stratify tumors based on gene expression. A subset of 55 tumors with extensive follow-up was used to identify gene sets that predicted outcome. The predictive gene set was further tested in previously published data sets. We used different statistical methods to identify three gene sets associated with disease free survival. A fourth gene set, consisting of 21 genes in common to all three sets, also had the ability to predict patient outcome. To validate the predictive utility of this derived gene set, it was tested in two published data sets from other groups. This gene set resulted in significant separation of patients on the basis of survival in these data sets, correctly predicting outcome in 62–65% of patients. By comparing outcome prediction within subgroups based on ER status, grade, and nodal status, we found that our gene set was most effective in predicting outcome in ER positive and node negative tumors. This robust gene selection with extensive validation has identified a predictive gene set that may have clinical utility for outcome prediction in breast cancer patients

Protein-Based Urine Test Predicts Kidney Transplant Outcomes

Science.gov (United States)

... News Releases News Release Thursday, August 22, 2013 Protein-based urine test predicts kidney transplant outcomes NIH- ... supporting development of noninvasive tests. Levels of a protein in the urine of kidney transplant recipients can ...

Could the outcome of the 2016 US elections have been predicted from past voting patterns?

Science.gov (United States)

Schmitz, Peter M. U.; Holloway, Jennifer P.; Dudeni-Tlhone, Nontembeko; Ntlangu, Mbulelo B.; Koen, Renee

2018-05-01

In South Africa, a team of analysts has for some years been using statistical techniques to predict election outcomes during election nights in South Africa. The prediction method involves using statistical clusters based on past voting patterns to predict final election outcomes, using a small number of released vote counts. With the US presidential elections in November 2016 hitting the global media headlines during the time period directly after successful predictions were done for the South African elections, the team decided to investigate adapting their meth-od to forecast the final outcome in the US elections. In particular, it was felt that the time zone differences between states would affect the time at which results are released and thereby provide a window of opportunity for doing election night prediction using only the early results from the eastern side of the US. Testing the method on the US presidential elections would have two advantages: it would determine whether the core methodology could be generalised, and whether it would work to include a stronger spatial element in the modelling, since the early results released would be spatially biased due to time zone differences. This paper presents a high-level view of the overall methodology and how it was adapted to predict the results of the US presidential elections. A discussion on the clustering of spatial units within the US is also provided and the spatial distribution of results together with the Electoral College prediction results from both a `test-run' and the final 2016 presidential elections are given and analysed.

Predicting the multi-domain progression of Parkinson's disease: a Bayesian multivariate generalized linear mixed-effect model.

Science.gov (United States)

Wang, Ming; Li, Zheng; Lee, Eun Young; Lewis, Mechelle M; Zhang, Lijun; Sterling, Nicholas W; Wagner, Daymond; Eslinger, Paul; Du, Guangwei; Huang, Xuemei

2017-09-25

It is challenging for current statistical models to predict clinical progression of Parkinson's disease (PD) because of the involvement of multi-domains and longitudinal data. Past univariate longitudinal or multivariate analyses from cross-sectional trials have limited power to predict individual outcomes or a single moment. The multivariate generalized linear mixed-effect model (GLMM) under the Bayesian framework was proposed to study multi-domain longitudinal outcomes obtained at baseline, 18-, and 36-month. The outcomes included motor, non-motor, and postural instability scores from the MDS-UPDRS, and demographic and standardized clinical data were utilized as covariates. The dynamic prediction was performed for both internal and external subjects using the samples from the posterior distributions of the parameter estimates and random effects, and also the predictive accuracy was evaluated based on the root of mean square error (RMSE), absolute bias (AB) and the area under the receiver operating characteristic (ROC) curve. First, our prediction model identified clinical data that were differentially associated with motor, non-motor, and postural stability scores. Second, the predictive accuracy of our model for the training data was assessed, and improved prediction was gained in particularly for non-motor (RMSE and AB: 2.89 and 2.20) compared to univariate analysis (RMSE and AB: 3.04 and 2.35). Third, the individual-level predictions of longitudinal trajectories for the testing data were performed, with ~80% observed values falling within the 95% credible intervals. Multivariate general mixed models hold promise to predict clinical progression of individual outcomes in PD. The data was obtained from Dr. Xuemei Huang's NIH grant R01 NS060722 , part of NINDS PD Biomarker Program (PDBP). All data was entered within 24 h of collection to the Data Management Repository (DMR), which is publically available ( https://pdbp.ninds.nih.gov/data-management ).

An etiologic prediction model incorporating biomarkers to predict the bladder cancer risk associated with occupational exposure to aromatic amines: a pilot study.

Science.gov (United States)

Mastrangelo, Giuseppe; Carta, Angela; Arici, Cecilia; Pavanello, Sofia; Porru, Stefano

2017-01-01

No etiological prediction model incorporating biomarkers is available to predict bladder cancer risk associated with occupational exposure to aromatic amines. Cases were 199 bladder cancer patients. Clinical, laboratory and genetic data were predictors in logistic regression models (full and short) in which the dependent variable was 1 for 15 patients with aromatic amines related bladder cancer and 0 otherwise. The receiver operating characteristics approach was adopted; the area under the curve was used to evaluate discriminatory ability of models. Area under the curve was 0.93 for the full model (including age, smoking and coffee habits, DNA adducts, 12 genotypes) and 0.86 for the short model (including smoking, DNA adducts, 3 genotypes). Using the "best cut-off" of predicted probability of a positive outcome, percentage of cases correctly classified was 92% (full model) against 75% (short model). Cancers classified as "positive outcome" are those to be referred for evaluation by an occupational physician for etiological diagnosis; these patients were 28 (full model) or 60 (short model). Using 3 genotypes instead of 12 can double the number of patients with suspect of aromatic amine related cancer, thus increasing costs of etiologic appraisal. Integrating clinical, laboratory and genetic factors, we developed the first etiologic prediction model for aromatic amine related bladder cancer. Discriminatory ability was excellent, particularly for the full model, allowing individualized predictions. Validation of our model in external populations is essential for practical use in the clinical setting.

Prediction models in in vitro fertilization; where are we? A mini review

Directory of Open Access Journals (Sweden)

Laura van Loendersloot

2014-05-01

Full Text Available Since the introduction of in vitro fertilization (IVF in 1978, over five million babies have been born worldwide using IVF. Contrary to the perception of many, IVF does not guarantee success. Almost 50% of couples that start IVF will remain childless, even if they undergo multiple IVF cycles. The decision to start or pursue with IVF is challenging due to the high cost, the burden of the treatment, and the uncertain outcome. In optimal counseling on chances of a pregnancy with IVF, prediction models may play a role, since doctors are not able to correctly predict pregnancy chances. There are three phases of prediction model development: model derivation, model validation, and impact analysis. This review provides an overview on predictive factors in IVF, the available prediction models in IVF and provides key principles that can be used to critically appraise the literature on prediction models in IVF. We will address these points by the three phases of model development.

Improving treatment outcome assessment in a mouse tuberculosis model.

Science.gov (United States)

Mourik, Bas C; Svensson, Robin J; de Knegt, Gerjo J; Bax, Hannelore I; Verbon, Annelies; Simonsson, Ulrika S H; de Steenwinkel, Jurriaan E M

2018-04-09

Preclinical treatment outcome evaluation of tuberculosis (TB) occurs primarily in mice. Current designs compare relapse rates of different regimens at selected time points, but lack information about the correlation between treatment length and treatment outcome, which is required to efficiently estimate a regimens' treatment-shortening potential. Therefore we developed a new approach. BALB/c mice were infected with a Mycobacterium tuberculosis Beijing genotype strain and were treated with rifapentine-pyrazinamide-isoniazid-ethambutol (R p ZHE), rifampicin-pyrazinamide-moxifloxacin-ethambutol (RZME) or rifampicin-pyrazinamide-moxifloxacin-isoniazid (RZMH). Treatment outcome was assessed in n = 3 mice after 9 different treatment lengths between 2-6 months. Next, we created a mathematical model that best fitted the observational data and used this for inter-regimen comparison. The observed data were best described by a sigmoidal E max model in favor over linear or conventional E max models. Estimating regimen-specific parameters showed significantly higher curative potentials for RZME and R p ZHE compared to RZMH. In conclusion, we provide a new design for treatment outcome evaluation in a mouse TB model, which (i) provides accurate tools for assessment of the relationship between treatment length and predicted cure, (ii) allows for efficient comparison between regimens and (iii) adheres to the reduction and refinement principles of laboratory animal use.

Low plasma bicarbonate predicts poor outcome of cerebral malaria ...

African Journals Online (AJOL)

Malaria remains a major cause of morbidity and mortality in many sub Saharan countries and cerebral malaria is widely recognised as one of its most fatal forms. We studied the predictive value of routine biochemical laboratory indices in predicting the outcome of cerebral malaria in 50 Nigerian children ages 9 months to 6 ...

Outcome prediction in plasmacytoma of bone: a risk model utilizing bone marrow flow cytometry and light-chain analysis.

Science.gov (United States)

Hill, Quentin A; Rawstron, Andy C; de Tute, Ruth M; Owen, Roger G

2014-08-21

The purpose of this study was to use multiparameter flow cytometry to detect occult marrow disease (OMD) in patients with solitary plasmacytoma of bone and assess its value in predicting outcome. Aberrant phenotype plasma cells were demonstrable in 34 of 50 (68%) patients and comprised a median of 0.52% of bone marrow leukocytes. With a median follow-up of 3.7 years, 28 of 50 patients have progressed with a median time to progression (TTP) of 18 months. Progression was documented in 72% of patients with OMD vs 12.5% without (median TTP, 26 months vs not reached; P = .003). Monoclonal urinary light chains (ULC) were similarly predictive of outcome because progression was documented in 91% vs 44% without (median TTP, 16 vs 82 months; P < .001). By using both parameters, it was possible to define patients with an excellent outcome (lacking both OMD and ULC, 7.7% progression) and high-risk patients (OMD and/or ULC, 75% progression; P = .001). Trials of systemic therapy are warranted in high-risk patients. © 2014 by The American Society of Hematology.

Models of Affective Decision Making: How Do Feelings Predict Choice?

Science.gov (United States)

Charpentier, Caroline J; De Neve, Jan-Emmanuel; Li, Xinyi; Roiser, Jonathan P; Sharot, Tali

2016-06-01

Intuitively, how you feel about potential outcomes will determine your decisions. Indeed, an implicit assumption in one of the most influential theories in psychology, prospect theory, is that feelings govern choice. Surprisingly, however, very little is known about the rules by which feelings are transformed into decisions. Here, we specified a computational model that used feelings to predict choices. We found that this model predicted choice better than existing value-based models, showing a unique contribution of feelings to decisions, over and above value. Similar to the value function in prospect theory, our feeling function showed diminished sensitivity to outcomes as value increased. However, loss aversion in choice was explained by an asymmetry in how feelings about losses and gains were weighted when making a decision, not by an asymmetry in the feelings themselves. The results provide new insights into how feelings are utilized to reach a decision. © The Author(s) 2016.

[Gastroschisis: Prenatal ultrasonography and obstetrical criteria for predicting neonatal outcome].

Science.gov (United States)

Ducellier, G; Moussy, P; Sahmoune, L; Bonneau, S; Alanio, E; Bory, J-P

2016-09-01

Prenatal diagnosis of complex laparoschisis is difficult and yet it is associated with a significantly increased morbidity and mortality. The aim of the study was to define ultrasonographic factor and obstetrical criteria to predicting adverse neonatal outcome. Retrospective cohort study over 10 years, of 35 gastroschisis cases in CHU of Reims (France). The primary outcome was the neonatal death due to gastroschisis. The sonographic markers was bowel dilatation intra- or extra-abdominale, amniotic fluid, intra-uterin growth. The obstetrical criteria was fetal vitality, fetal heart rate, type of delivery, the weight and the term of birth. There were 28 live births, 16 children with favorable outcome, 8 children with adverse perinatal outcome and 4 deaths. There were any sonographic criteria to predicting adverse neonatal outcome. Only the birth weight less than 2000g was associated with an increase gastrointestinal complications (P=0.049). The type of the delivery was not associated with an adverse prenatal outcome. The birth weight less than 2000g seems to be associate with an increase gastrointestinal complications. It is important to fight against prematurity in case of gastroschisis. Copyright © 2016 Elsevier Masson SAS. All rights reserved.

Optimizing Prediction Using Bayesian Model Averaging: Examples Using Large-Scale Educational Assessments.

Science.gov (United States)

Kaplan, David; Lee, Chansoon

2018-01-01

This article provides a review of Bayesian model averaging as a means of optimizing the predictive performance of common statistical models applied to large-scale educational assessments. The Bayesian framework recognizes that in addition to parameter uncertainty, there is uncertainty in the choice of models themselves. A Bayesian approach to addressing the problem of model uncertainty is the method of Bayesian model averaging. Bayesian model averaging searches the space of possible models for a set of submodels that satisfy certain scientific principles and then averages the coefficients across these submodels weighted by each model's posterior model probability (PMP). Using the weighted coefficients for prediction has been shown to yield optimal predictive performance according to certain scoring rules. We demonstrate the utility of Bayesian model averaging for prediction in education research with three examples: Bayesian regression analysis, Bayesian logistic regression, and a recently developed approach for Bayesian structural equation modeling. In each case, the model-averaged estimates are shown to yield better prediction of the outcome of interest than any submodel based on predictive coverage and the log-score rule. Implications for the design of large-scale assessments when the goal is optimal prediction in a policy context are discussed.

A behavioral economic reward index predicts drinking resolutions: moderation revisited and compared with other outcomes.

Science.gov (United States)

Tucker, Jalie A; Roth, David L; Vignolo, Mary J; Westfall, Andrew O

2009-04-01

Data were pooled from 3 studies of recently resolved community-dwelling problem drinkers to determine whether a behavioral economic index of the value of rewards available over different time horizons distinguished among moderation (n = 30), abstinent (n = 95), and unresolved (n = 77) outcomes. Moderation over 1- to 2-year prospective follow-up intervals was hypothesized to involve longer term behavior regulation processes than abstinence or relapse and to be predicted by more balanced preresolution monetary allocations between short-term and longer term objectives (i.e., drinking and saving for the future). Standardized odds ratios (ORs) based on changes in standard deviation units from a multinomial logistic regression indicated that increases on this "Alcohol-Savings Discretionary Expenditure" index predicted higher rates of abstinence (OR = 1.93, p = .004) and relapse (OR = 2.89, p moderation outcomes. The index had incremental utility in predicting moderation in complex models that included other established predictors. The study adds to evidence supporting a behavioral economic analysis of drinking resolutions and shows that a systematic analysis of preresolution spending patterns aids in predicting moderation.

Explained variation and predictive accuracy in general parametric statistical models: the role of model misspecification

DEFF Research Database (Denmark)

Rosthøj, Susanne; Keiding, Niels

2004-01-01

When studying a regression model measures of explained variation are used to assess the degree to which the covariates determine the outcome of interest. Measures of predictive accuracy are used to assess the accuracy of the predictions based on the covariates and the regression model. We give a ...... a detailed and general introduction to the two measures and the estimation procedures. The framework we set up allows for a study of the effect of misspecification on the quantities estimated. We also introduce a generalization to survival analysis....

Monitoring risk-adjusted outcomes in congenital heart surgery: does the appropriateness of a risk model change with time?

Science.gov (United States)

Tsang, Victor T; Brown, Katherine L; Synnergren, Mats Johanssen; Kang, Nicholas; de Leval, Marc R; Gallivan, Steve; Utley, Martin

2009-02-01

Risk adjustment of outcomes in pediatric congenital heart surgery is challenging due to the great diversity in diagnoses and procedures. We have previously shown that variable life-adjusted display (VLAD) charts provide an effective graphic display of risk-adjusted outcomes in this specialty. A question arises as to whether the risk model used remains appropriate over time. We used a recently developed graphic technique to evaluate the performance of an existing risk model among those patients at a single center during 2000 to 2003 originally used in model development. We then compared the distribution of predicted risk among these patients with that among patients in 2004 to 2006. Finally, we constructed a VLAD chart of risk-adjusted outcomes for the latter period. Among 1083 patients between April 2000 and March 2003, the risk model performed well at predicted risks above 3%, underestimated mortality at 2% to 3% predicted risk, and overestimated mortality below 2% predicted risk. There was little difference in the distribution of predicted risk among these patients and among 903 patients between June 2004 and October 2006. Outcomes for the more recent period were appreciably better than those expected according to the risk model. This finding cannot be explained by any apparent bias in the risk model combined with changes in case-mix. Risk models can, and hopefully do, become out of date. There is scope for complacency in the risk-adjusted audit if the risk model used is not regularly recalibrated to reflect changing standards and expectations.

Comparing 2 Whiplash Grading Systems to Predict Clinical Outcomes.

Science.gov (United States)

Croft, Arthur C; Bagherian, Alireza; Mickelsen, Patrick K; Wagner, Stephen

2016-06-01

Two whiplash severity grading systems have been developed: Quebec Task Force on Whiplash-Associated Disorders (QTF-WAD) and the Croft grading system. The majority of clinical studies to date have used the modified grading system published by the QTF-WAD in 1995 and have demonstrated some ability to predict outcome. But most studies include only injuries of lower severity (grades 1 and 2), preventing a broader interpretation. The purpose of this study was assess the ability of these grading systems to predict clinical outcome within the context of a broader injury spectrum. This study evaluated both grading systems for their ability to predict the bivalent outcome, recovery, within a sample of 118 whiplash patients who were part of a previous case-control designed study. Of these, 36% (controls) had recovered, and 64% (cases) had not recovered. The discrete bivariate distribution between recovery status and whiplash grade was analyzed using the 2-tailed cross-tabulation statistics. Applying the criteria of the original 1993 Croft grading system, the subset comprised 1 grade 1 injury, 32 grade 2 injuries, 53 grade 3 injuries, and 32 grade 4 injuries. Applying the criteria of the modified (QTF-WAD) grading system, there were 1 grade 1 injury, 89 grade 2 injuries, and 28 grade 3 injuries. Both whiplash grading systems correlated negatively with recovery; that is, higher severity grades predicted a lower probability of recovery, and statistically significant correlations were observed in both, but the Croft grading system substantially outperformed the QTF-WAD system on this measure. The Croft grading system for whiplash injury severity showed a better predictive measure for recovery status from whiplash injuries as compared with the QTF-WAD grading system.

Predicting Positive Education Outcomes for Emerging Adults in Mental Health Systems of Care.

Science.gov (United States)

Brennan, Eileen M; Nygren, Peggy; Stephens, Robert L; Croskey, Adrienne

2016-10-01

Emerging adults who receive services based on positive youth development models have shown an ability to shape their own life course to achieve positive goals. This paper reports secondary data analysis from the Longitudinal Child and Family Outcome Study including 248 culturally diverse youth ages 17 through 22 receiving mental health services in systems of care. After 12 months of services, school performance was positively related to youth ratings of school functioning and service participation and satisfaction. Regression analysis revealed ratings of young peoples' perceptions of school functioning, and their experience in services added to the significant prediction of satisfactory school performance, even controlling for sex and attendance. Finally, in addition to expected predictors, participation in planning their own services significantly predicted enrollment in higher education for those who finished high school. Findings suggest that programs and practices based on positive youth development approaches can improve educational outcomes for emerging adults.

Comparison of TMS and DTT for predicting motor outcome in intracerebral hemorrhage.

Science.gov (United States)

Jang, Sung Ho; Ahn, Sang Ho; Sakong, Joon; Byun, Woo Mok; Choi, Byung Yun; Chang, Chul Hoon; Bai, Daiseg; Son, Su Min

2010-03-15

TMS (transcranial magnetic stimulation) and DTT (diffusion tensor tractography) have different advantages in evaluating stroke patients. TMS has good clinical accessibility and economical benefit. On the contrary, DTT has a unique advantage to visualize neural tracts three-dimensionally although it requires an expensive and large MRI machine. Many studies have demonstrated that TMS and DTT have predictive values for motor outcome in stroke patients. However, there has been no study on the comparison of these two evaluation tools. In the current study, we compared the abilities of TMS and DTT to predict upper motor outcome in patients with ICH (intracerebral hemorrhage). Fifty-three consecutive patients with severe motor weakness were evaluated by TMS and DTT at the early stage (7-28 days) of ICH. Modified Brunnstrom classification (MBC) and the motricity index of upper extremity (UMI) were evaluated at onset and 6 months after onset. Patients with the presence of a motor evoked potential (MEP) in TMS or a preserved corticospinal tract (CST) in DTT showed better motor outcomes than those without (p=0.000). TMS showed higher positive predictive value than DTT. In contrast, DTT showed higher negative predictive value than TMS. TMS and DTT had different advantages in predicting motor outcome, and this result could be a reference to predict final neurological deficit at the early stage of ICH.

Looking for students'personal characteristics predicting study outcome

NARCIS (Netherlands)

Bergen, T.C.M.; Bragt, van C.A.C.; Bakx, A.W.E.A.; Croon, M.A.

2011-01-01

Abstract The central goal of this study is to clarify to what degree former education and students’ personal characteristics (the ‘Big Five personality characteristics’, personal orientations on learning and students’ study approach) may predict study outcome (required credits and study

Looking for students' personal characteristics predicting study outcome.

NARCIS (Netherlands)

Dr. A. Bakx; Theo Bergen; Dr. Cyrille A.C. Van Bragt; Marcel Croon

2011-01-01

Abstract The central goal of this study is to clarify to what degree former education and students' personal characteristics (the 'Big Five personality characteristics', personal orientations on learning and students' study approach) may predict study outcome (required credits and study

Prediction of medication non-adherence and associated outcomes in pediatric kidney transplant recipients.

Science.gov (United States)

Connelly, James; Pilch, N; Oliver, M; Jordan, C; Fleming, J; Meadows, H; Baliga, P; Nadig, S; Twombley, K; Shatat, I; Taber, D

2015-08-01

Studies have continued to evaluate risk factors associated with post-transplant non-adherence in pediatric patients. However, many of these studies fail to evaluate how risk factors can be utilized to predict MNA. The aims of this study were to (i) determine salient risk factors associated with MNA to develop an adequate predictive risk model and (ii) assess transplant outcomes based on the presence of MNA in a large, diverse cohort of pediatric KTX recipients. One hundred and seventy-five solitary pediatric KTX recipients transplanted from 1999 to 2013 were included. AA, males, older patients, those who lived in urban environments, had legal issues, and lived shorter distances from the transplant center were more likely to have MNA. Using logistic regression, a parsimonious model applying nine risk factors together was developed for predicting MNA, demonstrating a PPV of 69% and a NPV of 81%. Patients with MNA had more than twice the risk of biopsy proven acute rejection, 1.6 times the risk of hospitalization, and 1.8 times the risk of graft loss. Utilization of a predictive model to determine risk of MNA after pediatric KTX may offer clinicians the ability to efficiently and effectively monitor MNA following transplant. © 2015 John Wiley & Sons A/S. Published by John Wiley & Sons Ltd.

Output from Statistical Predictive Models as Input to eLearning Dashboards

Directory of Open Access Journals (Sweden)

Marlene A. Smith

2015-06-01

Full Text Available We describe how statistical predictive models might play an expanded role in educational analytics by giving students automated, real-time information about what their current performance means for eventual success in eLearning environments. We discuss how an online messaging system might tailor information to individual students using predictive analytics. The proposed system would be data-driven and quantitative; e.g., a message might furnish the probability that a student will successfully complete the certificate requirements of a massive open online course. Repeated messages would prod underperforming students and alert instructors to those in need of intervention. Administrators responsible for accreditation or outcomes assessment would have ready documentation of learning outcomes and actions taken to address unsatisfactory student performance. The article’s brief introduction to statistical predictive models sets the stage for a description of the messaging system. Resources and methods needed to develop and implement the system are discussed.

Predictive model for risk of cesarean section in pregnant women after induction of labor.

Science.gov (United States)

Hernández-Martínez, Antonio; Pascual-Pedreño, Ana I; Baño-Garnés, Ana B; Melero-Jiménez, María R; Tenías-Burillo, José M; Molina-Alarcón, Milagros

2016-03-01

To develop a predictive model for risk of cesarean section in pregnant women after induction of labor. A retrospective cohort study was conducted of 861 induced labors during 2009, 2010, and 2011 at Hospital "La Mancha-Centro" in Alcázar de San Juan, Spain. Multivariate analysis was used with binary logistic regression and areas under the ROC curves to determine predictive ability. Two predictive models were created: model A predicts the outcome at the time the woman is admitted to the hospital (before the decision to of the method of induction); and model B predicts the outcome at the time the woman is definitely admitted to the labor room. The predictive factors in the final model were: maternal height, body mass index, nulliparity, Bishop score, gestational age, macrosomia, gender of fetus, and the gynecologist's overall cesarean section rate. The predictive ability of model A was 0.77 [95% confidence interval (CI) 0.73-0.80] and model B was 0.79 (95% CI 0.76-0.83). The predictive ability for pregnant women with previous cesarean section with model A was 0.79 (95% CI 0.64-0.94) and with model B was 0.80 (95% CI 0.64-0.96). For a probability of estimated cesarean section ≥80%, the models A and B presented a positive likelihood ratio (+LR) for cesarean section of 22 and 20, respectively. Also, for a likelihood of estimated cesarean section ≤10%, the models A and B presented a +LR for vaginal delivery of 13 and 6, respectively. These predictive models have a good discriminative ability, both overall and for all subgroups studied. This tool can be useful in clinical practice, especially for pregnant women with previous cesarean section and diabetes.

Do infant vocabulary skills predict school-age language and literacy outcomes?

Science.gov (United States)

Duff, Fiona J; Reen, Gurpreet; Plunkett, Kim; Nation, Kate

2015-01-01

Background Strong associations between infant vocabulary and school-age language and literacy skills would have important practical and theoretical implications: Preschool assessment of vocabulary skills could be used to identify children at risk of reading and language difficulties, and vocabulary could be viewed as a cognitive foundation for reading. However, evidence to date suggests predictive ability from infant vocabulary to later language and literacy is low. This study provides an investigation into, and interpretation of, the magnitude of such infant to school-age relationships. Methods Three hundred British infants whose vocabularies were assessed by parent report in the 2nd year of life (between 16 and 24 months) were followed up on average 5 years later (ages ranged from 4 to 9 years), when their vocabulary, phonological and reading skills were measured. Results Structural equation modelling of age-regressed scores was used to assess the strength of longitudinal relationships. Infant vocabulary (a latent factor of receptive and expressive vocabulary) was a statistically significant predictor of later vocabulary, phonological awareness, reading accuracy and reading comprehension (accounting for between 4% and 18% of variance). Family risk for language or literacy difficulties explained additional variance in reading (approximately 10%) but not language outcomes. Conclusions Significant longitudinal relationships between preliteracy vocabulary knowledge and subsequent reading support the theory that vocabulary is a cognitive foundation of both reading accuracy and reading comprehension. Importantly however, the stability of vocabulary skills from infancy to later childhood is too low to be sufficiently predictive of language outcomes at an individual level – a finding that fits well with the observation that the majority of ‘late talkers’ resolve their early language difficulties. For reading outcomes, prediction of future difficulties is likely to

Proteomic signature of periodontal disease in pregnancy: Predictive validity for adverse outcomes.

Science.gov (United States)

Ramchandani, Manisha; Siddiqui, Muniza; Kanwar, Raveena; Lakha, Manwinder; Phi, Linda; Giacomelli, Luca; Chiappelli, Francesco

2011-01-06

The rate of preterm birth is a public health concern worldwide because it is increasing and efforts to prevent it have failed. We report a Clinically Relevant Complex Systematic Review (CSCSR) designed to identify and evaluate the best available evidence in support of the association between periodontal status in women and pregnancy outcome of preterm low birth weight. We hypothesize that the traditional limits of research synthesis must be expanded to incorporate a translational component. As a proof-of-concept model, we propose that this CSCSR can yield greater validity of efficacy and effectiveness through supplementing its recommendations with data of the proteomic signature of periodontal disease in pregnancy, which can contribute to addressing specifically the predictive validity for adverse outcomes. For this CRCSR, systematic reviews were identified through The National Library of MedicinePubmed, The Cochrane library, CINAHL, Google Scholar, Web of Science, and the American Dental Association web library. Independent reviewers quantified the relevance and quality of this literature with R-AMSTAR. Homogeneity and inter-rater reliability testing were supplemented with acceptable sampling analysis. Research synthesis outcomes were analyzed qualitatively toward a Bayesian inference, and converge to demonstrate a definite association between maternal periodontal disease and pregnancy outcome. This CRCSR limits heterogeneity in terms of periodontal disease, outcome measure, selection bias, uncontrolled confounders and effect modifiers. Taken together, the translational CRCSR model we propose suggests that further research is advocated to explore the fundamental mechanisms underlying this association, from a molecular and proteomic perspective.

Bootstrap prediction and Bayesian prediction under misspecified models

OpenAIRE

Fushiki, Tadayoshi

2005-01-01

We consider a statistical prediction problem under misspecified models. In a sense, Bayesian prediction is an optimal prediction method when an assumed model is true. Bootstrap prediction is obtained by applying Breiman's `bagging' method to a plug-in prediction. Bootstrap prediction can be considered to be an approximation to the Bayesian prediction under the assumption that the model is true. However, in applications, there are frequently deviations from the assumed model. In this paper, bo...

New Guideline for the Reporting of Studies Developing, Validating, or Updating a Multivariable Clinical Prediction Model : The TRIPOD Statement

NARCIS (Netherlands)

Moons, Karel G. M.; Altman, Douglas G.; Reitsma, Johannes B.; Collins, Gary S.

Prediction models are developed to aid health care providers in estimating the probability that a specific outcome or disease is present (diagnostic prediction models) or will occur in the future (prognostic prediction models), to inform their decision making. Prognostic models here also include

Predictive value of cognition for different domains of outcome in recent-onset schizophrenia.

Science.gov (United States)

Holthausen, Esther A E; Wiersma, Durk; Cahn, Wiepke; Kahn, René S; Dingemans, Peter M; Schene, Aart H; van den Bosch, Robert J

2007-01-15

The aim of this study was to see whether and how cognition predicts outcome in recent-onset schizophrenia in a large range of domains such as course of illness, self-care, interpersonal functioning, vocational functioning and need for care. At inclusion, 115 recent-onset patients were tested on a cognitive battery and 103 patients participated in the follow-up 2 years after inclusion. Differences in outcome between cognitively normal and cognitively impaired patients were also analysed. Cognitive measures at inclusion did not predict number of relapses, activities of daily living and interpersonal functioning. Time in psychosis or in full remission, as well as need for care, were partly predicted by specific cognitive measures. Although statistically significant, the predictive value of cognition with regard to clinical outcome was limited. There was a significant difference between patients with and without cognitive deficits in competitive employment status and vocational functioning. The predictive value of cognition for different social outcome domains varies. It seems that cognition most strongly predicts work performance, where having a cognitive deficit, regardless of the nature of the deficit, acts as a rate-limiting factor.

Testing process predictions of models of risky choice: a quantitative model comparison approach

Science.gov (United States)

Pachur, Thorsten; Hertwig, Ralph; Gigerenzer, Gerd; Brandstätter, Eduard

2013-01-01

This article presents a quantitative model comparison contrasting the process predictions of two prominent views on risky choice. One view assumes a trade-off between probabilities and outcomes (or non-linear functions thereof) and the separate evaluation of risky options (expectation models). Another view assumes that risky choice is based on comparative evaluation, limited search, aspiration levels, and the forgoing of trade-offs (heuristic models). We derived quantitative process predictions for a generic expectation model and for a specific heuristic model, namely the priority heuristic (Brandstätter et al., 2006), and tested them in two experiments. The focus was on two key features of the cognitive process: acquisition frequencies (i.e., how frequently individual reasons are looked up) and direction of search (i.e., gamble-wise vs. reason-wise). In Experiment 1, the priority heuristic predicted direction of search better than the expectation model (although neither model predicted the acquisition process perfectly); acquisition frequencies, however, were inconsistent with both models. Additional analyses revealed that these frequencies were primarily a function of what Rubinstein (1988) called “similarity.” In Experiment 2, the quantitative model comparison approach showed that people seemed to rely more on the priority heuristic in difficult problems, but to make more trade-offs in easy problems. This finding suggests that risky choice may be based on a mental toolbox of strategies. PMID:24151472

Testing Process Predictions of Models of Risky Choice: A Quantitative Model Comparison Approach

Directory of Open Access Journals (Sweden)

Thorsten ePachur

2013-09-01

Full Text Available This article presents a quantitative model comparison contrasting the process predictions of two prominent views on risky choice. One view assumes a trade-off between probabilities and outcomes (or nonlinear functions thereof and the separate evaluation of risky options (expectation models. Another view assumes that risky choice is based on comparative evaluation, limited search, aspiration levels, and the forgoing of trade-offs (heuristic models. We derived quantitative process predictions for a generic expectation model and for a specific heuristic model, namely the priority heuristic (Brandstätter, Gigerenzer, & Hertwig, 2006, and tested them in two experiments. The focus was on two key features of the cognitive process: acquisition frequencies (i.e., how frequently individual reasons are looked up and direction of search (i.e., gamble-wise vs. reason-wise. In Experiment 1, the priority heuristic predicted direction of search better than the expectation model (although neither model predicted the acquisition process perfectly; acquisition frequencies, however, were inconsistent with both models. Additional analyses revealed that these frequencies were primarily a function of what Rubinstein (1988 called similarity. In Experiment 2, the quantitative model comparison approach showed that people seemed to rely more on the priority heuristic in difficult problems, but to make more trade-offs in easy problems. This finding suggests that risky choice may be based on a mental toolbox of strategies.

Is the AIMS65 score useful in predicting outcomes in peptic ulcer bleeding?

Science.gov (United States)

Jung, Sung Hoon; Oh, Jung Hwan; Lee, Hye Yeon; Jeong, Joon Won; Go, Se Eun; You, Chan Ran; Jeon, Eun Jung; Choi, Sang Wook

2014-02-21

To evaluate the applicability of AIMS65 scores in predicting outcomes of peptic ulcer bleeding. This was a retrospective study in a single center between January 2006 and December 2011. We enrolled 522 patients with upper gastrointestinal haemorrhage who visited the emergency room. High-risk patients were regarded as those who had re-bleeding within 30 d from the first endoscopy as well as those who died within 30 d of visiting the Emergency room. A total of 149 patients with peptic ulcer bleeding were analysed, and the AIMS65 score was used to retrospectively predict the high-risk patients. A total of 149 patients with peptic ulcer bleeding were analysed. The poor outcome group comprised 28 patients [male: 23 (82.1%) vs female: 5 (10.7%)] while the good outcome group included 121 patients [male: 93 (76.9%) vs female: 28 (23.1%)]. The mean age in each group was not significantly different. The mean serum albumin levels in the poor outcome group were slightly lower than those in the good outcome group (P = 0.072). For the prediction of poor outcome, the AIMS65 score had a sensitivity of 35.5% (95%CI: 27.0-44.8) and a specificity of 82.1% (95%CI: 63.1-93.9) at a score of 0. The AIMS65 score was insufficient for predicting outcomes in peptic ulcer bleeding (area under curve = 0.571; 95%CI: 0.49-0.65). The AIMS65 score may therefore not be suitable for predicting clinical outcomes in peptic ulcer bleeding. Low albumin levels may be a risk factor associated with high mortality in peptic ulcer bleeding.

Prediction of surgical outcome in compressive cervical myelopathy: A novel clinicoradiological prognostic score

Directory of Open Access Journals (Sweden)

Rishi Anil Aggarwal

2016-01-01

Full Text Available Context: Preoperative severity of myelopathy, age, and duration of symptoms have been shown to be highly predictive of the outcome in compressive cervical myelopathy (CCM. The role of radiological parameters is still controversial. Aims: Define the prognostic factors in CCM and formulate a prognostic score to predict the outcome following surgery in CCM. Settings and Design: Retrospective. Materials and Methods: This study included 78 consecutive patients with CCM treated surgically. The modified Japanese Orthopaedic Association (mJOA scale was used to quantify severity of myelopathy at admission and at 12-month follow-up. The outcome was defined as "good" if the patient had mJOA score ≥16 and "poor" if the score was <16. Age, sex, duration of symptoms, comorbidities, intrinsic hand muscle wasting (IHMW, diagnosis, surgical technique, Torg ratio, instability on dynamic radiographs, and magnetic resonance imaging (MRI signal intensity changes were assessed. Statistics: Statistical Package for the Social Sciences (SPSS (version 20.0 was used for statistical analysis. The association was assessed amongst variables using logistic regression analysis. Parameters having a statistically significant correlation with the outcome were included in formulating a prognostic score. Results: Severity of myelopathy, IHMW, age, duration, diabetes, and instability on radiographs were predictive of the outcome with a P value <0.01. Genders, diagnosis, surgical procedure, Torg ratio, and intensity changes on MRI were not significantly related to the outcome. A 8-point scoring system was devised incorporating the significant clinicoradiological parameters, and it was found that nearly all patients (97.82% with a score below 5 had good outcome and all patients (100% with a score above 5 had poor outcome. The outcome is difficult to predict with a score of 5. Conclusions: Clinical parameters are better predictors of the outcome as compared to radiological findings

Sepsis progression and outcome: a dynamical model

Directory of Open Access Journals (Sweden)

Gessler Damian DG

2006-02-01

Full Text Available Abstract Background Sepsis (bloodstream infection is the leading cause of death in non-surgical intensive care units. It is diagnosed in 750,000 US patients per annum, and has high mortality. Current understanding of sepsis is predominately observational and correlational, with only a partial and incomplete understanding of the physiological dynamics underlying the syndrome. There exists a need for dynamical models of sepsis progression, based upon basic physiologic principles, which could eventually guide hourly treatment decisions. Results We present an initial mathematical model of sepsis, based on metabolic rate theory that links basic vascular and immunological dynamics. The model includes the rate of vascular circulation, a surrogate for the metabolic rate that is mechanistically associated with disease progression. We use the mass-specific rate of blood circulation (SRBC, a correlate of the body mass index, to build a differential equation model of circulation, infection, organ damage, and recovery. This introduces a vascular component into an infectious disease model that describes the interaction between a pathogen and the adaptive immune system. Conclusion The model predicts that deviations from normal SRBC correlate with disease progression and adverse outcome. We compare the predictions with population mortality data from cardiovascular disease and cancer and show that deviations from normal SRBC correlate with higher mortality rates.

Queue-based modelling and detection of parameters involved in stroke outcome

DEFF Research Database (Denmark)

Vilic, Adnan; Petersen, John Asger; Wienecke, Troels

2017-01-01

We designed a queue-based model, and investigated which parameters are of importance when predicting stroke outcome. Medical record forms have been collected for 57 ischemic stroke patients, including medical history and vital sign measurement along with neurological scores for the first twenty...

Adaptive Encoding of Outcome Prediction by Prefrontal Cortex Ensembles Supports Behavioral Flexibility.

Science.gov (United States)

Del Arco, Alberto; Park, Junchol; Wood, Jesse; Kim, Yunbok; Moghaddam, Bita

2017-08-30

The prefrontal cortex (PFC) is thought to play a critical role in behavioral flexibility by monitoring action-outcome contingencies. How PFC ensembles represent shifts in behavior in response to changes in these contingencies remains unclear. We recorded single-unit activity and local field potentials in the dorsomedial PFC (dmPFC) of male rats during a set-shifting task that required them to update their behavior, among competing options, in response to changes in action-outcome contingencies. As behavior was updated, a subset of PFC ensembles encoded the current trial outcome before the outcome was presented. This novel outcome-prediction encoding was absent in a control task, in which actions were rewarded pseudorandomly, indicating that PFC neurons are not merely providing an expectancy signal. In both control and set-shifting tasks, dmPFC neurons displayed postoutcome discrimination activity, indicating that these neurons also monitor whether a behavior is successful in generating rewards. Gamma-power oscillatory activity increased before the outcome in both tasks but did not differentiate between expected outcomes, suggesting that this measure is not related to set-shifting behavior but reflects expectation of an outcome after action execution. These results demonstrate that PFC neurons support flexible rule-based action selection by predicting outcomes that follow a particular action. SIGNIFICANCE STATEMENT Tracking action-outcome contingencies and modifying behavior when those contingencies change is critical to behavioral flexibility. We find that ensembles of dorsomedial prefrontal cortex neurons differentiate between expected outcomes when action-outcome contingencies change. This predictive mode of signaling may be used to promote a new response strategy at the service of behavioral flexibility. Copyright © 2017 the authors 0270-6474/17/378363-11$15.00/0.

Development and validation of risk models to predict outcomes following in-hospital cardiac arrest attended by a hospital-based resuscitation team☆

Science.gov (United States)

Harrison, David A.; Patel, Krishna; Nixon, Edel; Soar, Jasmeet; Smith, Gary B.; Gwinnutt, Carl; Nolan, Jerry P.; Rowan, Kathryn M.

2014-01-01

Aim The National Cardiac Arrest Audit (NCAA) is the UK national clinical audit for in-hospital cardiac arrest. To make fair comparisons among health care providers, clinical indicators require case mix adjustment using a validated risk model. The aim of this study was to develop and validate risk models to predict outcomes following in-hospital cardiac arrest attended by a hospital-based resuscitation team in UK hospitals. Methods Risk models for two outcomes—return of spontaneous circulation (ROSC) for greater than 20 min and survival to hospital discharge—were developed and validated using data for in-hospital cardiac arrests between April 2011 and March 2013. For each outcome, a full model was fitted and then simplified by testing for non-linearity, combining categories and stepwise reduction. Finally, interactions between predictors were considered. Models were assessed for discrimination, calibration and accuracy. Results 22,479 in-hospital cardiac arrests in 143 hospitals were included (14,688 development, 7791 validation). The final risk model for ROSC > 20 min included: age (non-linear), sex, prior length of stay in hospital, reason for attendance, location of arrest, presenting rhythm, and interactions between presenting rhythm and location of arrest. The model for hospital survival included the same predictors, excluding sex. Both models had acceptable performance across the range of measures, although discrimination for hospital mortality exceeded that for ROSC > 20 min (c index 0.81 versus 0.72). Conclusions Validated risk models for ROSC > 20 min and hospital survival following in-hospital cardiac arrest have been developed. These models will strengthen comparative reporting in NCAA and support local quality improvement. PMID:24830872

Fetal omphalocele ratios predict outcomes in prenatally diagnosed omphalocele.

Science.gov (United States)

Montero, Freddy J; Simpson, Lynn L; Brady, Paula C; Miller, Russell S

2011-09-01

The objective of the study was to evaluate whether ratios considering omphalocele diameter relative to fetal biometric measurements perform better than giant omphalocele designation at predicting inability to achieve neonatal primary surgical closure. Cases of fetal omphalocele that underwent evaluation between May 2003 and July 2010 were identified. Inclusion was restricted to live births with plan for postnatal repair. Omphalocele diameter upon antenatal ultrasound was compared with abdominal circumference, femur length, and head circumference, yielding the respective omphalocele (O)/abdominal circumference (AC), O/femur length (FL), and O/head circumference (HC) ratios. The absolute measurements were used to classify giant lesions. Omphalocele ratios and giant omphalocele designations were evaluated as predictors of inability to achieve primary repair. Among 25 included cases, staged or delayed closure occurred in 52%. With an optimal cutoff of 0.21 or greater, O/HC best predicted the primary outcome (sensitivity, 84.6%; specificity, 58.3%; odds ratio, 7.7). The O/HC of 0.21 or greater outperformed giant designations. The O/HC of 0.21 or greater best predicted staged or delayed omphalocele closure. Giant omphalocele designation, regardless of definition, poorly predicted outcome. Copyright © 2011 Mosby, Inc. All rights reserved.

Usefulness of the rivermead postconcussion symptoms questionnaire and the trail-making test for outcome prediction in patients with mild traumatic brain injury.

Science.gov (United States)

de Guise, Elaine; Bélanger, Sara; Tinawi, Simon; Anderson, Kirsten; LeBlanc, Joanne; Lamoureux, Julie; Audrit, Hélène; Feyz, Mitra

2016-01-01

The aim of the study was to determine if the Rivermead Postconcussion Symptoms Questionnaire (RPQ) is a better tool for outcome prediction than an objective neuropsychological assessment following mild traumatic brain injury (mTBI). The study included 47 patients with mTBI referred to an outpatient rehabilitation clinic. The RPQ and a brief neuropsychological battery were performed in the first few days following the trauma. The outcome measure used was the Mayo-Portland Adaptability Inventory-4 (MPAI-4) which was completed within the first 3 months. The only variable associated with results on the MPAI-4 was the RPQ score (p < .001). The predictive outcome model including age, education, and the results of the Trail-Making Test-Parts A and B (TMT) had a pseudo-R(2) of .02. When the RPQ score was added, the pseudo-R(2) climbed to .19. This model indicates that the usefulness of the RPQ score and the TMT in predicting moderate-to-severe limitations, while controlling for confounders, is substantial as suggested by a significant increase in the model chi-square value, delta (1df) = 6.517, p < .001. The RPQ and the TMT provide clinicians with a brief and reliable tool for predicting outcome functioning and can help target the need for further intervention and rehabilitation following mTBI.

Decision tree analysis in subarachnoid hemorrhage: prediction of outcome parameters during the course of aneurysmal subarachnoid hemorrhage using decision tree analysis.

Science.gov (United States)

Hostettler, Isabel Charlotte; Muroi, Carl; Richter, Johannes Konstantin; Schmid, Josef; Neidert, Marian Christoph; Seule, Martin; Boss, Oliver; Pangalu, Athina; Germans, Menno Robbert; Keller, Emanuela

2018-01-19

OBJECTIVE The aim of this study was to create prediction models for outcome parameters by decision tree analysis based on clinical and laboratory data in patients with aneurysmal subarachnoid hemorrhage (aSAH). METHODS The database consisted of clinical and laboratory parameters of 548 patients with aSAH who were admitted to the Neurocritical Care Unit, University Hospital Zurich. To examine the model performance, the cohort was randomly divided into a derivation cohort (60% [n = 329]; training data set) and a validation cohort (40% [n = 219]; test data set). The classification and regression tree prediction algorithm was applied to predict death, functional outcome, and ventriculoperitoneal (VP) shunt dependency. Chi-square automatic interaction detection was applied to predict delayed cerebral infarction on days 1, 3, and 7. RESULTS The overall mortality was 18.4%. The accuracy of the decision tree models was good for survival on day 1 and favorable functional outcome at all time points, with a difference between the training and test data sets of decision trees enables exploration of dependent variables in the context of multiple changing influences over the course of an illness. The decision tree currently generated increases awareness of the early systemic stress response, which is seemingly pertinent for prognostication.

Highly accurate prediction of food challenge outcome using routinely available clinical data.

Science.gov (United States)

DunnGalvin, Audrey; Daly, Deirdre; Cullinane, Claire; Stenke, Emily; Keeton, Diane; Erlewyn-Lajeunesse, Mich; Roberts, Graham C; Lucas, Jane; Hourihane, Jonathan O'B

2011-03-01

Serum specific IgE or skin prick tests are less useful at levels below accepted decision points. We sought to develop and validate a model to predict food challenge outcome by using routinely collected data in a diverse sample of children considered suitable for food challenge. The proto-algorithm was generated by using a limited data set from 1 service (phase 1). We retrospectively applied, evaluated, and modified the initial model by using an extended data set in another center (phase 2). Finally, we prospectively validated the model in a blind study in a further group of children undergoing food challenge for peanut, milk, or egg in the second center (phase 3). Allergen-specific models were developed for peanut, egg, and milk. Phase 1 (N = 429) identified 5 clinical factors associated with diagnosis of food allergy by food challenge. In phase 2 (N = 289), we examined the predictive ability of 6 clinical factors: skin prick test, serum specific IgE, total IgE minus serum specific IgE, symptoms, sex, and age. In phase 3 (N = 70), 97% of cases were accurately predicted as positive and 94% as negative. Our model showed an advantage in clinical prediction compared with serum specific IgE only, skin prick test only, and serum specific IgE and skin prick test (92% accuracy vs 57%, and 81%, respectively). Our findings have implications for the improved delivery of food allergy-related health care, enhanced food allergy-related quality of life, and economized use of health service resources by decreasing the number of food challenges performed. Copyright © 2011 American Academy of Allergy, Asthma & Immunology. Published by Mosby, Inc. All rights reserved.

Adolescent Eating Disorders Predict Psychiatric, High-Risk Behaviors and Weight Outcomes in Young Adulthood

Science.gov (United States)

Micali, Nadia; Solmi, Francesca; Horton, Nicholas J.; Crosby, Ross D.; Eddy, Kamryn T.; Calzo, Jerel P.; Sonneville, Kendrin R.; Swanson, Sonja A.; Field, Alison E.

2015-01-01

Objective To investigate whether anorexia nervosa (AN), bulimia nervosa (BN), binge eating disorder (BED), and other specified feeding and eating disorders (OSFED), including purging disorder (PD), subthreshold BN, and BED at ages 14 and 16, are prospectively associated with later depression, anxiety disorders, alcohol and substance use, and self-harm. Method Eating disorders were ascertained at 14 and 16 years of age in 6,140 youth at age 14 (58% of those eligible) and 5,069 at age 16 (52% of those eligible) as part of the prospective Avon Longitudinal Study of Parents and Children (ALSPAC). Outcomes (depression, anxiety disorders, binge drinking, drug use, deliberate self-harm, weight status) were measured using interviews and questionnaires about 2 years following predictors. Generalized estimating equation models adjusting for gender, socio-demographic variables, and prior outcome were used to examine prospective associations between eating disorders and each outcome. Results All eating disorders were predictive of later anxiety disorders. AN, BN, BED, PD, and OSFED were prospectively associated with depression (respectively AN: odds ratio [OR]=1.39 [95% CIs: 1.00-1.94]; BN: OR=3.39[1.25-9.20]; BED: OR=2.00 [1.06-3.75]; PD: OR=2.56 [1.38-4.74]). All eating disorders but AN predicted drug use and deliberate self-harm (BN: OR=5.72[2.22-14.72], PD: OR=4.88[2.78-8.57], subthreshold BN: OR=3.97[1.44-10.98], subthreshold BED: OR=2.32[1.43-3.75]). Whilst BED and BN predicted obesity (respectively OR=3.58 [1.06-12.14] and OR=6.42 [1.69-24.30]), AN was prospectively associated with underweight. Conclusions Adolescent eating disorders, including subthreshold presentations, predict negative outcomes, including mental health disorders, substance use, deliberate self-harm, and weight outcomes. This study highlights the high public health and clinical burden of eating disorders among adolescents. PMID:26210334

Predictive Modelling and Time: An Experiment in Temporal Archaeological Predictive Models

OpenAIRE

David Ebert

2006-01-01

One of the most common criticisms of archaeological predictive modelling is that it fails to account for temporal or functional differences in sites. However, a practical solution to temporal or functional predictive modelling has proven to be elusive. This article discusses temporal predictive modelling, focusing on the difficulties of employing temporal variables, then introduces and tests a simple methodology for the implementation of temporal modelling. The temporal models thus created ar...

Personalized Prediction of Lifetime Benefits with Statin Therapy for Asymptomatic Individuals: A Modeling Study

NARCIS (Netherlands)

B.S. Ferket (Bart); B.J.H. van Kempen (Bob); J. Heeringa (Jan); S. Spronk (Sandra); K.E. Fleischmann (Kirsten); R.L. Nijhuis (Rogier); A. Hofman (Albert); E.W. Steyerberg (Ewout); M.G.M. Hunink (Myriam)

2012-01-01

textabstractBackground: Physicians need to inform asymptomatic individuals about personalized outcomes of statin therapy for primary prevention of cardiovascular disease (CVD). However, current prediction models focus on short-term outcomes and ignore the competing risk of death due to other causes.

A wavelet-based technique to predict treatment outcome for Major Depressive Disorder

Science.gov (United States)

Xia, Likun; Mohd Yasin, Mohd Azhar; Azhar Ali, Syed Saad

2017-01-01

Treatment management for Major Depressive Disorder (MDD) has been challenging. However, electroencephalogram (EEG)-based predictions of antidepressant’s treatment outcome may help during antidepressant’s selection and ultimately improve the quality of life for MDD patients. In this study, a machine learning (ML) method involving pretreatment EEG data was proposed to perform such predictions for Selective Serotonin Reuptake Inhibitor (SSRIs). For this purpose, the acquisition of experimental data involved 34 MDD patients and 30 healthy controls. Consequently, a feature matrix was constructed involving time-frequency decomposition of EEG data based on wavelet transform (WT) analysis, termed as EEG data matrix. However, the resultant EEG data matrix had high dimensionality. Therefore, dimension reduction was performed based on a rank-based feature selection method according to a criterion, i.e., receiver operating characteristic (ROC). As a result, the most significant features were identified and further be utilized during the training and testing of a classification model, i.e., the logistic regression (LR) classifier. Finally, the LR model was validated with 100 iterations of 10-fold cross-validation (10-CV). The classification results were compared with short-time Fourier transform (STFT) analysis, and empirical mode decompositions (EMD). The wavelet features extracted from frontal and temporal EEG data were found statistically significant. In comparison with other time-frequency approaches such as the STFT and EMD, the WT analysis has shown highest classification accuracy, i.e., accuracy = 87.5%, sensitivity = 95%, and specificity = 80%. In conclusion, significant wavelet coefficients extracted from frontal and temporal pre-treatment EEG data involving delta and theta frequency bands may predict antidepressant’s treatment outcome for the MDD patients. PMID:28152063

A wavelet-based technique to predict treatment outcome for Major Depressive Disorder.

Science.gov (United States)

Mumtaz, Wajid; Xia, Likun; Mohd Yasin, Mohd Azhar; Azhar Ali, Syed Saad; Malik, Aamir Saeed

2017-01-01

Treatment management for Major Depressive Disorder (MDD) has been challenging. However, electroencephalogram (EEG)-based predictions of antidepressant's treatment outcome may help during antidepressant's selection and ultimately improve the quality of life for MDD patients. In this study, a machine learning (ML) method involving pretreatment EEG data was proposed to perform such predictions for Selective Serotonin Reuptake Inhibitor (SSRIs). For this purpose, the acquisition of experimental data involved 34 MDD patients and 30 healthy controls. Consequently, a feature matrix was constructed involving time-frequency decomposition of EEG data based on wavelet transform (WT) analysis, termed as EEG data matrix. However, the resultant EEG data matrix had high dimensionality. Therefore, dimension reduction was performed based on a rank-based feature selection method according to a criterion, i.e., receiver operating characteristic (ROC). As a result, the most significant features were identified and further be utilized during the training and testing of a classification model, i.e., the logistic regression (LR) classifier. Finally, the LR model was validated with 100 iterations of 10-fold cross-validation (10-CV). The classification results were compared with short-time Fourier transform (STFT) analysis, and empirical mode decompositions (EMD). The wavelet features extracted from frontal and temporal EEG data were found statistically significant. In comparison with other time-frequency approaches such as the STFT and EMD, the WT analysis has shown highest classification accuracy, i.e., accuracy = 87.5%, sensitivity = 95%, and specificity = 80%. In conclusion, significant wavelet coefficients extracted from frontal and temporal pre-treatment EEG data involving delta and theta frequency bands may predict antidepressant's treatment outcome for the MDD patients.

Predicting The Outcome of Marketing Negotiations: Role-Playing versus Unaided Opinions

OpenAIRE

JS Armstrong; Philip D. Hutcherson

2005-01-01

Role -playing and unaided opinions were used to forecast the outcome of three negotiations. Consistent with prior re search, role-playing yielded more accurate predictions. In two studies on marketing negotiations, the predictions based on role-playing were correct for 53% of the predictions while unaided opinions were correct for only 7% (p

Understanding reproducibility of human IVF traits to predict next IVF cycle outcome.

Science.gov (United States)

Wu, Bin; Shi, Juanzi; Zhao, Wanqiu; Lu, Suzhen; Silva, Marta; Gelety, Timothy J

2014-10-01

Evaluating the failed IVF cycle often provides useful prognostic information. Before undergoing another attempt, patients experiencing an unsuccessful IVF cycle frequently request information about the probability of future success. Here, we introduced the concept of reproducibility and formulae to predict the next IVF cycle outcome. The experimental design was based on the retrospective review of IVF cycle data from 2006 to 2013 in two different IVF centers and statistical analysis. The reproducibility coefficients (r) of IVF traits including number of oocytes retrieved, oocyte maturity, fertilization, embryo quality and pregnancy were estimated using the interclass correlation coefficient between the repeated IVF cycle measurements for the same patient by variance component analysis. The formulae were designed to predict next IVF cycle outcome. The number of oocytes retrieved from patients and their fertilization rate had the highest reproducibility coefficients (r = 0.81 ~ 0.84), which indicated a very close correlation between the first retrieval cycle and subsequent IVF cycles. Oocyte maturity and number of top quality embryos had middle level reproducibility (r = 0.38 ~ 0.76) and pregnancy rate had a relative lower reproducibility (r = 0.23 ~ 0.27). Based on these parameters, the next outcome for these IVF traits might be accurately predicted by the designed formulae. The introduction of the concept of reproducibility to our human IVF program allows us to predict future IVF cycle outcomes. The traits of oocyte numbers retrieved, oocyte maturity, fertilization, and top quality embryos had higher or middle reproducibility, which provides a basis for accurate prediction of future IVF outcomes. Based on this prediction, physicians may counsel their patients or change patient's stimulation plans, and laboratory embryologists may improve their IVF techniques accordingly.

A Behavioral Economic Reward Index Predicts Drinking Resolutions: Moderation Re-visited and Compared with Other Outcomes

Science.gov (United States)

Tucker, Jalie A.; Roth, David L.; Vignolo, Mary J.; Westfall, Andrew O.

2014-01-01

Data were pooled from three studies of recently resolved community-dwelling problem drinkers to determine whether a behavioral economic index of the value of rewards available over different time horizons distinguished among moderation (n = 30), abstinent (n = 95), and unresolved (n = 77) outcomes. Moderation over 1-2 year prospective follow-up intervals was hypothesized to involve longer term behavior regulation processes compared to abstinence or relapse and to be predicted by more balanced pre-resolution monetary allocations between short- and longer-term objectives (i.e., drinking and saving for the future). Standardized odds ratios (OR) based on changes in standard deviation units from a multinomial logistic regression indicated that increases on this “Alcohol-Savings Discretionary Expenditure” index predicted higher rates of both abstinence (OR = 1.93, p = .004) and relapse (OR = 2.89, p moderation outcomes. The index had incremental utility in predicting moderation in complex models that included other established predictors. The study adds to evidence supporting a behavioral economic analysis of drinking resolutions and shows that a systematic analysis of pre-resolution spending patterns aids in predicting moderation. PMID:19309182

Black Hole Sign Predicts Poor Outcome in Patients with Intracerebral Hemorrhage.

Science.gov (United States)

Li, Qi; Yang, Wen-Song; Chen, Sheng-Li; Lv, Fu-Rong; Lv, Fa-Jin; Hu, Xi; Zhu, Dan; Cao, Du; Wang, Xing-Chen; Li, Rui; Yuan, Liang; Qin, Xin-Yue; Xie, Peng

2018-01-01

In spontaneous intracerebral hemorrhage (ICH), black hole sign has been proposed as a promising imaging marker that predicts hematoma expansion in patients with ICH. The aim of our study was to investigate whether admission CT black hole sign predicts hematoma growth in patients with ICH. From July 2011 till February 2016, patients with spontaneous ICH who underwent baseline CT scan within 6 h of symptoms onset and follow-up CT scan were recruited into the study. The presence of black hole sign on admission non-enhanced CT was independently assessed by 2 readers. The functional outcome was assessed using the modified Rankin Scale (mRS) at 90 days. Univariate and multivariable logistic regression analyses were performed to assess the association between the presence of the black hole sign and functional outcome. A total of 225 patients (67.6% male, mean age 60.3 years) were included in our study. Black hole sign was identified in 32 of 225 (14.2%) patients on admission CT scan. The multivariate logistic regression analysis demonstrated that age, intraventricular hemorrhage, baseline ICH volume, admission Glasgow Coma Scale score, and presence of black hole sign on baseline CT independently predict poor functional outcome at 90 days. There are significantly more patients with a poor functional outcome (defined as mRS ≥4) among patients with black hole sign than those without (84.4 vs. 32.1%, p black hole sign independently predicts poor outcome in patients with ICH. Early identification of black hole sign is useful in prognostic stratification and may serve as a potential therapeutic target for anti-expansion clinical trials. © 2018 S. Karger AG, Basel.

Using Predictive Modelling to Identify Students at Risk of Poor University Outcomes

Science.gov (United States)

Jia, Pengfei; Maloney, Tim

2015-01-01

Predictive modelling is used to identify students at risk of failing their first-year courses and not returning to university in the second year. Our aim is twofold. Firstly, we want to understand the factors that lead to poor first-year experiences at university. Secondly, we want to develop simple, low-cost tools that would allow universities to…

Comparisons of prediction models of quality of life after laparoscopic cholecystectomy: a longitudinal prospective study.

Directory of Open Access Journals (Sweden)

Hon-Yi Shi

Full Text Available BACKGROUND: Few studies of laparoscopic cholecystectomy (LC outcome have used longitudinal data for more than two years. Moreover, no studies have considered group differences in factors other than outcome such as age and nonsurgical treatment. Additionally, almost all published articles agree that the essential issue of the internal validity (reproducibility of the artificial neural network (ANN, support vector machine (SVM, Gaussian process regression (GPR and multiple linear regression (MLR models has not been adequately addressed. This study proposed to validate the use of these models for predicting quality of life (QOL after LC and to compare the predictive capability of ANNs with that of SVM, GPR and MLR. METHODOLOGY/PRINCIPAL FINDINGS: A total of 400 LC patients completed the SF-36 and the Gastrointestinal Quality of Life Index at baseline and at 2 years postoperatively. The criteria for evaluating the accuracy of the system models were mean square error (MSE and mean absolute percentage error (MAPE. A global sensitivity analysis was also performed to assess the relative significance of input parameters in the system model and to rank the variables in order of importance. Compared to SVM, GPR and MLR models, the ANN model generally had smaller MSE and MAPE values in the training data set and test data set. Most ANN models had MAPE values ranging from 4.20% to 8.60%, and most had high prediction accuracy. The global sensitivity analysis also showed that preoperative functional status was the best parameter for predicting QOL after LC. CONCLUSIONS/SIGNIFICANCE: Compared with SVM, GPR and MLR models, the ANN model in this study was more accurate in predicting patient-reported QOL and had higher overall performance indices. Further studies of this model may consider the effect of a more detailed database that includes complications and clinical examination findings as well as more detailed outcome data.

Predictive Modelling Risk Calculators and the Non Dialysis Pathway.

Science.gov (United States)

Robins, Jennifer; Katz, Ivor

2013-04-16

This guideline will review the current prediction models and survival/mortality scores available for decision making in patients with advanced kidney disease who are being considered for a non-dialysis treatment pathway. Risk prediction is gaining increasing attention with emerging literature suggesting improved patient outcomes through individualised risk prediction (1). Predictive models help inform the nephrologist and the renal palliative care specialists in their discussions with patients and families about suitability or otherwise of dialysis. Clinical decision making in the care of end stage kidney disease (ESKD) patients on a non-dialysis treatment pathway is currently governed by several observational trials (3). Despite the paucity of evidence based medicine in this field, it is becoming evident that the survival advantages associated with renal replacement therapy in these often elderly patients with multiple co-morbidities and limited functional status may be negated by loss of quality of life (7) (6), further functional decline (5, 8), increased complications and hospitalisations. This article is protected by copyright. All rights reserved.

Development and validation of a risk model for prediction of hazardous alcohol consumption in general practice attendees: the predictAL study.

Science.gov (United States)

King, Michael; Marston, Louise; Švab, Igor; Maaroos, Heidi-Ingrid; Geerlings, Mirjam I; Xavier, Miguel; Benjamin, Vicente; Torres-Gonzalez, Francisco; Bellon-Saameno, Juan Angel; Rotar, Danica; Aluoja, Anu; Saldivia, Sandra; Correa, Bernardo; Nazareth, Irwin

2011-01-01

Little is known about the risk of progression to hazardous alcohol use in people currently drinking at safe limits. We aimed to develop a prediction model (predictAL) for the development of hazardous drinking in safe drinkers. A prospective cohort study of adult general practice attendees in six European countries and Chile followed up over 6 months. We recruited 10,045 attendees between April 2003 to February 2005. 6193 European and 2462 Chilean attendees recorded AUDIT scores below 8 in men and 5 in women at recruitment and were used in modelling risk. 38 risk factors were measured to construct a risk model for the development of hazardous drinking using stepwise logistic regression. The model was corrected for over fitting and tested in an external population. The main outcome was hazardous drinking defined by an AUDIT score ≥8 in men and ≥5 in women. 69.0% of attendees were recruited, of whom 89.5% participated again after six months. The risk factors in the final predictAL model were sex, age, country, baseline AUDIT score, panic syndrome and lifetime alcohol problem. The predictAL model's average c-index across all six European countries was 0.839 (95% CI 0.805, 0.873). The Hedge's g effect size for the difference in log odds of predicted probability between safe drinkers in Europe who subsequently developed hazardous alcohol use and those who did not was 1.38 (95% CI 1.25, 1.51). External validation of the algorithm in Chilean safe drinkers resulted in a c-index of 0.781 (95% CI 0.717, 0.846) and Hedge's g of 0.68 (95% CI 0.57, 0.78). The predictAL risk model for development of hazardous consumption in safe drinkers compares favourably with risk algorithms for disorders in other medical settings and can be a useful first step in prevention of alcohol misuse.

Development and validation of a risk model for prediction of hazardous alcohol consumption in general practice attendees: the predictAL study.

Directory of Open Access Journals (Sweden)

Michael King

Full Text Available Little is known about the risk of progression to hazardous alcohol use in people currently drinking at safe limits. We aimed to develop a prediction model (predictAL for the development of hazardous drinking in safe drinkers.A prospective cohort study of adult general practice attendees in six European countries and Chile followed up over 6 months. We recruited 10,045 attendees between April 2003 to February 2005. 6193 European and 2462 Chilean attendees recorded AUDIT scores below 8 in men and 5 in women at recruitment and were used in modelling risk. 38 risk factors were measured to construct a risk model for the development of hazardous drinking using stepwise logistic regression. The model was corrected for over fitting and tested in an external population. The main outcome was hazardous drinking defined by an AUDIT score ≥8 in men and ≥5 in women.69.0% of attendees were recruited, of whom 89.5% participated again after six months. The risk factors in the final predictAL model were sex, age, country, baseline AUDIT score, panic syndrome and lifetime alcohol problem. The predictAL model's average c-index across all six European countries was 0.839 (95% CI 0.805, 0.873. The Hedge's g effect size for the difference in log odds of predicted probability between safe drinkers in Europe who subsequently developed hazardous alcohol use and those who did not was 1.38 (95% CI 1.25, 1.51. External validation of the algorithm in Chilean safe drinkers resulted in a c-index of 0.781 (95% CI 0.717, 0.846 and Hedge's g of 0.68 (95% CI 0.57, 0.78.The predictAL risk model for development of hazardous consumption in safe drinkers compares favourably with risk algorithms for disorders in other medical settings and can be a useful first step in prevention of alcohol misuse.

Embryo quality predictive models based on cumulus cells gene expression

Directory of Open Access Journals (Sweden)

Devjak R

2016-06-01

Full Text Available Since the introduction of in vitro fertilization (IVF in clinical practice of infertility treatment, the indicators for high quality embryos were investigated. Cumulus cells (CC have a specific gene expression profile according to the developmental potential of the oocyte they are surrounding, and therefore, specific gene expression could be used as a biomarker. The aim of our study was to combine more than one biomarker to observe improvement in prediction value of embryo development. In this study, 58 CC samples from 17 IVF patients were analyzed. This study was approved by the Republic of Slovenia National Medical Ethics Committee. Gene expression analysis [quantitative real time polymerase chain reaction (qPCR] for five genes, analyzed according to embryo quality level, was performed. Two prediction models were tested for embryo quality prediction: a binary logistic and a decision tree model. As the main outcome, gene expression levels for five genes were taken and the area under the curve (AUC for two prediction models were calculated. Among tested genes, AMHR2 and LIF showed significant expression difference between high quality and low quality embryos. These two genes were used for the construction of two prediction models: the binary logistic model yielded an AUC of 0.72 ± 0.08 and the decision tree model yielded an AUC of 0.73 ± 0.03. Two different prediction models yielded similar predictive power to differentiate high and low quality embryos. In terms of eventual clinical decision making, the decision tree model resulted in easy-to-interpret rules that are highly applicable in clinical practice.

Rapid improvements in emotion regulation predict intensive treatment outcome for patients with bulimia nervosa and purging disorder.

Science.gov (United States)

MacDonald, Danielle E; Trottier, Kathryn; Olmsted, Marion P

2017-10-01

Rapid and substantial behavior change (RSBC) early in cognitive behavior therapy (CBT) for eating disorders is the strongest known predictor of treatment outcome. Rapid change in other clinically relevant variables may also be important. This study examined whether rapid change in emotion regulation predicted treatment outcomes, beyond the effects of RSBC. Participants were diagnosed with bulimia nervosa or purging disorder (N = 104) and completed ≥6 weeks of CBT-based intensive treatment. Hierarchical regression models were used to test whether rapid change in emotion regulation variables predicted posttreatment outcomes, defined in three ways: (a) binge/purge abstinence; (b) cognitive eating disorder psychopathology; and (c) depression symptoms. Baseline psychopathology and emotion regulation difficulties and RSBC were controlled for. After controlling for baseline variables and RSBC, rapid improvement in access to emotion regulation strategies made significant unique contributions to the prediction of posttreatment binge/purge abstinence, cognitive psychopathology of eating disorders, and depression symptoms. Individuals with eating disorders who rapidly improve their belief that they can effectively modulate negative emotions are more likely to achieve a variety of good treatment outcomes. This supports the formal inclusion of emotion regulation skills early in CBT, and encouraging patient beliefs that these strategies are helpful. © 2017 Wiley Periodicals, Inc.

Predictive efficacy of radioisotope voiding cystography for renal outcome

International Nuclear Information System (INIS)

Kim, Seok Ki; Lee, Dong Soo; Kim, Kwang Myeung; Choi, Whang; Chung, June Key; Lee, Myung Chul

2000-01-01

As vesicoureteral reflux (VUR) could lead to renal functional deterioration when combined with urinary tract infection, we need to decide whether operative anti-reflux treatment should be performed at the time of diagnosis of VUR. Predictive value of radioisotope voiding cystography (RIVCG) for renal outcome was tested. In 35 children (18 males, 17 females), radiologic voiding cystoure-thrography (VCU), RIVCG and DMSA scan were performed. Change in renal function was evaluated using the follow-up DMSA scan, ultrasonography, and clinical information. Discriminant analysis was performed using individual or integrated variables such as reflux amount and extent at each phase of voiding on RIVCG, in addition to age, gender and cortical defect on DMSA scan at the time of diagnosis. Discriminant function was composed and its performance was examined. Reflux extent at the filling phase and reflux amount and extent at postvoiding phase had a significant prognostic value. Total reflux amount was a composite variable to predict prognosis. Discriminant function composed of reflux extent at the filling phase and reflux amount and extent at postvoiding phase showed better positive predictive value and specificity than conventional reflux grading. RIVCG could predict renal outcome by disclosing characteristic reflux pattern during various voiding phases.=20

Predicting an optimal outcome after radical prostatectomy: the trifecta nomogram.

Science.gov (United States)

Eastham, James A; Scardino, Peter T; Kattan, Michael W

2008-06-01

The optimal outcome after radical prostatectomy for clinically localized prostate cancer is freedom from biochemical recurrence along with the recovery of continence and erectile function, a so-called trifecta. We evaluated our series of open radical prostatectomy cases to determine the likelihood of this outcome and develop a nomogram predicting the trifecta. We reviewed the records of patients undergoing open radical prostatectomy for clinical stage T1c-T3a prostate cancer at our center during 2000 to 2006. Men were excluded if they received preoperative hormonal therapy, chemotherapy or radiation therapy, if pretreatment prostate specific antigen was more than 50 ng/ml, or if they were impotent or incontinent before radical prostatectomy. A total of 1,577 men were included in the study. Freedom from biochemical recurrence was defined as post-radical prostatectomy prostate specific antigen less than 0.2 ng/ml. Continence was defined as not having to wear any protective pads. Potency was defined as erection adequate for intercourse upon most attempts with or without phosphodiesterase-5 inhibitor. Mean patient age was 58 years and mean pretreatment prostate specific antigen was 6.4 ng/ml. A trifecta outcome (cancer-free status with recovery of continence and potency) was achieved in 62% of patients. In a nomogram developed to predict the likelihood of the trifecta baseline prostate specific antigen was the major predictive factor. Area under the ROC curve for the nomogram was 0.773 and calibration appeared excellent. A trifecta (optimal) outcome can be achieved in most men undergoing radical prostatectomy. The nomogram permits patients to estimate preoperatively their likelihood of an optimal outcome after radical prostatectomy.

Prediction of 90Y Radioembolization Outcome from Pretherapeutic Factors with Random Survival Forests.

Science.gov (United States)

Ingrisch, Michael; Schöppe, Franziska; Paprottka, Karolin; Fabritius, Matthias; Strobl, Frederik F; De Toni, Enrico N; Ilhan, Harun; Todica, Andrei; Michl, Marlies; Paprottka, Philipp Marius

2018-05-01

Our objective was to predict the outcome of 90 Y radioembolization in patients with intrahepatic tumors from pretherapeutic baseline parameters and to identify predictive variables using a machine-learning approach based on random survival forests. Methods: In this retrospective study, 366 patients with primary ( n = 92) or secondary ( n = 274) liver tumors who had received 90 Y radioembolization were analyzed. A random survival forest was trained to predict individual risk from baseline values of cholinesterase, bilirubin, type of primary tumor, age at radioembolization, hepatic tumor burden, presence of extrahepatic disease, and sex. The predictive importance of each baseline parameter was determined using the minimal-depth concept, and the partial dependency of predicted risk on the continuous variables bilirubin level and cholinesterase level was determined. Results: Median overall survival was 11.4 mo (95% confidence interval, 9.7-14.2 mo), with 228 deaths occurring during the observation period. The random-survival-forest analysis identified baseline cholinesterase and bilirubin as the most important variables (forest-averaged lowest minimal depth, 1.2 and 1.5, respectively), followed by the type of primary tumor (1.7), age (2.4), tumor burden (2.8), and presence of extrahepatic disease (3.5). Sex had the highest forest-averaged minimal depth (5.5), indicating little predictive value. Baseline bilirubin levels above 1.5 mg/dL were associated with a steep increase in predicted mortality. Similarly, cholinesterase levels below 7.5 U predicted a strong increase in mortality. The trained random survival forest achieved a concordance index of 0.657, with an SE of 0.02, comparable to the concordance index of 0.652 and SE of 0.02 for a previously published Cox proportional hazards model. Conclusion: Random survival forests are a simple and straightforward machine-learning approach for prediction of overall survival. The predictive performance of the trained model

Characterizing Tumor Heterogeneity With Functional Imaging and Quantifying High-Risk Tumor Volume for Early Prediction of Treatment Outcome: Cervical Cancer as a Model

International Nuclear Information System (INIS)

Mayr, Nina A.; Huang Zhibin; Wang, Jian Z.; Lo, Simon S.; Fan, Joline M.; Grecula, John C.; Sammet, Steffen; Sammet, Christina L.; Jia Guang; Zhang Jun; Knopp, Michael V.; Yuh, William T.C.

2012-01-01

Purpose: Treatment response in cancer has been monitored by measuring anatomic tumor volume (ATV) at various times without considering the inherent functional tumor heterogeneity known to critically influence ultimate treatment outcome: primary tumor control and survival. This study applied dynamic contrast-enhanced (DCE) functional MRI to characterize tumors' heterogeneous subregions with low DCE values, at risk for treatment failure, and to quantify the functional risk volume (FRV) for personalized early prediction of treatment outcome. Methods and Materials: DCE-MRI was performed in 102 stage IB 2 –IVA cervical cancer patients to assess tumor perfusion heterogeneity before and during radiation/chemotherapy. FRV represents the total volume of tumor voxels with critically low DCE signal intensity ( 20, >13, and >5 cm 3 , respectively, significantly predicted unfavorable 6-year primary tumor control (p = 0.003, 7.3 × 10 −8 , 2.0 × 10 −8 ) and disease-specific survival (p = 1.9 × 10 −4 , 2.1 × 10 −6 , 2.5 × 10 −7 , respectively). The FRVs were superior to the ATVs as early predictors of outcome, and the differentiating power of FRVs increased during treatment. Discussion: Our preliminary results suggest that functional tumor heterogeneity can be characterized by DCE-MRI to quantify FRV for predicting ultimate long-term treatment outcome. FRV is a novel functional imaging heterogeneity parameter, superior to ATV, and can be clinically translated for personalized early outcome prediction before or as early as 2–5 weeks into treatment.

Clinical Nomogram for Predicting Survival Outcomes in Early Mucinous Breast Cancer.

Directory of Open Access Journals (Sweden)

Jianfei Fu

Full Text Available The features related to the prognosis of patients with mucinous breast cancer (MBC remain controversial. We aimed to explore the prognostic factors of MBC and develop a nomogram for predicting survival outcomes.The Surveillance, Epidemiology, and End Results (SEER database was searched to identify 139611 women with resectable breast cancer from 1990 to 2007. Survival curves were generated using Kaplan-Meier methods. The 5-year and 10-year cancer-specific survival (CSS rates were calculated using the Life-Table method. Based on Cox models, a nomogram was constructed to predict the probabilities of CSS for an individual patient. The competing risk regression model was used to analyse the specific survival of patients with MBC.There were 136569 (97.82% infiltrative ductal cancer (IDC patients and 3042 (2.18% MBC patients. Patients with MBC had less lymph node involvement, a higher frequency of well-differentiated lesions, and more estrogen receptor (ER-positive tumors. Patients with MBC had significantly higher 5 and10-year CSS rates (98.23 and 96.03%, respectively than patients with IDC (91.44 and 85.48%, respectively. Univariate and multivariate analyses showed that MBC was an independent factor for better prognosis. As for patients with MBC, the event of death caused by another disease exceeded the event of death caused by breast cancer. A competing risk regression model further showed that lymph node involvement, poorly differentiated grade and advanced T-classification were independent factors of poor prognosis in patients with MBC. The Nomogram can accurately predict CSS with a high C-index (0.816. Risk scores developed from the nomogram can more accurately predict the prognosis of patients with MBC (C-index = 0.789 than the traditional TNM system (C-index = 0.704, P< 0.001.Patients with MBC have a better prognosis than patients with IDC. Nomograms could help clinicians make more informed decisions in clinical practice. The competing risk

Atterberg Limits Prediction Comparing SVM with ANFIS Model

Directory of Open Access Journals (Sweden)

Mohammad Murtaza Sherzoy

2017-03-01

Full Text Available Support Vector Machine (SVM and Adaptive Neuro-Fuzzy inference Systems (ANFIS both analytical methods are used to predict the values of Atterberg limits, such as the liquid limit, plastic limit and plasticity index. The main objective of this study is to make a comparison between both forecasts (SVM & ANFIS methods. All data of 54 soil samples are used and taken from the area of Peninsular Malaysian and tested for different parameters containing liquid limit, plastic limit, plasticity index and grain size distribution and were. The input parameter used in for this case are the fraction of grain size distribution which are the percentage of silt, clay and sand. The actual and predicted values of Atterberg limit which obtained from the SVM and ANFIS models are compared by using the correlation coefficient R2 and root mean squared error (RMSE value.  The outcome of the study show that the ANFIS model shows higher accuracy than SVM model for the liquid limit (R2 = 0.987, plastic limit (R2 = 0.949 and plastic index (R2 = 0966. RMSE value that obtained for both methods have shown that the ANFIS model has represent the best performance than SVM model to predict the Atterberg Limits as a whole.

Longitudinal modeling to predict vital capacity in amyotrophic lateral sclerosis.

Science.gov (United States)

Jahandideh, Samad; Taylor, Albert A; Beaulieu, Danielle; Keymer, Mike; Meng, Lisa; Bian, Amy; Atassi, Nazem; Andrews, Jinsy; Ennist, David L

2018-05-01

Death in amyotrophic lateral sclerosis (ALS) patients is related to respiratory failure, which is assessed in clinical settings by measuring vital capacity. We developed ALS-VC, a modeling tool for longitudinal prediction of vital capacity in ALS patients. A gradient boosting machine (GBM) model was trained using the PRO-ACT (Pooled Resource Open-access ALS Clinical Trials) database of over 10,000 ALS patient records. We hypothesized that a reliable vital capacity predictive model could be developed using PRO-ACT. The model was used to compare FVC predictions with a 30-day run-in period to predictions made from just baseline. The internal root mean square deviations (RMSD) of the run-in and baseline models were 0.534 and 0.539, respectively, across the 7L FVC range captured in PRO-ACT. The RMSDs of the run-in and baseline models using an unrelated, contemporary external validation dataset (0.553 and 0.538, respectively) were comparable to the internal validation. The model was shown to have similar accuracy for predicting SVC (RMSD = 0.562). The most important features for both run-in and baseline models were "Baseline forced vital capacity" and "Days since baseline." We developed ALS-VC, a GBM model trained with the PRO-ACT ALS dataset that provides vital capacity predictions generalizable to external datasets. The ALS-VC model could be helpful in advising and counseling patients, and, in clinical trials, it could be used to generate virtual control arms against which observed outcomes could be compared, or used to stratify patients into slowly, average, and rapidly progressing subgroups.

External Validation and Recalibration of Risk Prediction Models for Acute Traumatic Brain Injury among Critically Ill Adult Patients in the United Kingdom.

Science.gov (United States)

Harrison, David A; Griggs, Kathryn A; Prabhu, Gita; Gomes, Manuel; Lecky, Fiona E; Hutchinson, Peter J A; Menon, David K; Rowan, Kathryn M

2015-10-01

This study validates risk prediction models for acute traumatic brain injury (TBI) in critical care units in the United Kingdom and recalibrates the models to this population. The Risk Adjustment In Neurocritical care (RAIN) Study was a prospective, observational cohort study in 67 adult critical care units. Adult patients admitted to critical care following acute TBI with a last pre-sedation Glasgow Coma Scale score of less than 15 were recruited. The primary outcomes were mortality and unfavorable outcome (death or severe disability, assessed using the Extended Glasgow Outcome Scale) at six months following TBI. Of 3626 critical care unit admissions, 2975 were analyzed. Following imputation of missing outcomes, mortality at six months was 25.7% and unfavorable outcome 57.4%. Ten risk prediction models were validated from Hukkelhoven and colleagues, the Medical Research Council (MRC) Corticosteroid Randomisation After Significant Head Injury (CRASH) Trial Collaborators, and the International Mission for Prognosis and Analysis of Clinical Trials in TBI (IMPACT) group. The model with the best discrimination was the IMPACT "Lab" model (C index, 0.779 for mortality and 0.713 for unfavorable outcome). This model was well calibrated for mortality at six months but substantially under-predicted the risk of unfavorable outcome. Recalibration of the models resulted in small improvements in discrimination and excellent calibration for all models. The risk prediction models demonstrated sufficient statistical performance to support their use in research and audit but fell below the level required to guide individual patient decision-making. The published models for unfavorable outcome at six months had poor calibration in the UK critical care setting and the models recalibrated to this setting should be used in future research.

Role of Subdural Electrocorticography in Prediction of Long-Term Seizure Outcome in Epilepsy Surgery

Science.gov (United States)

Asano, Eishi; Juhasz, Csaba; Shah, Aashit; Sood, Sandeep; Chugani, Harry T.

2009-01-01

Since prediction of long-term seizure outcome using preoperative diagnostic modalities remains suboptimal in epilepsy surgery, we evaluated whether interictal spike frequency measures obtained from extraoperative subdural electrocorticography (ECoG) recording could predict long-term seizure outcome. This study included 61 young patients (age…

Predicting Battle Outcomes with Classification Trees

National Research Council Canada - National Science Library

Coban, Muzaffer

2001-01-01

... from the actual battlefield, The models built by using classification trees reveal that the objective variables alone cannot explain the outcome of battles, Relative factors, such as leadership, have deep...

WE-E-17A-02: Predictive Modeling of Outcome Following SABR for NSCLC Based On Radiomics of FDG-PET Images

Energy Technology Data Exchange (ETDEWEB)

Li, R; Aguilera, T; Shultz, D; Rubin, D; Diehn, M; Loo, B [Stanford University, Stanford, CA (United States)

2014-06-15

Purpose: This study aims to develop predictive models of patient outcome by extracting advanced imaging features (i.e., Radiomics) from FDG-PET images. Methods: We acquired pre-treatment PET scans for 51 stage I NSCLC patients treated with SABR. We calculated 139 quantitative features from each patient PET image, including 5 morphological features, 8 statistical features, 27 texture features, and 100 features from the intensity-volume histogram. Based on the imaging features, we aim to distinguish between 2 risk groups of patients: those with regional failure or distant metastasis versus those without. We investigated 3 pattern classification algorithms: linear discriminant analysis (LDA), naive Bayes (NB), and logistic regression (LR). To avoid the curse of dimensionality, we performed feature selection by first removing redundant features and then applying sequential forward selection using the wrapper approach. To evaluate the predictive performance, we performed 10-fold cross validation with 1000 random splits of the data and calculated the area under the ROC curve (AUC). Results: Feature selection identified 2 texture features (homogeneity and/or wavelet decompositions) for NB and LR, while for LDA SUVmax and one texture feature (correlation) were identified. All 3 classifiers achieved statistically significant improvements over conventional PET imaging metrics such as tumor volume (AUC = 0.668) and SUVmax (AUC = 0.737). Overall, NB achieved the best predictive performance (AUC = 0.806). This also compares favorably with MTV using the best threshold at an SUV of 11.6 (AUC = 0.746). At a sensitivity of 80%, NB achieved 69% specificity, while SUVmax and tumor volume only had 36% and 47% specificity. Conclusion: Through a systematic analysis of advanced PET imaging features, we are able to build models with improved predictive value over conventional imaging metrics. If validated in a large independent cohort, the proposed techniques could potentially aid in

WE-E-17A-02: Predictive Modeling of Outcome Following SABR for NSCLC Based On Radiomics of FDG-PET Images

International Nuclear Information System (INIS)

Li, R; Aguilera, T; Shultz, D; Rubin, D; Diehn, M; Loo, B

2014-01-01

Purpose: This study aims to develop predictive models of patient outcome by extracting advanced imaging features (i.e., Radiomics) from FDG-PET images. Methods: We acquired pre-treatment PET scans for 51 stage I NSCLC patients treated with SABR. We calculated 139 quantitative features from each patient PET image, including 5 morphological features, 8 statistical features, 27 texture features, and 100 features from the intensity-volume histogram. Based on the imaging features, we aim to distinguish between 2 risk groups of patients: those with regional failure or distant metastasis versus those without. We investigated 3 pattern classification algorithms: linear discriminant analysis (LDA), naive Bayes (NB), and logistic regression (LR). To avoid the curse of dimensionality, we performed feature selection by first removing redundant features and then applying sequential forward selection using the wrapper approach. To evaluate the predictive performance, we performed 10-fold cross validation with 1000 random splits of the data and calculated the area under the ROC curve (AUC). Results: Feature selection identified 2 texture features (homogeneity and/or wavelet decompositions) for NB and LR, while for LDA SUVmax and one texture feature (correlation) were identified. All 3 classifiers achieved statistically significant improvements over conventional PET imaging metrics such as tumor volume (AUC = 0.668) and SUVmax (AUC = 0.737). Overall, NB achieved the best predictive performance (AUC = 0.806). This also compares favorably with MTV using the best threshold at an SUV of 11.6 (AUC = 0.746). At a sensitivity of 80%, NB achieved 69% specificity, while SUVmax and tumor volume only had 36% and 47% specificity. Conclusion: Through a systematic analysis of advanced PET imaging features, we are able to build models with improved predictive value over conventional imaging metrics. If validated in a large independent cohort, the proposed techniques could potentially aid in

Validation of the DRAGON Score in a Chinese Population to Predict Functional Outcome of Intravenous Thrombolysis-Treated Stroke Patients.

Science.gov (United States)

Zhang, Xinmiao; Liao, Xiaoling; Wang, Chunjuan; Liu, Liping; Wang, Chunxue; Zhao, Xingquan; Pan, Yuesong; Wang, Yilong; Wang, Yongjun

2015-08-01

The DRAGON score predicts functional outcome of ischemic stroke patients treated with intravenous thrombolysis. Our aim was to evaluate its utility in a Chinese stroke population. Patients with acute ischemic stroke treated with intravenous thrombolysis were prospectively registered in the Thrombolysis Implementation and Monitor of acute ischemic Stroke in China. We excluded patients with basilar artery occlusion and missing data, leaving 970 eligible patients. We calculated the DRAGON score, and the clinical outcome was measured by the modified Rankin Scale at 3 months. Model discrimination was quantified by calculating the C statistic. Calibration was assessed using Pearson correlation coefficient. The C statistic was .73 (.70-.76) for good outcome and .75 (.70-.79) for miserable outcome. Proportions of patients with good outcome were 94%, 83%, 70%, and 0% for 0 to 1, 2, 3, and 8 to 10 score points, respectively. Proportions of patients with miserable outcome were 0%, 3%, 9%, and 50% for 0 to 1, 2, 3, and 8 to 10 points, respectively. There was high correlation between predicted and observed probability of 3-month favorable and miserable outcome in the external validation cohort (Pearson correlation coefficient, .98 and .98, respectively, both P DRAGON score showed good performance to predict functional outcome after tissue-type plasminogen activator treatment in the Chinese population. This study demonstrated the accuracy and usability of the DRAGON score in the Chinese population in daily practice. Copyright © 2015 National Stroke Association. Published by Elsevier Inc. All rights reserved.

Developing and validating a model to predict the success of an IHCS implementation: the Readiness for Implementation Model

Science.gov (United States)

Gustafson, David H; Hawkins, Robert P; Brennan, Patricia F; Dinauer, Susan; Johnson, Pauley R; Siegler, Tracy

2010-01-01

Objective To develop and validate the Readiness for Implementation Model (RIM). This model predicts a healthcare organization's potential for success in implementing an interactive health communication system (IHCS). The model consists of seven weighted factors, with each factor containing five to seven elements. Design Two decision-analytic approaches, self-explicated and conjoint analysis, were used to measure the weights of the RIM with a sample of 410 experts. The RIM model with weights was then validated in a prospective study of 25 IHCS implementation cases. Measurements Orthogonal main effects design was used to develop 700 conjoint-analysis profiles, which varied on seven factors. Each of the 410 experts rated the importance and desirability of the factors and their levels, as well as a set of 10 different profiles. For the prospective 25-case validation, three time-repeated measures of the RIM scores were collected for comparison with the implementation outcomes. Results Two of the seven factors, ‘organizational motivation’ and ‘meeting user needs,’ were found to be most important in predicting implementation readiness. No statistically significant difference was found in the predictive validity of the two approaches (self-explicated and conjoint analysis). The RIM was a better predictor for the 1-year implementation outcome than the half-year outcome. Limitations The expert sample, the order of the survey tasks, the additive model, and basing the RIM cut-off score on experience are possible limitations of the study. Conclusion The RIM needs to be empirically evaluated in institutions adopting IHCS and sustaining the system in the long term. PMID:20962135

Do symptom-specific stages of change predict eating disorder treatment outcome?

Science.gov (United States)

Ackard, Diann M; Cronemeyer, Catherine L; Richter, Sara; Egan, Amber

2015-03-01

Interview methods to assess stages of change (SOC) in eating disorders (ED) indicate that SOC are positively correlated with symptom improvement over time. However, interviews require significant time and staff training and global measures of SOC do not capture varying levels of motivation across ED symptoms. This study used a self-report, ED symptom-specific SOC measure to determine prevalence of stages across symptoms and identify if SOC predict treatment outcome. Participants [N = 182; age 13-58 years; 92% Caucasian; 96% female; average BMI 21.7 (SD = 5.9); 50% ED not otherwise specified (EDNOS), 30.8% bulimia nervosa (BN), 19.2% anorexia nervosa (AN)] seeking ED treatment at a diverse-milieu multi-disciplinary facility in the United States completed stages of change, behavioral (ED symptom use and frequency) and psychological (ED concerns, anxiety, depression) measures at intake assessment and at 3, 6 and 12 months thereafter. Descriptive summaries were generated using ANOVA or Kruskal-Wallis (continuous) and χ (2) (categorical) tests. Repeated measures linear regression models with autoregressive correlation structure predicted treatment outcome. At intake assessment, 53.3% of AN, 34.0% of BN and 18.1% of EDNOS patients were in Preparation/Action. Readiness to change specific symptoms was highest for binge-eating (57.8%) and vomiting (56.5%). Frequency of fasting and restricting behaviors, and scores on all eating disorder and psychological measures improved over time regardless of SOC at intake assessment. Symptom-specific SOC did not predict reductions in ED symptom frequency. Overall SOC predicted neither improvement in Eating Disorder Examination Questionnaire (EDE-Q) scores nor reduction in depression or trait anxiety; however, higher overall SOC predicted lower state anxiety across follow-up. Readiness to change ED behaviors varies considerably. Most patients reduced eating disorder behaviors and increased psychological functioning regardless of stages

Predicting 30-Day Readmissions in an Asian Population: Building a Predictive Model by Incorporating Markers of Hospitalization Severity.

Directory of Open Access Journals (Sweden)

Lian Leng Low

Full Text Available To reduce readmissions, it may be cost-effective to consider risk stratification, with targeting intervention programs to patients at high risk of readmissions. In this study, we aimed to derive and validate a prediction model including several novel markers of hospitalization severity, and compare the model with the LACE index (Length of stay, Acuity of admission, Charlson comorbidity index, Emergency department visits in past 6 months, an established risk stratification tool.This was a retrospective cohort study of all patients ≥ 21 years of age, who were admitted to a tertiary hospital in Singapore from January 1, 2013 through May 31, 2015. Data were extracted from the hospital's electronic health records. The outcome was defined as unplanned readmissions within 30 days of discharge from the index hospitalization. Candidate predictive variables were broadly grouped into five categories: Patient demographics, social determinants of health, past healthcare utilization, medical comorbidities, and markers of hospitalization severity. Multivariable logistic regression was used to predict the outcome, and receiver operating characteristic analysis was performed to compare our model with the LACE index.74,102 cases were enrolled for analysis. Of these, 11,492 patient cases (15.5% were readmitted within 30 days of discharge. A total of fifteen predictive variables were strongly associated with the risk of 30-day readmissions, including number of emergency department visits in the past 6 months, Charlson Comorbidity Index, markers of hospitalization severity such as 'requiring inpatient dialysis during index admission, and 'treatment with intravenous furosemide 40 milligrams or more' during index admission. Our predictive model outperformed the LACE index by achieving larger area under the curve values: 0.78 (95% confidence interval [CI]: 0.77-0.79 versus 0.70 (95% CI: 0.69-0.71.Several factors are important for the risk of 30-day readmissions

Prediction of cognitive outcome based on the progression of auditory discrimination during coma.

Science.gov (United States)

Juan, Elsa; De Lucia, Marzia; Tzovara, Athina; Beaud, Valérie; Oddo, Mauro; Clarke, Stephanie; Rossetti, Andrea O

2016-09-01

To date, no clinical test is able to predict cognitive and functional outcome of cardiac arrest survivors. Improvement of auditory discrimination in acute coma indicates survival with high specificity. Whether the degree of this improvement is indicative of recovery remains unknown. Here we investigated if progression of auditory discrimination can predict cognitive and functional outcome. We prospectively recorded electroencephalography responses to auditory stimuli of post-anoxic comatose patients on the first and second day after admission. For each recording, auditory discrimination was quantified and its evolution over the two recordings was used to classify survivors as "predicted" when it increased vs. "other" if not. Cognitive functions were tested on awakening and functional outcome was assessed at 3 months using the Cerebral Performance Categories (CPC) scale. Thirty-two patients were included, 14 "predicted survivors" and 18 "other survivors". "Predicted survivors" were more likely to recover basic cognitive functions shortly after awakening (ability to follow a standardized neuropsychological battery: 86% vs. 44%; p=0.03 (Fisher)) and to show a very good functional outcome at 3 months (CPC 1: 86% vs. 33%; p=0.004 (Fisher)). Moreover, progression of auditory discrimination during coma was strongly correlated with cognitive performance on awakening (phonemic verbal fluency: rs=0.48; p=0.009 (Spearman)). Progression of auditory discrimination during coma provides early indication of future recovery of cognitive functions. The degree of improvement is informative of the degree of functional impairment. If confirmed in a larger cohort, this test would be the first to predict detailed outcome at the single-patient level. Copyright © 2016 Elsevier Ireland Ltd. All rights reserved.

Do infant vocabulary skills predict school-age language and literacy outcomes?

Science.gov (United States)

Duff, Fiona J; Reen, Gurpreet; Plunkett, Kim; Nation, Kate

2015-08-01

Strong associations between infant vocabulary and school-age language and literacy skills would have important practical and theoretical implications: Preschool assessment of vocabulary skills could be used to identify children at risk of reading and language difficulties, and vocabulary could be viewed as a cognitive foundation for reading. However, evidence to date suggests predictive ability from infant vocabulary to later language and literacy is low. This study provides an investigation into, and interpretation of, the magnitude of such infant to school-age relationships. Three hundred British infants whose vocabularies were assessed by parent report in the 2nd year of life (between 16 and 24 months) were followed up on average 5 years later (ages ranged from 4 to 9 years), when their vocabulary, phonological and reading skills were measured. Structural equation modelling of age-regressed scores was used to assess the strength of longitudinal relationships. Infant vocabulary (a latent factor of receptive and expressive vocabulary) was a statistically significant predictor of later vocabulary, phonological awareness, reading accuracy and reading comprehension (accounting for between 4% and 18% of variance). Family risk for language or literacy difficulties explained additional variance in reading (approximately 10%) but not language outcomes. Significant longitudinal relationships between preliteracy vocabulary knowledge and subsequent reading support the theory that vocabulary is a cognitive foundation of both reading accuracy and reading comprehension. Importantly however, the stability of vocabulary skills from infancy to later childhood is too low to be sufficiently predictive of language outcomes at an individual level - a finding that fits well with the observation that the majority of 'late talkers' resolve their early language difficulties. For reading outcomes, prediction of future difficulties is likely to be improved when considering family

Pre-delivery fibrinogen predicts adverse maternal or neonatal outcomes in patients with placental abruption.

Science.gov (United States)

Wang, Liangcheng; Matsunaga, Shigetaka; Mikami, Yukiko; Takai, Yasushi; Terui, Katsuo; Seki, Hiroyuki

2016-07-01

Placental abruption is a severe obstetric complication of pregnancy that can cause disseminated intravascular coagulation and progress to massive post-partum hemorrhage. Coagulation disorder due to extreme consumption of fibrinogen is considered the main pathogenesis of disseminated intravascular coagulation in patients with placental abruption. The present study sought to determine if the pre-delivery fibrinogen level could predict adverse maternal or neonatal outcomes in patients with placental abruption. This retrospective medical chart review was conducted in a center for maternal, fetal, and neonatal medicine in Japan with 61 patients with placental abruption. Fibrinogen levels prior to delivery were collected and evaluated for the prediction of maternal and neonatal outcomes. The main outcome measures for maternal outcomes were disseminated intravascular coagulation and hemorrhage, and the main outcome measures for neonatal outcomes were Apgar score at 5 min, umbilical artery pH, and stillbirth. The receiver-operator curve and multivariate logistic regression analyses indicated that fibrinogen significantly predicted overt disseminated intravascular coagulation and the requirement of ≥6 red blood cell units, ≥10 fresh frozen plasma units, and ≥20 fresh frozen plasma units for transfusion. Moderate hemorrhage occurred in 71.5% of patients with a decrease in fibrinogen levels to 155 mg/dL. Fibrinogen could also predict neonatal outcomes. Umbilical artery pH neonatal outcomes with placental abruption. © 2016 Japan Society of Obstetrics and Gynecology. © 2016 Japan Society of Obstetrics and Gynecology.

Modeling the economic outcomes of immuno-oncology drugs: alternative model frameworks to capture clinical outcomes.

Science.gov (United States)

Gibson, E J; Begum, N; Koblbauer, I; Dranitsaris, G; Liew, D; McEwan, P; Tahami Monfared, A A; Yuan, Y; Juarez-Garcia, A; Tyas, D; Lees, M

2018-01-01

Economic models in oncology are commonly based on the three-state partitioned survival model (PSM) distinguishing between progression-free and progressive states. However, the heterogeneity of responses observed in immuno-oncology (I-O) suggests that new approaches may be appropriate to reflect disease dynamics meaningfully. This study explored the impact of incorporating immune-specific health states into economic models of I-O therapy. Two variants of the PSM and a Markov model were populated with data from one clinical trial in metastatic melanoma patients. Short-term modeled outcomes were benchmarked to the clinical trial data and a lifetime model horizon provided estimates of life years and quality adjusted life years (QALYs). The PSM-based models produced short-term outcomes closely matching the trial outcomes. Adding health states generated increased QALYs while providing a more granular representation of outcomes for decision making. The Markov model gave the greatest level of detail on outcomes but gave short-term results which diverged from those of the trial (overstating year 1 progression-free survival by around 60%). Increased sophistication in the representation of disease dynamics in economic models is desirable when attempting to model treatment response in I-O. However, the assumptions underlying different model structures and the availability of data for health state mapping may be important limiting factors.

Predicting unfavourable outcome in herpetic meningoencephalitis

DEFF Research Database (Denmark)

Erdem, Hakan; Cag, Yasemin; Karaahmetoglu, Gokhan

BACKGROUND: Herpetic meningoencephalitis is the most frequent form of sporadic fatal encephalitis in the world and accounts for 10- 20% of all viral encephalitides. There were studies assessing the outcomes particularly by comparing the efficacies of antiviral drugs in the past. To the best of our...... knowledge, no datum exists in the literature on the mortality indicators of HME patients with definite microbiological diagnosis. Thus, our study makes use of the largest case series ever reported in the literature to provide data for the predictors of unfavorable outcome in HME cases. METHODS...... outcome in HME. Thus, it appears that both host and therapeutic parameters contribute to success in these cases. Table. Final model including independent predictors of unfavorable outcome 95% CIs OR [1] Low High p Age (years) 1.04 1.02 1.05 0.000 Glasgow coma scale 0.84 0.77 0.93 0.000 Elapsed time [2] >2...

Predicting IVF Outcome: A Proposed Web-based System Using Artificial Intelligence.

Science.gov (United States)

Siristatidis, Charalampos; Vogiatzi, Paraskevi; Pouliakis, Abraham; Trivella, Marialenna; Papantoniou, Nikolaos; Bettocchi, Stefano

2016-01-01

To propose a functional in vitro fertilization (IVF) prediction model to assist clinicians in tailoring personalized treatment of subfertile couples and improve assisted reproduction outcome. Construction and evaluation of an enhanced web-based system with a novel Artificial Neural Network (ANN) architecture and conformed input and output parameters according to the clinical and bibliographical standards, driven by a complete data set and "trained" by a network expert in an IVF setting. The system is capable to act as a routine information technology platform for the IVF unit and is capable of recalling and evaluating a vast amount of information in a rapid and automated manner to provide an objective indication on the outcome of an artificial reproductive cycle. ANNs are an exceptional candidate in providing the fertility specialist with numerical estimates to promote personalization of healthcare and adaptation of the course of treatment according to the indications. Copyright © 2016 International Institute of Anticancer Research (Dr. John G. Delinassios), All rights reserved.

A Comparative Study of Glasgow Coma Scale and Full Outline of Unresponsiveness Scores for Predicting Long-Term Outcome After Brain Injury.

Science.gov (United States)

McNett, Molly M; Amato, Shelly; Philippbar, Sue Ann

2016-01-01

The aim of this study was to compare predictive ability of hospital Glasgow Coma Scale (GCS) scores and scores obtained using a novel coma scoring tool (the Full Outline of Unresponsiveness [FOUR] scale) on long-term outcomes among patients with traumatic brain injury. Preliminary research of the FOUR scale suggests that it is comparable with GCS for predicting mortality and functional outcome at hospital discharge. No research has investigated relationships between coma scores and outcome 12 months postinjury. This is a prospective cohort study. Data were gathered on adult patients with traumatic brain injury admitted to urban level I trauma center. GCS and FOUR scores were assigned at 24 and 72 hours and at hospital discharge. Glasgow Outcome Scale scores were assigned at 6 and 12 months. The sample size was n = 107. Mean age was 53.5 (SD = ±21, range = 18-91) years. Spearman correlations were comparable and strongest among discharge GCS and FOUR scores and 12-month outcome (r = .73, p coma scores performed best for both tools, with GCS discharge scores predictive in multivariate models.

Adolescent Eating Disorders Predict Psychiatric, High-Risk Behaviors and Weight Outcomes in Young Adulthood.

Science.gov (United States)

Micali, Nadia; Solmi, Francesca; Horton, Nicholas J; Crosby, Ross D; Eddy, Kamryn T; Calzo, Jerel P; Sonneville, Kendrin R; Swanson, Sonja A; Field, Alison E

2015-08-01

To investigate whether anorexia nervosa (AN), bulimia nervosa (BN), binge eating disorder (BED), and other specified feeding and eating disorders (OSFED), including purging disorder (PD), subthreshold BN, and BED at ages 14 and 16 years, are prospectively associated with later depression, anxiety disorders, alcohol and substance use, and self-harm. Eating disorders were ascertained at ages 14 and 16 years in 6,140 youth at age 14 (58% of those eligible) and 5,069 at age 16 (52% of those eligible) as part of the prospective Avon Longitudinal Study of Parents and Children (ALSPAC). Outcomes (depression, anxiety disorders, binge drinking, drug use, deliberate self-harm, weight status) were measured using interviews and questionnaires about 2 years after predictors. Generalized estimating equation models adjusting for gender, socio-demographic variables, and prior outcome were used to examine prospective associations between eating disorders and each outcome. All eating disorders were predictive of later anxiety disorders. AN, BN, BED, PD, and OSFED were prospectively associated with depression (respectively AN: odds ratio [OR] = 1.39, 95% CI = 1.00-1.94; BN: OR = 3.39, 95% CI = 1.25-9.20; BED: OR = 2.00, 95% CI = 1.06-3.75; and PD: OR = 2.56, 95% CI = 1.38-4.74). All eating disorders but AN predicted drug use and deliberate self-harm (BN: OR = 5.72, 95% CI = 2.22-14.72; PD: OR = 4.88, 95% CI = 2.78-8.57; subthreshold BN: OR = 3.97, 95% CI = 1.44-10.98; and subthreshold BED: OR = 2.32, 95% CI = 1.43-3.75). Although BED and BN predicted obesity (respectively OR = 3.58, 95% CI = 1.06-12.14 and OR = 6.42, 95% CI = 1.69-24.30), AN was prospectively associated with underweight. Adolescent eating disorders, including subthreshold presentations, predict negative outcomes, including mental health disorders, substance use, deliberate self-harm, and weight outcomes. This study highlights the high public health and clinical burden of eating disorders

Assessing the performance of prediction models: a framework for traditional and novel measures

DEFF Research Database (Denmark)

Steyerberg, Ewout W; Vickers, Andrew J; Cook, Nancy R

2010-01-01

The performance of prediction models can be assessed using a variety of methods and metrics. Traditional measures for binary and survival outcomes include the Brier score to indicate overall model performance, the concordance (or c) statistic for discriminative ability (or area under the receiver...

Assessing the performance of prediction models: A framework for traditional and novel measures

NARCIS (Netherlands)

E.W. Steyerberg (Ewout); A.J. Vickers (Andrew); N.R. Cook (Nancy); T.A. Gerds (Thomas); M. Gonen (Mithat); N. Obuchowski (Nancy); M. Pencina (Michael); M.W. Kattan (Michael)

2010-01-01

textabstractThe performance of prediction models can be assessed using a variety of methods and metrics. Traditional measures for binary and survival outcomes include the Brier score to indicate overall model performance, the concordance (or c) statistic for discriminative ability (or area under the

Comparison of logistic regression and neural models in predicting the outcome of biopsy in breast cancer from MRI findings

International Nuclear Information System (INIS)

Abdolmaleki, P.; Yarmohammadi, M.; Gity, M.

2004-01-01

Background: We designed an algorithmic model based on regression analysis and a non-algorithmic model based on the Artificial Neural Network. Materials and methods: The ability of these models was compared together in clinical application to differentiate malignant from benign breast tumors in a study group of 161 patient's records. Each patient's record consisted of 6 subjective features extracted from MRI appearance. These findings were enclosed as features extracted for an Artificial Neural Network as well as a logistic regression model to predict biopsy outcome. After both models had been trained perfectly on samples (n=100), the validation samples (n=61) were presented to the trained network as well as the established logistic regression models. Finally, the diagnostic performance of models were compared to the that of the radiologist in terms of sensitivity, specificity and accuracy, using receiver operating characteristic curve analysis. Results: The average out put of the Artificial Neural Network yielded a perfect sensitivity (98%) and high accuracy (90%) similar to that one of an expert radiologist (96% and 92%) while specificity was smaller than that (67%) verses 80%). The output of the logistic regression model using significant features showed improvement in specificity from 60% for the logistic regression model using all features to 93% for the reduced logistic regression model, keeping the accuracy around 90%. Conclusion: Results show that Artificial Neural Network and logistic regression model prove the relationship between extracted morphological features and biopsy results. Using statistically significant variables reduced logistic regression model outperformed of Artificial Neural Network with remarkable specificity while keeping high sensitivity is achieved

Characterizing Tumor Heterogeneity With Functional Imaging and Quantifying High-Risk Tumor Volume for Early Prediction of Treatment Outcome: Cervical Cancer as a Model

Energy Technology Data Exchange (ETDEWEB)

Mayr, Nina A., E-mail: Nina.Mayr@osumc.edu [Department of Radiation Oncology, Ohio State University, Columbus, OH (United States); Huang Zhibin [Department of Radiation Oncology and Department of Physics, East Carolina University, Greenville, NC (United States); Wang, Jian Z. [Department of Radiation Oncology, Ohio State University, Columbus, OH (United States); Lo, Simon S. [Department of Radiation Oncology, Case Western Reserve University, Cleveland, OH (United States); Fan, Joline M. [Department of Molecular Biology, Stanford University, Stanford, CA (United States); Grecula, John C. [Department of Radiation Oncology, Ohio State University, Columbus, OH (United States); Sammet, Steffen [Department of Radiology, University of Chicago, Chicago, IL (United States); Department of Radiology, Ohio State University, Columbus, OH (United States); Sammet, Christina L. [Department of Radiology, University of Chicago, Chicago, IL (United States); Jia Guang; Zhang Jun; Knopp, Michael V.; Yuh, William T.C. [Department of Radiology, Ohio State University, Columbus, OH (United States)

2012-07-01

Purpose: Treatment response in cancer has been monitored by measuring anatomic tumor volume (ATV) at various times without considering the inherent functional tumor heterogeneity known to critically influence ultimate treatment outcome: primary tumor control and survival. This study applied dynamic contrast-enhanced (DCE) functional MRI to characterize tumors' heterogeneous subregions with low DCE values, at risk for treatment failure, and to quantify the functional risk volume (FRV) for personalized early prediction of treatment outcome. Methods and Materials: DCE-MRI was performed in 102 stage IB{sub 2}-IVA cervical cancer patients to assess tumor perfusion heterogeneity before and during radiation/chemotherapy. FRV represents the total volume of tumor voxels with critically low DCE signal intensity (<2.1 compared with precontrast image, determined by previous receiver operator characteristic analysis). FRVs were correlated with treatment outcome (follow-up: 0.2-9.4, mean 6.8 years) and compared with ATVs (Mann-Whitney, Kaplan-Meier, and multivariate analyses). Results: Before and during therapy at 2-2.5 and 4-5 weeks of RT, FRVs >20, >13, and >5 cm{sup 3}, respectively, significantly predicted unfavorable 6-year primary tumor control (p = 0.003, 7.3 Multiplication-Sign 10{sup -8}, 2.0 Multiplication-Sign 10{sup -8}) and disease-specific survival (p = 1.9 Multiplication-Sign 10{sup -4}, 2.1 Multiplication-Sign 10{sup -6}, 2.5 Multiplication-Sign 10{sup -7}, respectively). The FRVs were superior to the ATVs as early predictors of outcome, and the differentiating power of FRVs increased during treatment. Discussion: Our preliminary results suggest that functional tumor heterogeneity can be characterized by DCE-MRI to quantify FRV for predicting ultimate long-term treatment outcome. FRV is a novel functional imaging heterogeneity parameter, superior to ATV, and can be clinically translated for personalized early outcome prediction before or as early as 2

A balance of activity in brain control and reward systems predicts self-regulatory outcomes

OpenAIRE

Lopez, Richard B.; Chen, Pin-Hao A.; Huckins, Jeremy F.; Hofmann, Wilhelm; Kelley, William M.; Heatherton, Todd F.

2017-01-01

Abstract Previous neuroimaging work has shown that increased reward-related activity following exposure to food cues is predictive of self-control failure. The balance model suggests that self-regulation failures result from an imbalance in reward and executive control mechanisms. However, an open question is whether the relative balance of activity in brain systems associated with executive control (vs reward) supports self-regulatory outcomes when people encounter tempting cues in daily lif...

Preoperative MRI findings predict two-year postoperative clinical outcome in lumbar spinal stenosis.

Directory of Open Access Journals (Sweden)

Pekka Kuittinen

Full Text Available To study the predictive value of preoperative magnetic resonance imaging (MRI findings for the two-year postoperative clinical outcome in lumbar spinal stenosis (LSS.84 patients (mean age 63±11 years, male 43% with symptoms severe enough to indicate LSS surgery were included in this prospective observational single-center study. Preoperative MRI of the lumbar spine was performed with a 1.5-T unit. The imaging protocol conformed to the requirements of the American College of Radiology for the performance of MRI of the adult spine. Visual and quantitative assessment of MRI was performed by one experienced neuroradiologist. At the two-year postoperative follow-up, functional ability was assessed with the Oswestry Disability Index (ODI 0-100% and treadmill test (0-1000 m, pain symptoms with the overall Visual Analogue Scale (VAS 0-100 mm, and specific low back pain (LBP and specific leg pain (LP separately with a numeric rating scale from 0-10 (NRS-11. Satisfaction with the surgical outcome was also assessed.Preoperative severe central stenosis predicted postoperatively lower LP, LBP, and VAS when compared in patients with moderate central stenosis (p<0.05. Moreover, severe stenosis predicted higher postoperative satisfaction (p = 0.029. Preoperative scoliosis predicted an impaired outcome in the ODI (p = 0.031 and lowered the walking distance in the treadmill test (p = 0.001. The preoperative finding of only one stenotic level in visual assessment predicted less postoperative LBP when compared with patients having 2 or more stenotic levels (p = 0.026. No significant differences were detected between quantitative measurements and the patient outcome.Routine preoperative lumbar spine MRI can predict the patient outcome in a two-year follow up in patients with LSS surgery. Severe central stenosis and one-level central stenosis are predictors of good outcome. Preoperative finding of scoliosis may indicate worse functional ability.

Clinical Prediction Models for Cardiovascular Disease: The Tufts PACE CPM Database

Science.gov (United States)

Wessler, Benjamin S.; Lana Lai, YH; Kramer, Whitney; Cangelosi, Michael; Raman, Gowri; Lutz, Jennifer S.; Kent, David M.

2015-01-01

Background Clinical prediction models (CPMs) estimate the probability of clinical outcomes and hold the potential to improve decision making and individualize care. For patients with cardiovascular disease (CVD) there are numerous CPMs available though the extent of this literature is not well described. Methods and Results We conducted a systematic review for articles containing CPMs for CVD published between January 1990 through May 2012. CVD includes coronary heart disease (CHD), heart failure (HF), arrhythmias, stroke, venous thromboembolism (VTE) and peripheral vascular disease (PVD). We created a novel database and characterized CPMs based on the stage of development, population under study, performance, covariates, and predicted outcomes. There are 796 models included in this database. The number of CPMs published each year is increasing steadily over time. 717 (90%) are de novo CPMs, 21 (3%) are CPM recalibrations, and 58 (7%) are CPM adaptations. This database contains CPMs for 31 index conditions including 215 CPMs for patients with CAD, 168 CPMs for population samples, and 79 models for patients with HF. There are 77 distinct index/ outcome (I/O) pairings. Of the de novo models in this database 450 (63%) report a c-statistic and 259 (36%) report some information on calibration. Conclusions There is an abundance of CPMs available for a wide assortment of CVD conditions, with substantial redundancy in the literature. The comparative performance of these models, the consistency of effects and risk estimates across models and the actual and potential clinical impact of this body of literature is poorly understood. PMID:26152680

Early prediction of outcome of activities of daily living after stroke: a systematic review

OpenAIRE

Veerbeek, J.M.; Kwakkel, G.; Wegen, van, E.E.H.; Ket, J.C.F.; Heijmans, M.W.

2011-01-01

BACKGROUND AND PURPOSE-Knowledge about robust and unbiased factors that predict outcome of activities of daily living (ADL) is paramount in stroke management. This review investigates the methodological quality of prognostic studies in the early poststroke phase for final ADL to identify variables that are predictive or not predictive for outcome of ADL after stroke. METHODS-PubMed, Ebsco/Cinahl and Embase were systematically searched for prognostic studies in which stroke patients were inclu...

Available clinical markers of treatment outcome integrated in mathematical models to guide therapy in HIV infection.

Science.gov (United States)

Vergu, Elisabeta; Mallet, Alain; Golmard, Jean-Louis

2004-02-01

Because treatment failure in many HIV-infected persons may be due to multiple causes, including resistance to antiretroviral agents, it is important to better tailor drug therapy to individual patients. This improvement requires the prediction of treatment outcome from baseline immunological or virological factors, and from results of resistance tests. Here, we review briefly the available clinical factors that have an impact on therapy outcome, and discuss the role of a predictive modelling approach integrating these factors proposed in a previous work. Mathematical and statistical models could become essential tools to address questions that are difficult to study clinically and experimentally, thereby guiding decisions in the choice of individualized drug regimens.

Applying a computer-aided scheme to detect a new radiographic image marker for prediction of chemotherapy outcome

International Nuclear Information System (INIS)

Wang, Yunzhi; Qiu, Yuchen; Thai, Theresa; Moore, Kathleen; Liu, Hong; Zheng, Bin

2016-01-01

To investigate the feasibility of automated segmentation of visceral and subcutaneous fat areas from computed tomography (CT) images of ovarian cancer patients and applying the computed adiposity-related image features to predict chemotherapy outcome. A computerized image processing scheme was developed to segment visceral and subcutaneous fat areas, and compute adiposity-related image features. Then, logistic regression models were applied to analyze association between the scheme-generated assessment scores and progression-free survival (PFS) of patients using a leave-one-case-out cross-validation method and a dataset involving 32 patients. The correlation coefficients between automated and radiologist’s manual segmentation of visceral and subcutaneous fat areas were 0.76 and 0.89, respectively. The scheme-generated prediction scores using adiposity-related radiographic image features significantly associated with patients’ PFS (p < 0.01). Using a computerized scheme enables to more efficiently and robustly segment visceral and subcutaneous fat areas. The computed adiposity-related image features also have potential to improve accuracy in predicting chemotherapy outcome

Noninvasive work of breathing improves prediction of post-extubation outcome.

Science.gov (United States)

Banner, Michael J; Euliano, Neil R; Martin, A Daniel; Al-Rawas, Nawar; Layon, A Joseph; Gabrielli, Andrea

2012-02-01

We hypothesized that non-invasively determined work of breathing per minute (WOB(N)/min) (esophageal balloon not required) may be useful for predicting extubation outcome, i.e., appropriate work of breathing values may be associated with extubation success, while inappropriately increased values may be associated with failure. Adult candidates for extubation were divided into a training set (n = 38) to determine threshold values of indices for assessing extubation and a prospective validation set (n = 59) to determine the predictive power of the threshold values for patients successfully extubated and those who failed extubation. All were evaluated for extubation during a spontaneous breathing trial (5 cmH(2)O pressure support ventilation, 5 cmH(2)O positive end expiratory pressure) using routine clinical practice standards. WOB(N)/min data were blinded to attending physicians. Area under the receiver operating characteristic curves (AUC), sensitivity, specificity, and positive and negative predictive values of all extubation indices were determined. AUC for WOB(N)/min was 0.96 and significantly greater (p indices. WOB(N)/min had a specificity of 0.83, the highest sensitivity at 0.96, positive predictive value at 0.84, and negative predictive value at 0.96 compared to all indices. For 95% of those successfully extubated, WOB(N)/min was ≤10 J/min. WOB(N)/min had the greatest overall predictive accuracy for extubation compared to traditional indices. WOB(N)/min warrants consideration for use in a complementary manner with spontaneous breathing pattern data for predicting extubation outcome.

Combining Spot Sign and Intracerebral Hemorrhage Score to Estimate Functional Outcome: Analysis From the PREDICT Cohort.

Science.gov (United States)

Schneider, Hauke; Huynh, Thien J; Demchuk, Andrew M; Dowlatshahi, Dar; Rodriguez-Luna, David; Silva, Yolanda; Aviv, Richard; Dzialowski, Imanuel

2018-06-01

The intracerebral hemorrhage (ICH) score is the most commonly used grading scale for stratifying functional outcome in patients with acute ICH. We sought to determine whether a combination of the ICH score and the computed tomographic angiography spot sign may improve outcome prediction in the cohort of a prospective multicenter hemorrhage trial. Prospectively collected data from 241 patients from the observational PREDICT study (Prediction of Hematoma Growth and Outcome in Patients With Intracerebral Hemorrhage Using the CT-Angiography Spot Sign) were analyzed. Functional outcome at 3 months was dichotomized using the modified Rankin Scale (0-3 versus 4-6). Performance of (1) the ICH score and (2) the spot sign ICH score-a scoring scale combining ICH score and spot sign number-was tested. Multivariable analysis demonstrated that ICH score (odds ratio, 3.2; 95% confidence interval, 2.2-4.8) and spot sign number (n=1: odds ratio, 2.7; 95% confidence interval, 1.1-7.4; n>1: odds ratio, 3.8; 95% confidence interval, 1.2-17.1) were independently predictive of functional outcome at 3 months with similar odds ratios. Prediction of functional outcome was not significantly different using the spot sign ICH score compared with the ICH score alone (spot sign ICH score area under curve versus ICH score area under curve: P =0.14). In the PREDICT cohort, a prognostic score adding the computed tomographic angiography-based spot sign to the established ICH score did not improve functional outcome prediction compared with the ICH score. © 2018 American Heart Association, Inc.

Development of a prognostic model for predicting spontaneous singleton preterm birth.

Science.gov (United States)

Schaaf, Jelle M; Ravelli, Anita C J; Mol, Ben Willem J; Abu-Hanna, Ameen

2012-10-01

To develop and validate a prognostic model for prediction of spontaneous preterm birth. Prospective cohort study using data of the nationwide perinatal registry in The Netherlands. We studied 1,524,058 singleton pregnancies between 1999 and 2007. We developed a multiple logistic regression model to estimate the risk of spontaneous preterm birth based on maternal and pregnancy characteristics. We used bootstrapping techniques to internally validate our model. Discrimination (AUC), accuracy (Brier score) and calibration (calibration graphs and Hosmer-Lemeshow C-statistic) were used to assess the model's predictive performance. Our primary outcome measure was spontaneous preterm birth at model included 13 variables for predicting preterm birth. The predicted probabilities ranged from 0.01 to 0.71 (IQR 0.02-0.04). The model had an area under the receiver operator characteristic curve (AUC) of 0.63 (95% CI 0.63-0.63), the Brier score was 0.04 (95% CI 0.04-0.04) and the Hosmer Lemeshow C-statistic was significant (pvalues of predicted probability. The positive predictive value was 26% (95% CI 20-33%) for the 0.4 probability cut-off point. The model's discrimination was fair and it had modest calibration. Previous preterm birth, drug abuse and vaginal bleeding in the first half of pregnancy were the most important predictors for spontaneous preterm birth. Although not applicable in clinical practice yet, this model is a next step towards early prediction of spontaneous preterm birth that enables caregivers to start preventive therapy in women at higher risk. Copyright © 2012 Elsevier Ireland Ltd. All rights reserved.

Multivariate Models for Prediction of Human Skin Sensitization ...

Science.gov (United States)

One of the lnteragency Coordinating Committee on the Validation of Alternative Method's (ICCVAM) top priorities is the development and evaluation of non-animal approaches to identify potential skin sensitizers. The complexity of biological events necessary to produce skin sensitization suggests that no single alternative method will replace the currently accepted animal tests. ICCVAM is evaluating an integrated approach to testing and assessment based on the adverse outcome pathway for skin sensitization that uses machine learning approaches to predict human skin sensitization hazard. We combined data from three in chemico or in vitro assays - the direct peptide reactivity assay (DPRA), human cell line activation test (h-CLAT) and KeratinoSens TM assay - six physicochemical properties and an in silico read-across prediction of skin sensitization hazard into 12 variable groups. The variable groups were evaluated using two machine learning approaches , logistic regression and support vector machine, to predict human skin sensitization hazard. Models were trained on 72 substances and tested on an external set of 24 substances. The six models (three logistic regression and three support vector machine) with the highest accuracy (92%) used: (1) DPRA, h-CLAT and read-across; (2) DPRA, h-CLAT, read-across and KeratinoSens; or (3) DPRA, h-CLAT, read-across, KeratinoSens and log P. The models performed better at predicting human skin sensitization hazard than the murine

Risk adjusted surgical audit in gynaecological oncology: P-POSSUM does not predict outcome.

Science.gov (United States)

Das, N; Talaat, A S; Naik, R; Lopes, A D; Godfrey, K A; Hatem, M H; Edmondson, R J

2006-12-01

To assess the Physiological and Operative Severity Score for the enumeration of mortality and morbidity (POSSUM) and its validity for use in gynaecological oncology surgery. All patients undergoing gynaecological oncology surgery at the Northern Gynaecological Oncology Centre (NGOC) Gateshead, UK over a period of 12months (2002-2003) were assessed prospectively. Mortality and morbidity predictions using the Portsmouth modification of the POSSUM algorithm (P-POSSUM) were compared to the actual outcomes. Performance of the model was also evaluated using the Hosmer and Lemeshow Chi square statistic (testing the goodness of fit). During this period 468 patients were assessed. The P-POSSUM appeared to over predict mortality rates for our patients. It predicted a 7% mortality rate for our patients compared to an observed rate of 2% (35 predicted deaths in comparison to 10 observed deaths), a difference that was statistically significant (H&L chi(2)=542.9, d.f. 8, prisk of mortality for gynaecological oncology patients undergoing surgery. The P-POSSUM algorithm will require further adjustments prior to adoption for gynaecological cancer surgery as a risk adjusted surgical audit tool.

Writing Abilities Longitudinally Predict Academic Outcomes of Adolescents with ADHD

Science.gov (United States)

Molitor, Stephen J.; Langberg, Joshuah M.; Bourchtein, Elizaveta; Eddy, Laura D.; Dvorsky, Melissa R.; Evans, Steven W.

2016-01-01

Students with ADHD often experience a host of negative academic outcomes and deficits in reading and mathematics abilities contribute to these academic impairments. Students with ADHD may also have difficulties with written expression but there has been minimal research in this area and it is not clear whether written expression abilities uniquely contribute to the academic functioning of students with ADHD. The current study included a sample of 104 middle school students diagnosed with ADHD (grades 6–8). Participants were followed longitudinally to evaluate whether written expression abilities at baseline predicted student GPA and parent ratings of academic impairment 18 months later, after controlling for reading ability and additional relevant covariates. Written expression abilities longitudinally predicted both academic outcomes above and beyond ADHD and ODD symptoms, medication use, reading ability, and baseline values of GPA and parent-rated academic impairment. Follow-up analyses revealed that no single aspect of written expression was demonstrably more impactful on academic outcomes than the others, suggesting that writing as an entire process should be the focus of intervention. PMID:26783650

Prediction of delayed cerebral ischemia, rebleeding, and outcome after aneurysmal subarachnoid hemorrhage

NARCIS (Netherlands)

Hijdra, A.; van Gijn, J.; Nagelkerke, N. J.; Vermeulen, M.; van Crevel, H.

1988-01-01

Using logistic regression, we analyzed the predictive value of a number of entry variables with respect to the outcome variables delayed cerebral ischemia, rebleeding, and poor outcome (death or severe disability) in patients with aneurysmal subarachnoid hemorrhage. The entry variables were clinical

Daily Autonomy Support and Sexual Identity Disclosure Predicts Daily Mental and Physical Health Outcomes.

Science.gov (United States)

Legate, Nicole; Ryan, Richard M; Rogge, Ronald D

2017-06-01

Using a daily diary methodology, we examined how social environments support or fail to support sexual identity disclosure, and associated mental and physical health outcomes. Results showed that variability in disclosure across the diary period related to greater psychological well-being and fewer physical symptoms, suggesting potential adaptive benefits to selectively disclosing. A multilevel path model indicated that perceiving autonomy support in conversations predicted more disclosure, which in turn predicted more need satisfaction, greater well-being, and fewer physical symptoms that day. Finally, mediation analyses revealed that disclosure and need satisfaction explained why perceiving autonomy support in a conversation predicted greater well-being and fewer physical symptoms. That is, perceiving autonomy support in conversations indirectly predicted greater wellness through sexual orientation disclosure, along with feeling authentic and connected in daily interactions with others. Discussion highlights the role of supportive social contexts and everyday opportunities to disclose in affecting sexual minority mental and physical health.

Do treatment quality indicators predict cardiovascular outcomes in patients with diabetes?

Directory of Open Access Journals (Sweden)

Grigory Sidorenkov

Full Text Available BACKGROUND: Landmark clinical trials have led to optimal treatment recommendations for patients with diabetes. Whether optimal treatment is actually delivered in practice is even more important than the efficacy of the drugs tested in trials. To this end, treatment quality indicators have been developed and tested against intermediate outcomes. No studies have tested whether these treatment quality indicators also predict hard patient outcomes. METHODS: A cohort study was conducted using data collected from >10.000 diabetes patients in the Groningen Initiative to Analyze Type 2 Treatment (GIANTT database and Dutch Hospital Data register. Included quality indicators measured glucose-, lipid-, blood pressure- and albuminuria-lowering treatment status and treatment intensification. Hard patient outcome was the composite of cardiovascular events and all-cause death. Associations were tested using Cox regression adjusting for confounding, reporting hazard ratios (HR with 95% confidence intervals. RESULTS: Lipid and albuminuria treatment status, but not blood pressure lowering treatment status, were associated with the composite outcome (HR = 0.77, 0.67-0.88; HR = 0.75, 0.59-0.94. Glucose lowering treatment status was associated with the composite outcome only in patients with an elevated HbA1c level (HR = 0.72, 0.56-0.93. Treatment intensification with glucose-lowering but not with lipid-, blood pressure- and albuminuria-lowering drugs was associated with the outcome (HR = 0.73, 0.60-0.89. CONCLUSION: Treatment quality indicators measuring lipid- and albuminuria-lowering treatment status are valid quality measures, since they predict a lower risk of cardiovascular events and mortality in patients with diabetes. The quality indicators for glucose-lowering treatment should only be used for restricted populations with elevated HbA1c levels. Intriguingly, the tested indicators for blood pressure-lowering treatment did not predict patient

Modelling bankruptcy prediction models in Slovak companies

Directory of Open Access Journals (Sweden)

Kovacova Maria

2017-01-01

Full Text Available An intensive research from academics and practitioners has been provided regarding models for bankruptcy prediction and credit risk management. In spite of numerous researches focusing on forecasting bankruptcy using traditional statistics techniques (e.g. discriminant analysis and logistic regression and early artificial intelligence models (e.g. artificial neural networks, there is a trend for transition to machine learning models (support vector machines, bagging, boosting, and random forest to predict bankruptcy one year prior to the event. Comparing the performance of this with unconventional approach with results obtained by discriminant analysis, logistic regression, and neural networks application, it has been found that bagging, boosting, and random forest models outperform the others techniques, and that all prediction accuracy in the testing sample improves when the additional variables are included. On the other side the prediction accuracy of old and well known bankruptcy prediction models is quiet high. Therefore, we aim to analyse these in some way old models on the dataset of Slovak companies to validate their prediction ability in specific conditions. Furthermore, these models will be modelled according to new trends by calculating the influence of elimination of selected variables on the overall prediction ability of these models.

The Identification of a Threshold of Long Work Hours for Predicting Elevated Risks of Adverse Health Outcomes.

Science.gov (United States)

Conway, Sadie H; Pompeii, Lisa A; Gimeno Ruiz de Porras, David; Follis, Jack L; Roberts, Robert E

2017-07-15

Working long hours has been associated with adverse health outcomes. However, a definition of long work hours relative to adverse health risk has not been established. Repeated measures of work hours among approximately 2,000 participants from the Panel Study of Income Dynamics (1986-2011), conducted in the United States, were retrospectively analyzed to derive statistically optimized cutpoints of long work hours that best predicted three health outcomes. Work-hours cutpoints were assessed for model fit, calibration, and discrimination separately for the outcomes of poor self-reported general health, incident cardiovascular disease, and incident cancer. For each outcome, the work-hours threshold that best predicted increased risk was 52 hours per week or more for a minimum of 10 years. Workers exposed at this level had a higher risk of poor self-reported general health (relative risk (RR) = 1.28; 95% confidence interval (CI): 1.06, 1.53), cardiovascular disease (RR = 1.42; 95% CI: 1.24, 1.63), and cancer (RR = 1.62; 95% CI: 1.22, 2.17) compared with those working 35-51 hours per week for the same duration. This study provides the first health risk-based definition of long work hours. Further examination of the predictive power of this cutpoint on other health outcomes and in other study populations is needed. © The Author 2017. Published by Oxford University Press on behalf of the Johns Hopkins Bloomberg School of Public Health. All rights reserved. For permissions, please e-mail: journals.permissions@oup.com.

Predicting sugar-sweetened behaviours with theory of planned behaviour constructs: Outcome and process results from the SIPsmartER behavioural intervention

Science.gov (United States)

Zoellner, Jamie M.; Porter, Kathleen J.; Chen, Yvonnes; Hedrick, Valisa E.; You, Wen; Hickman, Maja; Estabrooks, Paul A.

2017-01-01

Objective Guided by the theory of planned behaviour (TPB) and health literacy concepts, SIPsmartER is a six-month multicomponent intervention effective at improving SSB behaviours. Using SIPsmartER data, this study explores prediction of SSB behavioural intention (BI) and behaviour from TPB constructs using: (1) cross-sectional and prospective models and (2) 11 single-item assessments from interactive voice response (IVR) technology. Design Quasi-experimental design, including pre- and post-outcome data and repeated-measures process data of 155 intervention participants. Main Outcome Measures Validated multi-item TPB measures, single-item TPB measures, and self-reported SSB behaviours. Hypothesised relationships were investigated using correlation and multiple regression models. Results TPB constructs explained 32% of the variance cross sectionally and 20% prospectively in BI; and explained 13–20% of variance cross sectionally and 6% prospectively. Single-item scale models were significant, yet explained less variance. All IVR models predicting BI (average 21%, range 6–38%) and behaviour (average 30%, range 6–55%) were significant. Conclusion Findings are interpreted in the context of other cross-sectional, prospective and experimental TPB health and dietary studies. Findings advance experimental application of the TPB, including understanding constructs at outcome and process time points and applying theory in all intervention development, implementation and evaluation phases. PMID:28165771

Patient-Specific MRI-Based Right Ventricle Models Using Different Zero-Load Diastole and Systole Geometries for Better Cardiac Stress and Strain Calculations and Pulmonary Valve Replacement Surgical Outcome Predictions.

Directory of Open Access Journals (Sweden)

Dalin Tang

Full Text Available Accurate calculation of ventricular stress and strain is critical for cardiovascular investigations. Sarcomere shortening in active contraction leads to change of ventricular zero-stress configurations during the cardiac cycle. A new model using different zero-load diastole and systole geometries was introduced to provide more accurate cardiac stress/strain calculations with potential to predict post pulmonary valve replacement (PVR surgical outcome.Cardiac magnetic resonance (CMR data were obtained from 16 patients with repaired tetralogy of Fallot prior to and 6 months after pulmonary valve replacement (8 male, 8 female, mean age 34.5 years. Patients were divided into Group 1 (n = 8 with better post PVR outcome and Group 2 (n = 8 with worse post PVR outcome based on their change in RV ejection fraction (EF. CMR-based patient-specific computational RV/LV models using one zero-load geometry (1G model and two zero-load geometries (diastole and systole, 2G model were constructed and RV wall thickness, volume, circumferential and longitudinal curvatures, mechanical stress and strain were obtained for analysis. Pairwise T-test and Linear Mixed Effect (LME model were used to determine if the differences from the 1G and 2G models were statistically significant, with the dependence of the pair-wise observations and the patient-slice clustering effects being taken into consideration. For group comparisons, continuous variables (RV volumes, WT, C- and L- curvatures, and stress and strain values were summarized as mean ± SD and compared between the outcome groups by using an unpaired Student t-test. Logistic regression analysis was used to identify potential morphological and mechanical predictors for post PVR surgical outcome.Based on results from the 16 patients, mean begin-ejection stress and strain from the 2G model were 28% and 40% higher than that from the 1G model, respectively. Using the 2G model results, RV EF changes correlated negatively with

Predicting an Optimal Outcome after Radical Prostatectomy: The “Trifecta” Nomogram

Science.gov (United States)

Eastham, James A.; Scardino, Peter T.; Kattan, Michael W.

2014-01-01

Purpose The optimal outcome after radical prostatectomy (RP) for clinically localized prostate cancer is freedom from biochemical recurrence (BCR) along with recovery of continence and erectile function, a so-called trifecta. We evaluated our series of open radical prostatectomy patients to determine the likelihood of this outcome and to develop a nomogram predicting the trifecta. Material and Methods We reviewed records of patients undergoing open RP for clinical stage T1c–T3a prostate cancer at our center during 2000–2006. Men were excluded if they received preoperative hormonal therapy, chemotherapy, or radiation therapy; if their pre-treatment PSA was >50 ng/ml; or if they were impotent or incontinent before RP; 1577 men were included in the study. Freedom from BCR was defined as post-RP PSA <0.2 ng/ml. Continence was defined as not having to wear any protective pads. Potency was defined as erections adequate for intercourse on the majority of attempts, with or without a phosphodiesterase-5 inhibitor. Results Mean patient age was 58 years and mean pretreatment PSA was 6.4 ng/ml. A trifecta outcome (cancer-free status with recovery of continence and potency) was achieved in 62% of patients. In a nomogram developed to predict the likelihood of the trifecta, baseline PSA was the major predictive factor. The area under the receiver operating characteristic curve for the nomogram was 0.773, and calibration appeared excellent. Conclusions A trifecta (optimal) outcome can be achieved in the majority of men undergoing RP. The nomogram will permit patients to estimate preoperatively their likelihood of an optimal outcome after RP. PMID:18423693

Personalized prediction of lifetime benefits with statin therapy for asymptomatic individuals: a modeling study.

Directory of Open Access Journals (Sweden)

Bart S Ferket

Full Text Available BACKGROUND: Physicians need to inform asymptomatic individuals about personalized outcomes of statin therapy for primary prevention of cardiovascular disease (CVD. However, current prediction models focus on short-term outcomes and ignore the competing risk of death due to other causes. We aimed to predict the potential lifetime benefits with statin therapy, taking into account competing risks. METHODS AND FINDINGS: A microsimulation model based on 5-y follow-up data from the Rotterdam Study, a population-based cohort of individuals aged 55 y and older living in the Ommoord district of Rotterdam, the Netherlands, was used to estimate lifetime outcomes with and without statin therapy. The model was validated in-sample using 10-y follow-up data. We used baseline variables and model output to construct (1 a web-based calculator for gains in total and CVD-free life expectancy and (2 color charts for comparing these gains to the Systematic Coronary Risk Evaluation (SCORE charts. In 2,428 participants (mean age 67.7 y, 35.5% men, statin therapy increased total life expectancy by 0.3 y (SD 0.2 and CVD-free life expectancy by 0.7 y (SD 0.4. Age, sex, smoking, blood pressure, hypertension, lipids, diabetes, glucose, body mass index, waist-to-hip ratio, and creatinine were included in the calculator. Gains in total and CVD-free life expectancy increased with blood pressure, unfavorable lipid levels, and body mass index after multivariable adjustment. Gains decreased considerably with advancing age, while SCORE 10-y CVD mortality risk increased with age. Twenty-five percent of participants with a low SCORE risk achieved equal or larger gains in CVD-free life expectancy than the median gain in participants with a high SCORE risk. CONCLUSIONS: We developed tools to predict personalized increases in total and CVD-free life expectancy with statin therapy. The predicted gains we found are small. If the underlying model is validated in an independent cohort, the

Risk prediction models for major adverse cardiac event (MACE) following percutaneous coronary intervention (PCI): A review

Science.gov (United States)

Manan, Norhafizah A.; Abidin, Basir

2015-02-01

Five percent of patients who went through Percutaneous Coronary Intervention (PCI) experienced Major Adverse Cardiac Events (MACE) after PCI procedure. Risk prediction of MACE following a PCI procedure therefore is helpful. This work describes a review of such prediction models currently in use. Literature search was done on PubMed and SCOPUS database. Thirty literatures were found but only 4 studies were chosen based on the data used, design, and outcome of the study. Particular emphasis was given and commented on the study design, population, sample size, modeling method, predictors, outcomes, discrimination and calibration of the model. All the models had acceptable discrimination ability (C-statistics >0.7) and good calibration (Hosmer-Lameshow P-value >0.05). Most common model used was multivariate logistic regression and most popular predictor was age.

Moderate efficiency of clinicians' predictions decreased for blurred clinical conditions and benefits from the use of BRASS index. A longitudinal study on geriatric patients' outcomes.

Science.gov (United States)

Signorini, Giulia; Dagani, Jessica; Bulgari, Viola; Ferrari, Clarissa; de Girolamo, Giovanni

2016-01-01

Accurate prognosis is an essential aspect of good clinical practice and efficient health services, particularly for chronic and disabling diseases, as in geriatric populations. This study aims to examine the accuracy of clinical prognostic predictions and to devise prediction models combining clinical variables and clinicians' prognosis for a geriatric patient sample. In a sample of 329 consecutive older patients admitted to 10 geriatric units, we evaluated the accuracy of clinicians' prognosis regarding three outcomes at discharge: global functioning, length of stay (LoS) in hospital, and destination at discharge (DD). A comprehensive set of sociodemographic, clinical, and treatment-related information were also collected. Moderate predictive performance was found for all three outcomes: area under receiver operating characteristic curve of 0.79 and 0.78 for functioning and LoS, respectively, and moderate concordance, Cohen's K = 0.45, between predicted and observed DD. Predictive models found the Blaylock Risk Assessment Screening Score together with clinicians' judgment relevant to improve predictions for all outcomes (absolute improvement in adjusted and pseudo-R(2) up to 19%). Although the clinicians' estimates were important factors in predicting global functioning, LoS, and DD, more research is needed regarding both methodological aspects and clinical measurements, to improve prognostic clinical indices. Copyright © 2016 Elsevier Inc. All rights reserved.

Issues and Importance of "Good" Starting Points for Nonlinear Regression for Mathematical Modeling with Maple: Basic Model Fitting to Make Predictions with Oscillating Data

Science.gov (United States)

Fox, William

2012-01-01

The purpose of our modeling effort is to predict future outcomes. We assume the data collected are both accurate and relatively precise. For our oscillating data, we examined several mathematical modeling forms for predictions. We also examined both ignoring the oscillations as an important feature and including the oscillations as an important…

Interpretable Predictive Models for Knowledge Discovery from Home-Care Electronic Health Records

Directory of Open Access Journals (Sweden)

Bonnie L. Westra

2011-01-01

Full Text Available The purpose of this methodological study was to compare methods of developing predictive rules that are parsimonious and clinically interpretable from electronic health record (EHR home visit data, contrasting logistic regression with three data mining classification models. We address three problems commonly encountered in EHRs: the value of including clinically important variables with little variance, handling imbalanced datasets, and ease of interpretation of the resulting predictive models. Logistic regression and three classification models using Ripper, decision trees, and Support Vector Machines were applied to a case study for one outcome of improvement in oral medication management. Predictive rules for logistic regression, Ripper, and decision trees are reported and results compared using F-measures for data mining models and area under the receiver-operating characteristic curve for all models. The rules generated by the three classification models provide potentially novel insights into mining EHRs beyond those provided by standard logistic regression, and suggest steps for further study.

Post-injury personality in the prediction of outcome following severe acquired brain injury.

Science.gov (United States)

Cattran, Charlotte Jane; Oddy, Michael; Wood, Rodger Llewellyn; Moir, Jane Frances

2011-01-01

The aim of the study was to examine the utility of five measures of non-cognitive neurobehavioural (NCNB) changes that often occur following acquired brain injury, in predicting outcome (measured in terms of participation and social adaptation) at 1-year follow-up. The study employed a longitudinal, correlational design. Multiple regression was employed to investigate the value of five new NCNB measures of social perception, emotional regulation, motivation, impulsivity and disinhibition in the prediction of outcome as measured by the Mayo-Portland Adaptability Inventory (MPAI). Two NCNB measures (motivation and emotional regulation) were found to significantly predict outcome at 1-year follow-up, accounting for 53% of the variance in MPAI total scores. These measures provide a method of quantifying the extent of NCNB changes following brain injury. The predictive value of the measures indicates that they may represent a useful tool which could aid clinicians in identifying early-on those whose symptoms are likely to persist and who may require ongoing intervention. This could facilitate the planning of rehabilitation programmes.

Machine Learning Approaches for Predicting Radiation Therapy Outcomes: A Clinician's Perspective

International Nuclear Information System (INIS)

Kang, John; Schwartz, Russell; Flickinger, John; Beriwal, Sushil

2015-01-01

Radiation oncology has always been deeply rooted in modeling, from the early days of isoeffect curves to the contemporary Quantitative Analysis of Normal Tissue Effects in the Clinic (QUANTEC) initiative. In recent years, medical modeling for both prognostic and therapeutic purposes has exploded thanks to increasing availability of electronic data and genomics. One promising direction that medical modeling is moving toward is adopting the same machine learning methods used by companies such as Google and Facebook to combat disease. Broadly defined, machine learning is a branch of computer science that deals with making predictions from complex data through statistical models. These methods serve to uncover patterns in data and are actively used in areas such as speech recognition, handwriting recognition, face recognition, “spam” filtering (junk email), and targeted advertising. Although multiple radiation oncology research groups have shown the value of applied machine learning (ML), clinical adoption has been slow due to the high barrier to understanding these complex models by clinicians. Here, we present a review of the use of ML to predict radiation therapy outcomes from the clinician's point of view with the hope that it lowers the “barrier to entry” for those without formal training in ML. We begin by describing 7 principles that one should consider when evaluating (or creating) an ML model in radiation oncology. We next introduce 3 popular ML methods—logistic regression (LR), support vector machine (SVM), and artificial neural network (ANN)—and critique 3 seminal papers in the context of these principles. Although current studies are in exploratory stages, the overall methodology has progressively matured, and the field is ready for larger-scale further investigation.

Characteristics of Fibromyalgia Independently Predict Poorer Long‐Term Analgesic Outcomes Following Total Knee and Hip Arthroplasty

Science.gov (United States)

Urquhart, Andrew G.; Hassett, Afton L.; Tsodikov, Alex; Hallstrom, Brian R.; Wood, Nathan I.; Williams, David A.; Clauw, Daniel J.

2015-01-01

Objective While psychosocial factors have been associated with poorer outcomes after knee and hip arthroplasty, we hypothesized that augmented pain perception, as occurs in conditions such as fibromyalgia, may account for decreased responsiveness to primary knee and hip arthroplasty. Methods A prospective, observational cohort study was conducted. Preoperative phenotyping was conducted using validated questionnaires to assess pain, function, depression, anxiety, and catastrophizing. Participants also completed the 2011 fibromyalgia survey questionnaire, which addresses the widespread body pain and comorbid symptoms associated with characteristics of fibromyalgia. Results Of the 665 participants, 464 were retained 6 months after surgery. Since individuals who met criteria for being classified as having fibromyalgia were expected to respond less favorably, all primary analyses excluded these individuals (6% of the cohort). In the multivariate linear regression model predicting change in knee/hip pain (primary outcome), a higher fibromyalgia survey score was independently predictive of less improvement in pain (estimate −0.25, SE 0.044; P fibromyalgia survey score (P = 0.00032). The fibromyalgia survey score was also independently predictive of change in overall pain and patient global impression of change. Conclusion Our findings indicate that the fibromyalgia survey score is a robust predictor of poorer arthroplasty outcomes, even among individuals whose score falls well below the threshold for the categorical diagnosis of fibromyalgia. PMID:25772388

Pediatric extracorporeal shock wave lithotripsy: Predicting successful outcomes.

Science.gov (United States)

McAdams, Sean; Shukla, Aseem R

2010-10-01

Extracorporeal shock wave lithotripsy (ESWL) is currently a first-line procedure of most upper urinary tract stones ionizing radiation, perhaps utilizing advancements in ultrasound and magnetic resonance imaging. This report provides a review of the current literature evaluating the patient attributes and stone factors that may be predictive of successful ESWL outcomes along with reviewing the role of pre-operative imaging and considerations for patient safety.

Satisfaction of psychotic patients with care and its value to predict outcomes

NARCIS (Netherlands)

Vermeulen, J. M.; Schirmbeck, N. F.; Van Tricht, M. J.; de Haan, L.

2018-01-01

Background: A key indicator of quality of treatment from the patient's perspective is expressed by satisfaction with care. Our aim was to (i) explore satisfaction and its relation to clinical outcome measures; and (ii) explore the predictive value of satisfaction for the course of outcomes over

Decisions on control of foot-and-mouth disease informed using model predictions

DEFF Research Database (Denmark)

Hisham Beshara Halasa, Tariq; Willeberg, P.; Christiansen, Lasse Engbo

2013-01-01

, epidemic duration, geographical size and costs. The first 14 days spatial spread (FFS) was also included to further support the prediction. The epidemic data was obtained from a Danish version (DTU-DADS) of a pre-existing FMD simulation model (Davis Animal Disease Spread – DADS) adapted to model the spread......The decision on whether or not to change the control strategy, such as introducing emergency vaccination, is perhaps one of the most difficult decisions faced by the veterinary authorities during a foot-and-mouth disease (FMD) epidemic. A simple tool that may predict the epidemic outcome...... and consequences would be useful to assist the veterinary authorities in the decision-making process. A previously proposed simple quantitative tool based on the first 14 days outbreaks (FFO) of FMD was used with results from an FMD simulation exercise. Epidemic outcomes included the number of affected herds...

Microsatellite Instability Predicts Clinical Outcome in Radiation-Treated Endometrioid Endometrial Cancer

International Nuclear Information System (INIS)

Bilbao, Cristina; Lara, Pedro Carlos; Ramirez, Raquel; Henriquez-Hernandez, Luis Alberto; Rodriguez, German; Falcon, Orlando; Leon, Laureano; Perucho, Manuel

2010-01-01

Purpose: To elucidate whether microsatellite instability (MSI) predicts clinical outcome in radiation-treated endometrioid endometrial cancer (EEC). Methods and Materials: A consecutive series of 93 patients with EEC treated with extrafascial hysterectomy and postoperative radiotherapy was studied. The median clinical follow-up of patients was 138 months, with a maximum of 232 months. Five quasimonomorphic mononucleotide markers (BAT-25, BAT-26, NR21, NR24, and NR27) were used for MSI classification. Results: Twenty-five patients (22%) were classified as MSI. Both in the whole series and in early stages (I and II), univariate analysis showed a significant association between MSI and poorer 10-year local disease-free survival, disease-free survival, and cancer-specific survival. In multivariate analysis, MSI was excluded from the final regression model in the whole series, but in early stages MSI provided additional significant predictive information independent of traditional prognostic and predictive factors (age, stage, grade, and vascular invasion) for disease-free survival (hazard ratio [HR] 3.25, 95% confidence interval [CI] 1.01-10.49; p = 0.048) and cancer-specific survival (HR 4.20, 95% CI 1.23-14.35; p = 0.022) and was marginally significant for local disease-free survival (HR 3.54, 95% CI 0.93-13.46; p = 0.064). Conclusions: These results suggest that MSI may predict radiotherapy response in early-stage EEC.

A new nomogram to predict pathologic outcome following radical prostatectomy

Directory of Open Access Journals (Sweden)

Alexandre Crippa

2006-04-01

Full Text Available OBJECTIVE: To develop a preoperative nomogram to predict pathologic outcome in patients submitted to radical prostatectomy for clinical localized prostate cancer. MATERIALS AND METHODS: Nine hundred and sixty patients with clinical stage T1 and T2 prostate cancer were evaluated following radical prostatectomy, and 898 were included in the study. Following a multivariate analysis, nomograms were developed incorporating serum PSA, biopsy Gleason score, and percentage of positive biopsy cores in order to predict the risks of extraprostatic tumor extension, and seminal vesicle involvement. RESULTS: In univariate analysis there was a significant association between percentage of positive biopsy cores (p < 0.001, serum PSA (p = 0.001 and biopsy Gleason score (p < 0.001 with extraprostatic tumor extension. A similar pathologic outcome was seen among tumors with Gleason score 7, and Gleason score 8 to 10. In multivariate analysis, the 3 preoperative variables showed independent significance to predict tumor extension. This allowed the development of nomogram-1 (using Gleason scores in 3 categories - 2 to 6, 7 and 8 to 10 and nomogram-2 (using Gleason scores in 2 categories - 2 to 6 and 7 to 10 to predict disease extension based on these 3 parameters. In the validation analysis, 87% and 91.1% of the time the nomograms-1 and 2, correctly predicted the probability of a pathological stage to within 10% respectively. CONCLUSION: Incorporating percent of positive biopsy cores to a nomogram that includes preoperative serum PSA and biopsy Gleason score, can accurately predict the presence of extraprostatic disease extension in patients with clinical localized prostate cancer.

The Adverse Effect of Spasticity on 3-Month Poststroke Outcome Using a Population-Based Model

Directory of Open Access Journals (Sweden)

S. R. Belagaje

2014-01-01

Full Text Available Several devices and medications have been used to address poststroke spasticity. Yet, spasticity’s impact on outcomes remains controversial. Using data from a cohort of 460 ischemic stroke patients, we previously published a validated multivariable regression model for predicting 3-month modified Rankin Score (mRS as an indicator of functional outcome. Here, we tested whether including spasticity improved model fit and estimated the effect spasticity had on the outcome. Spasticity was defined by a positive response to the question “Did you have spasticity following your stroke?” on direct interview at 3 months from stroke onset. Patients who had expired by 90 days (n=30 or did not have spasticity data available (n=102 were excluded. Spasticity affected the 3-month functional status (β=0.420, 95 CI=0.194 to 0.645 after accounting for age, diabetes, leukoaraiosis, and retrospective NIHSS. Using spasticity as a covariable, the model’s R2 changed from 0.599 to 0.622. In our model, the presence of spasticity in the cohort was associated with a worsened 3-month mRS by an average of 0.4 after adjusting for known covariables. This significant adverse effect on functional outcomes adds predictive value beyond previously established factors.

Predicting Outcome in Patients with Anti-GBM Glomerulonephritis.

Science.gov (United States)

van Daalen, Emma E; Jennette, J Charles; McAdoo, Stephen P; Pusey, Charles D; Alba, Marco A; Poulton, Caroline J; Wolterbeek, Ron; Nguyen, Tri Q; Goldschmeding, Roel; Alchi, Bassam; Griffiths, Meryl; de Zoysa, Janak R; Vincent, Beula; Bruijn, Jan A; Bajema, Ingeborg M

2018-01-06

Large studies on long-term kidney outcome in patients with anti-glomerular basement membrane (anti-GBM) GN are lacking. This study aimed to identify clinical and histopathologic parameters that predict kidney outcome in these patients. This retrospective analysis included a total of 123 patients with anti-GBM GN between 1986 and 2015 from six centers worldwide. Their kidney biopsy samples were classified according to the histopathologic classification for ANCA-associated GN. Clinical data such as details of treatment were retrieved from clinical records. The primary outcome parameter was the occurrence of ESRD. Kidney survival was analyzed using the log-rank test and Cox regression analyses. The 5-year kidney survival rate was 34%, with an improved rate observed among patients diagnosed after 2007 ( P =0.01). In patients with anti-GBM GN, histopathologic class and kidney survival were associated ( P GBM GN. Kidney outcome has improved during recent years; the success rate doubled after 2007. This article contains a podcast at https://www.asn-online.org/media/podcast/CJASN/2017_11_21_CJASNPodcast_18_1_v.mp3. Copyright © 2018 by the American Society of Nephrology.

Relative size predicts competitive outcome through 2 million years.

Science.gov (United States)

Liow, Lee Hsiang; Di Martino, Emanuela; Krzeminska, Malgorzata; Ramsfjell, Mali; Rust, Seabourne; Taylor, Paul D; Voje, Kjetil L

2017-08-01

Competition is an important biotic interaction that influences survival and reproduction. While competition on ecological timescales has received great attention, little is known about competition on evolutionary timescales. Do competitive abilities change over hundreds of thousands to millions of years? Can we predict competitive outcomes using phenotypic traits? How much do traits that confer competitive advantage and competitive outcomes change? Here we show, using communities of encrusting marine bryozoans spanning more than 2 million years, that size is a significant determinant of overgrowth outcomes: colonies with larger zooids tend to overgrow colonies with smaller zooids. We also detected temporally coordinated changes in average zooid sizes, suggesting that different species responded to a common external driver. Although species-specific average zooid sizes change over evolutionary timescales, species-specific competitive abilities seem relatively stable, suggesting that traits other than zooid size also control overgrowth outcomes and/or that evolutionary constraints are involved. © 2017 John Wiley & Sons Ltd/CNRS.

Baseline prediction of combination therapy outcome in hepatitis C virus 1b infected patients by discriminant analysis using viral and host factors.

Science.gov (United States)

Saludes, Verónica; Bracho, Maria Alma; Valero, Oliver; Ardèvol, Mercè; Planas, Ramón; González-Candelas, Fernando; Ausina, Vicente; Martró, Elisa

2010-11-30

Current treatment of chronic hepatitis C virus (HCV) infection has limited efficacy -especially among genotype 1 infected patients-, is costly, and involves severe side effects. Thus, predicting non-response is of major interest for both patient wellbeing and health care expense. At present, treatment cannot be individualized on the basis of any baseline predictor of response. We aimed to identify pre-treatment clinical and virological parameters associated with treatment failure, as well as to assess whether therapy outcome could be predicted at baseline. Forty-three HCV subtype 1b (HCV-1b) chronically infected patients treated with pegylated-interferon alpha plus ribavirin were retrospectively studied (21 responders and 22 non-responders). Host (gender, age, weight, transaminase levels, fibrosis stage, and source of infection) and viral-related factors (viral load, and genetic variability in the E1-E2 and Core regions) were assessed. Logistic regression and discriminant analyses were used to develop predictive models. A "leave-one-out" cross-validation method was used to assess the reliability of the discriminant models. Lower alanine transaminase levels (ALT, p=0.009), a higher number of quasispecies variants in the E1-E2 region (number of haplotypes, nHap_E1-E2) (p=0.003), and the absence of both amino acid arginine at position 70 and leucine at position 91 in the Core region (p=0.039) were significantly associated with treatment failure. Therapy outcome was most accurately predicted by discriminant analysis (90.5% sensitivity and 95.5% specificity, 85.7% sensitivity and 81.8% specificity after cross-validation); the most significant variables included in the predictive model were the Core amino acid pattern, the nHap_E1-E2, and gamma-glutamyl transferase and ALT levels. Discriminant analysis has been shown as a useful tool to predict treatment outcome using baseline HCV genetic variability and host characteristics. The discriminant models obtained in this

Serum YKL-40 independently predicts outcome after transcatheter arterial chemoembolization of hepatocellular carcinoma.

Directory of Open Access Journals (Sweden)

Cheng-Bao Zhu

Full Text Available Transcatheter arterial chemoembolization (TACE is the most widely used treatment option for unresectable hepatocellular carcinoma (HCC. Elevated serum YKL-40 level has been shown to predict poor prognosis in HCC patients undergoing resection. This study was designed to validate the prognostic significance of serum YKL-40 in patients with HCC undergoing TACE treatment.Serum YKL-40 level was determined by enzyme-linked immunosorbent assay. Overall survival (OS was evaluated with the Kaplan-Meier method and compared by the log-rank test. Multivariate study with Cox proportional hazard model was used to evaluate independent prognostic variables of OS.The median pretreatment serum YKL-40 in HCC patients with was significantly higher than that in healthy controls (P<0.001. The YKL-40 could predict survival precisely either in a dichotomized or continuous fashion (P<0.001 and P = 0.001, respectively. Multivariate Cox regression analysis indicated that serum YKL-40 was an independent prognostic factor for OS in HCC patients (P = 0.001. In further stratified analyses, YKL-40 could discriminate the outcomes of patients with low and high alpha-fetoprotein (AFP level (P = 0.006 and 0.016, respectively. Furthermore, the combination of serum YKL-40 and AFP had more capacity to predict patients' outcomes.Serum YKL-40 was demonstrated to be an independent prognostic biomarker in HCC patients treated with TACE. Our results need confirmation in an independent study.

Endometrial Receptivity and its Predictive Value for IVF/ICSI-Outcome.

Science.gov (United States)

Heger, A; Sator, M; Pietrowski, D

2012-08-01

Endometrial receptivity plays a crucial role in the establishment of a healthy pregnancy in cycles of assisted reproduction. The endometrium as a key factor during reproduction can be assessed in multiple ways, most commonly through transvaginal grey-scale or 3-D ultrasound. It has been shown that controlled ovarian hyperstimulation has a great impact on the uterine lining, which leads to different study results for the predictive value of endometrial factors measured on different cycle days. There is no clear consensus on whether endometrial factors are appropriate to predict treatment outcome and if so, which one is suited best. The aim of this review is to summarize recent findings of studies about the influence of endometrial thickness, volume and pattern on IVF- and ICSI-treatment outcome and provide an overview of future developments in the field.

Development of a Predictive Model for Induction Success of Labour

Directory of Open Access Journals (Sweden)

Cristina Pruenza

2018-03-01

Full Text Available Induction of the labour process is an extraordinarily common procedure used in some pregnancies. Obstetricians face the need to end a pregnancy, for medical reasons usually (maternal or fetal requirements or less frequently, social (elective inductions for convenience. The success of induction procedure is conditioned by a multitude of maternal and fetal variables that appear before or during pregnancy or birth process, with a low predictive value. The failure of the induction process involves performing a caesarean section. This project arises from the clinical need to resolve a situation of uncertainty that occurs frequently in our clinical practice. Since the weight of clinical variables is not adequately weighted, we consider very interesting to know a priori the possibility of success of induction to dismiss those inductions with high probability of failure, avoiding unnecessary procedures or postponing end if possible. We developed a predictive model of induced labour success as a support tool in clinical decision making. Improve the predictability of a successful induction is one of the current challenges of Obstetrics because of its negative impact. The identification of those patients with high chances of failure, will allow us to offer them better care improving their health outcomes (adverse perinatal outcomes for mother and newborn, costs (medication, hospitalization, qualified staff and patient perceived quality. Therefore a Clinical Decision Support System was developed to give support to the Obstetricians. In this article, we had proposed a robust method to explore and model a source of clinical information with the purpose of obtaining all possible knowledge. Generally, in classification models are difficult to know the contribution that each attribute provides to the model. We had worked in this direction to offer transparency to models that may be considered as black boxes. The positive results obtained from both the

FDG PET imaging for grading and prediction of outcome in chondrosarcoma patients

Energy Technology Data Exchange (ETDEWEB)

Brenner, Winfried; Eary, Janet F. [Division of Nuclear Medicine, University of Washington Medical Center, 1959 NE Pacific Street, Box 356113, WA 98195-6113, Seattle (United States); Conrad, Ernest U. [Department of Orthopaedics, University of Washington Medical Center, Seattle, WA (United States)

2004-02-01

The aims of this study were to assess the potential of fluorine-18 fluorodeoxyglucose positron emission tomography (FDG PET) for tumor grading in chondrosarcoma patients and to evaluate the role of standardized uptake value (SUV) as a parameter for prediction of patient outcome. FDG PET imaging was performed in 31 patients with chondrosarcoma prior to therapy. SUV was calculated for each tumor and correlated to tumor grade and size, and to patient outcome in terms of local relapse or metastatic disease with a mean follow-up period of 48 months. Chondrosarcomas were detectable in all patients. Tumor SUV was 3.38{+-}1.61 for grade I (n=15), 5.44{+-}3.06 for grade II (n=13), and 7.10{+-}2.61 for grade III (n=3). Significant differences were found between patients with and without disease progression: SUV was 6.42{+-}2.70 (n=10) in patients developing recurrent or metastatic disease compared with 3.74{+-}2.22 in patients without relapse (P=0.015). Using a cut-off of 4 for SUV, sensitivity, specificity, and positive and negative predictive values for a relapse were 90%, 76%, 64%, and 94%, respectively. Combining tumor grade and SUV, these parameters improved to 90%, 95%, 90%, and 95%, respectively. Pretherapeutic tumor SUV obtained by FDG PET imaging was a useful parameter for tumor grading and prediction of outcome in chondrosarcoma patients. The combination of SUV and histopathologic tumor grade further improved prediction of outcome substantially, allowing identification of patients at high risk for local relapse or metastatic disease. (orig.)

A polynomial based model for cell fate prediction in human diseases.

Science.gov (United States)

Ma, Lichun; Zheng, Jie

2017-12-21

Cell fate regulation directly affects tissue homeostasis and human health. Research on cell fate decision sheds light on key regulators, facilitates understanding the mechanisms, and suggests novel strategies to treat human diseases that are related to abnormal cell development. In this study, we proposed a polynomial based model to predict cell fate. This model was derived from Taylor series. As a case study, gene expression data of pancreatic cells were adopted to test and verify the model. As numerous features (genes) are available, we employed two kinds of feature selection methods, i.e. correlation based and apoptosis pathway based. Then polynomials of different degrees were used to refine the cell fate prediction function. 10-fold cross-validation was carried out to evaluate the performance of our model. In addition, we analyzed the stability of the resultant cell fate prediction model by evaluating the ranges of the parameters, as well as assessing the variances of the predicted values at randomly selected points. Results show that, within both the two considered gene selection methods, the prediction accuracies of polynomials of different degrees show little differences. Interestingly, the linear polynomial (degree 1 polynomial) is more stable than others. When comparing the linear polynomials based on the two gene selection methods, it shows that although the accuracy of the linear polynomial that uses correlation analysis outcomes is a little higher (achieves 86.62%), the one within genes of the apoptosis pathway is much more stable. Considering both the prediction accuracy and the stability of polynomial models of different degrees, the linear model is a preferred choice for cell fate prediction with gene expression data of pancreatic cells. The presented cell fate prediction model can be extended to other cells, which may be important for basic research as well as clinical study of cell development related diseases.

Modeling a Predictive Energy Equation Specific for Maintenance Hemodialysis.

Science.gov (United States)

Byham-Gray, Laura D; Parrott, J Scott; Peters, Emily N; Fogerite, Susan Gould; Hand, Rosa K; Ahrens, Sean; Marcus, Andrea Fleisch; Fiutem, Justin J

2017-03-01

Hypermetabolism is theorized in patients diagnosed with chronic kidney disease who are receiving maintenance hemodialysis (MHD). We aimed to distinguish key disease-specific determinants of resting energy expenditure to create a predictive energy equation that more precisely establishes energy needs with the intent of preventing protein-energy wasting. For this 3-year multisite cross-sectional study (N = 116), eligible participants were diagnosed with chronic kidney disease and were receiving MHD for at least 3 months. Predictors for the model included weight, sex, age, C-reactive protein (CRP), glycosylated hemoglobin, and serum creatinine. The outcome variable was measured resting energy expenditure (mREE). Regression modeling was used to generate predictive formulas and Bland-Altman analyses to evaluate accuracy. The majority were male (60.3%), black (81.0%), and non-Hispanic (76.7%), and 23% were ≥65 years old. After screening for multicollinearity, the best predictive model of mREE ( R 2 = 0.67) included weight, age, sex, and CRP. Two alternative models with acceptable predictability ( R 2 = 0.66) were derived with glycosylated hemoglobin or serum creatinine. Based on Bland-Altman analyses, the maintenance hemodialysis equation that included CRP had the best precision, with the highest proportion of participants' predicted energy expenditure classified as accurate (61.2%) and with the lowest number of individuals with underestimation or overestimation. This study confirms disease-specific factors as key determinants of mREE in patients on MHD and provides a preliminary predictive energy equation. Further prospective research is necessary to test the reliability and validity of this equation across diverse populations of patients who are receiving MHD.

Utilizing Machine Learning and Automated Performance Metrics to Evaluate Robot-Assisted Radical Prostatectomy Performance and Predict Outcomes.

Science.gov (United States)

Hung, Andrew J; Chen, Jian; Che, Zhengping; Nilanon, Tanachat; Jarc, Anthony; Titus, Micha; Oh, Paul J; Gill, Inderbir S; Liu, Yan

2018-05-01

Surgical performance is critical for clinical outcomes. We present a novel machine learning (ML) method of processing automated performance metrics (APMs) to evaluate surgical performance and predict clinical outcomes after robot-assisted radical prostatectomy (RARP). We trained three ML algorithms utilizing APMs directly from robot system data (training material) and hospital length of stay (LOS; training label) (≤2 days and >2 days) from 78 RARP cases, and selected the algorithm with the best performance. The selected algorithm categorized the cases as "Predicted as expected LOS (pExp-LOS)" and "Predicted as extended LOS (pExt-LOS)." We compared postoperative outcomes of the two groups (Kruskal-Wallis/Fisher's exact tests). The algorithm then predicted individual clinical outcomes, which we compared with actual outcomes (Spearman's correlation/Fisher's exact tests). Finally, we identified five most relevant APMs adopted by the algorithm during predicting. The "Random Forest-50" (RF-50) algorithm had the best performance, reaching 87.2% accuracy in predicting LOS (73 cases as "pExp-LOS" and 5 cases as "pExt-LOS"). The "pExp-LOS" cases outperformed the "pExt-LOS" cases in surgery time (3.7 hours vs 4.6 hours, p = 0.007), LOS (2 days vs 4 days, p = 0.02), and Foley duration (9 days vs 14 days, p = 0.02). Patient outcomes predicted by the algorithm had significant association with the "ground truth" in surgery time (p algorithm in predicting, were largely related to camera manipulation. To our knowledge, ours is the first study to show that APMs and ML algorithms may help assess surgical RARP performance and predict clinical outcomes. With further accrual of clinical data (oncologic and functional data), this process will become increasingly relevant and valuable in surgical assessment and training.

Epidemiology of Mild Traumatic Brain Injury with Intracranial Hemorrhage: Focusing Predictive Models for Neurosurgical Intervention.

Science.gov (United States)

Orlando, Alessandro; Levy, A Stewart; Carrick, Matthew M; Tanner, Allen; Mains, Charles W; Bar-Or, David

2017-11-01

To outline differences in neurosurgical intervention (NI) rates between intracranial hemorrhage (ICH) types in mild traumatic brain injuries and help identify which ICH types are most likely to benefit from creation of predictive models for NI. A multicenter retrospective study of adult patients spanning 3 years at 4 U.S. trauma centers was performed. Patients were included if they presented with mild traumatic brain injury (Glasgow Coma Scale score 13-15) with head CT scan positive for ICH. Patients were excluded for skull fractures, "unspecified hemorrhage," or coagulopathy. Primary outcome was NI. Stepwise multivariable logistic regression models were built to analyze the independent association between ICH variables and outcome measures. The study comprised 1876 patients. NI rate was 6.7%. There was a significant difference in rate of NI by ICH type. Subdural hematomas had the highest rate of NI (15.5%) and accounted for 78% of all NIs. Isolated subarachnoid hemorrhages had the lowest, nonzero, NI rate (0.19%). Logistic regression models identified ICH type as the most influential independent variable when examining NI. A model predicting NI for isolated subarachnoid hemorrhages would require 26,928 patients, but a model predicting NI for isolated subdural hematomas would require only 328 patients. This study highlighted disparate NI rates among ICH types in patients with mild traumatic brain injury and identified mild, isolated subdural hematomas as most appropriate for construction of predictive NI models. Increased health care efficiency will be driven by accurate understanding of risk, which can come only from accurate predictive models. Copyright © 2017 Elsevier Inc. All rights reserved.

Prediction of Functional Outcome in Axonal Guillain-Barre Syndrome.

Science.gov (United States)

Sung, Eun Jung; Kim, Dae Yul; Chang, Min Cheol; Ko, Eun Jae

2016-06-01

To identify the factors that could predict the functional outcome in patients with the axonal type of Guillain-Barre syndrome (GBS). Two hundred and two GBS patients admitted to our university hospital between 2003 and 2014 were reviewed retrospectively. We defined a good outcome as being "able to walk independently at 1 month after onset" and a poor outcome as being "unable to walk independently at 1 month after onset". We evaluated the factors that differed between the good and poor outcome groups. Twenty-four patients were classified into the acute motor axonal neuropathy type. There was a statistically significant difference between the good and poor outcome groups in terms of the GBS disability score at admission, and GBS disability score and Medical Research Council sum score at 1 month after admission. In an electrophysiologic analysis, the good outcome group showed greater amplitude of median, ulnar, deep peroneal, and posterior tibial nerve compound muscle action potentials (CMAP) and greater amplitude of median, ulnar, and superficial peroneal sensory nerve action potentials (SNAP) than the poor outcome group. A lower GBS disability score at admission, high amplitude of median, ulnar, deep peroneal, and posterior tibial CMAPs, and high amplitude of median, ulnar, and superficial peroneal SNAPs were associated with being able to walk at 1 month in patients with axonal GBS.

Electroencephalography Predicts Poor and Good Outcomes After Cardiac Arrest: A Two-Center Study.

Science.gov (United States)

Rossetti, Andrea O; Tovar Quiroga, Diego F; Juan, Elsa; Novy, Jan; White, Roger D; Ben-Hamouda, Nawfel; Britton, Jeffrey W; Oddo, Mauro; Rabinstein, Alejandro A

2017-07-01

The prognostic role of electroencephalography during and after targeted temperature management in postcardiac arrest patients, relatively to other predictors, is incompletely known. We assessed performances of electroencephalography during and after targeted temperature management toward good and poor outcomes, along with other recognized predictors. Cohort study (April 2009 to March 2016). Two academic hospitals (Centre Hospitalier Universitaire Vaudois, Lausanne, Switzerland; Mayo Clinic, Rochester, MN). Consecutive comatose adults admitted after cardiac arrest, identified through prospective registries. All patients were managed with targeted temperature management, receiving prespecified standardized clinical, neurophysiologic (particularly, electroencephalography during and after targeted temperature management), and biochemical evaluations. We assessed electroencephalography variables (reactivity, continuity, epileptiform features, and prespecified "benign" or "highly malignant" patterns based on the American Clinical Neurophysiology Society nomenclature) and other clinical, neurophysiologic (somatosensory-evoked potential), and biochemical prognosticators. Good outcome (Cerebral Performance Categories 1 and 2) and mortality predictions at 3 months were calculated. Among 357 patients, early electroencephalography reactivity and continuity and flexor or better motor reaction had greater than 70% positive predictive value for good outcome; reactivity (80.4%; 95% CI, 75.9-84.4%) and motor response (80.1%; 95% CI, 75.6-84.1%) had highest accuracy. Early benign electroencephalography heralded good outcome in 86.2% (95% CI, 79.8-91.1%). False positive rates for mortality were less than 5% for epileptiform or nonreactive early electroencephalography, nonreactive late electroencephalography, absent somatosensory-evoked potential, absent pupillary or corneal reflexes, presence of myoclonus, and neuron-specific enolase greater than 75 µg/L; accuracy was highest for

Predicting Defects Using Information Intelligence Process Models in the Software Technology Project.

Science.gov (United States)

Selvaraj, Manjula Gandhi; Jayabal, Devi Shree; Srinivasan, Thenmozhi; Balasubramanie, Palanisamy

2015-01-01

A key differentiator in a competitive market place is customer satisfaction. As per Gartner 2012 report, only 75%-80% of IT projects are successful. Customer satisfaction should be considered as a part of business strategy. The associated project parameters should be proactively managed and the project outcome needs to be predicted by a technical manager. There is lot of focus on the end state and on minimizing defect leakage as much as possible. Focus should be on proactively managing and shifting left in the software life cycle engineering model. Identify the problem upfront in the project cycle and do not wait for lessons to be learnt and take reactive steps. This paper gives the practical applicability of using predictive models and illustrates use of these models in a project to predict system testing defects thus helping to reduce residual defects.

Pediatric extracorporeal shock wave lithotripsy: Predicting successful outcomes

Directory of Open Access Journals (Sweden)

Sean McAdams

2010-01-01

Full Text Available Extracorporeal shock wave lithotripsy (ESWL is currently a first-line procedure of most upper urinary tract stones <2 cm of size because of established success rates, its minimal invasiveness and long-term safety with minimal complications. Given that alternative surgical and endourological options exist for the management of stone disease and that ESWL failure often results in the need for repeat ESWL or secondary procedures, it is highly desirable to identify variables predicting successful outcomes of ESWL in the pediatric population. Despite numerous reports and growing experience, few prospective studies and guidelines for pediatric ESWL have been completed. Variation in the methods by which study parameters are measured and reported can make it difficult to compare individual studies or make definitive recommendations. There is ongoing work and a need for continuing improvement of imaging protocols in children with renal colic, with a current focus on minimizing exposure to ionizing radiation, perhaps utilizing advancements in ultrasound and magnetic resonance imaging. This report provides a review of the current literature evaluating the patient attributes and stone factors that may be predictive of successful ESWL outcomes along with reviewing the role of pre-operative imaging and considerations for patient safety.

Hadamard Kernel SVM with applications for breast cancer outcome predictions.

Science.gov (United States)

Jiang, Hao; Ching, Wai-Ki; Cheung, Wai-Shun; Hou, Wenpin; Yin, Hong

2017-12-21

Breast cancer is one of the leading causes of deaths for women. It is of great necessity to develop effective methods for breast cancer detection and diagnosis. Recent studies have focused on gene-based signatures for outcome predictions. Kernel SVM for its discriminative power in dealing with small sample pattern recognition problems has attracted a lot attention. But how to select or construct an appropriate kernel for a specified problem still needs further investigation. Here we propose a novel kernel (Hadamard Kernel) in conjunction with Support Vector Machines (SVMs) to address the problem of breast cancer outcome prediction using gene expression data. Hadamard Kernel outperform the classical kernels and correlation kernel in terms of Area under the ROC Curve (AUC) values where a number of real-world data sets are adopted to test the performance of different methods. Hadamard Kernel SVM is effective for breast cancer predictions, either in terms of prognosis or diagnosis. It may benefit patients by guiding therapeutic options. Apart from that, it would be a valuable addition to the current SVM kernel families. We hope it will contribute to the wider biology and related communities.

Leptomeningeal collateral status predicts outcome after middle cerebral artery occlusion

DEFF Research Database (Denmark)

Madelung, Christopher Fugl; Ovesen, C; Trampedach, C

2017-01-01

NCCT and according to European Cooperative Acute Stroke Study (ECASS) criteria. Modified Rankin Scale score was assessed at 90 days, and mortality at 1 year. RESULTS: At 90 days, median (IQR) modified Rankin Scale score in patients with poor collateral status was 4 (3-6) compared to 2 (1-4) in patients...... population (P = .001). CONCLUSIONS: Leptomeningeal collateral status predicts functional outcome, mortality, and hemorrhagic transformation following middle cerebral artery occlusion.......OBJECTIVES: Perfusion through leptomeningeal collateral vessels is a likely pivotal factor in the outcome of stroke patients. We aimed to investigate the effect of collateral status on outcome in a cohort of unselected, consecutive stroke patients with middle cerebral artery occlusion undergoing...

Validation of a Dutch risk score predicting poor outcome in adults with bacterial meningitis in Vietnam and Malawi.

Directory of Open Access Journals (Sweden)

Ewout S Schut

Full Text Available We have previously developed and validated a prognostic model to predict the risk for unfavorable outcome in Dutch adults with bacterial meningitis. The aim of the current study was to validate this model in adults with bacterial meningitis from two developing countries, Vietnam and Malawi. Demographic and clinical characteristics of Vietnamese (n = 426, Malawian patients (n = 465 differed substantially from those of Dutch patients (n = 696. The Dutch model underestimated the risk of poor outcome in both Malawi and Vietnam. The discrimination of the original model (c-statistic [c] 0.84; 95% confidence interval 0.81 to 0.86 fell considerably when re-estimated in the Vietnam cohort (c = 0.70 or in the Malawian cohort (c = 0.68. Our validation study shows that new prognostic models have to be developed for these countries in a sufficiently large series of unselected patients.

How to diagnose rheumatoid arthritis early: a prediction model for persistent (erosive) arthritis

NARCIS (Netherlands)

Visser, Henk; le Cessie, Saskia; Vos, Koen; Breedveld, Ferdinand C.; Hazes, Johanna M. W.

2002-01-01

To develop a clinical model for the prediction, at the first visit, of 3 forms of arthritis outcome: self-limiting, persistent nonerosive, and persistent erosive arthritis. A standardized diagnostic evaluation was performed on 524 consecutive, newly referred patients with early arthritis.

Modeling the economic outcomes of immuno-oncology drugs: alternative model frameworks to capture clinical outcomes

Directory of Open Access Journals (Sweden)

Gibson EJ

2018-03-01

Full Text Available EJ Gibson,1 N Begum,1 I Koblbauer,1 G Dranitsaris,2 D Liew,3 P McEwan,4 AA Tahami Monfared,5,6 Y Yuan,7 A Juarez-Garcia,7 D Tyas,8 M Lees9 1Wickenstones Ltd, Didcot, UK; 2Augmentium Pharma Consulting Inc, Toronto, ON, Canada; 3Department of Epidemiology and Preventive Medicine, Alfred Hospital, Monash University, Melbourne, VIC, Australia; 4Health Economics and Outcomes Research Ltd, Cardiff, UK; 5Bristol-Myers Squibb Canada, Saint-Laurent, QC Canada; 6Department of Epidemiology, Biostatistics, and Occupational Health, McGill University, Montreal, QC, Canada; 7Bristol-Myers Squibb, Princeton, NJ, USA; 8Bristol-Myers Squibb, Uxbridge, UK; 9Bristol-Myers Squibb, Rueil-Malmaison, France Background: Economic models in oncology are commonly based on the three-state partitioned survival model (PSM distinguishing between progression-free and progressive states. However, the heterogeneity of responses observed in immuno-oncology (I-O suggests that new approaches may be appropriate to reflect disease dynamics meaningfully. Materials and methods: This study explored the impact of incorporating immune-specific health states into economic models of I-O therapy. Two variants of the PSM and a Markov model were populated with data from one clinical trial in metastatic melanoma patients. Short-term modeled outcomes were benchmarked to the clinical trial data and a lifetime model horizon provided estimates of life years and quality adjusted life years (QALYs. Results: The PSM-based models produced short-term outcomes closely matching the trial outcomes. Adding health states generated increased QALYs while providing a more granular representation of outcomes for decision making. The Markov model gave the greatest level of detail on outcomes but gave short-term results which diverged from those of the trial (overstating year 1 progression-free survival by around 60%. Conclusion: Increased sophistication in the representation of disease dynamics in economic models

Machine Learning Approaches for Predicting Radiation Therapy Outcomes: A Clinician's Perspective.

Science.gov (United States)

Kang, John; Schwartz, Russell; Flickinger, John; Beriwal, Sushil

2015-12-01

Radiation oncology has always been deeply rooted in modeling, from the early days of isoeffect curves to the contemporary Quantitative Analysis of Normal Tissue Effects in the Clinic (QUANTEC) initiative. In recent years, medical modeling for both prognostic and therapeutic purposes has exploded thanks to increasing availability of electronic data and genomics. One promising direction that medical modeling is moving toward is adopting the same machine learning methods used by companies such as Google and Facebook to combat disease. Broadly defined, machine learning is a branch of computer science that deals with making predictions from complex data through statistical models. These methods serve to uncover patterns in data and are actively used in areas such as speech recognition, handwriting recognition, face recognition, "spam" filtering (junk email), and targeted advertising. Although multiple radiation oncology research groups have shown the value of applied machine learning (ML), clinical adoption has been slow due to the high barrier to understanding these complex models by clinicians. Here, we present a review of the use of ML to predict radiation therapy outcomes from the clinician's point of view with the hope that it lowers the "barrier to entry" for those without formal training in ML. We begin by describing 7 principles that one should consider when evaluating (or creating) an ML model in radiation oncology. We next introduce 3 popular ML methods--logistic regression (LR), support vector machine (SVM), and artificial neural network (ANN)--and critique 3 seminal papers in the context of these principles. Although current studies are in exploratory stages, the overall methodology has progressively matured, and the field is ready for larger-scale further investigation. Copyright © 2015 Elsevier Inc. All rights reserved.

Prediction of treatment outcomes to exercise in patients with nonremitted major depressive disorder.

Science.gov (United States)

Rethorst, Chad D; South, Charles C; Rush, A John; Greer, Tracy L; Trivedi, Madhukar H

2017-12-01

Only one-third of patients with major depressive disorder (MDD) achieve remission with initial treatment. Consequently, current clinical practice relies on a "trial-and-error" approach to identify an effective treatment for each patient. The purpose of this report was to determine whether we could identify a set of clinical and biological parameters with potential clinical utility for prescription of exercise for treatment of MDD in a secondary analysis of the Treatment with Exercise Augmentation in Depression (TREAD) trial. Participants with nonremitted MDD were randomized to one of two exercise doses for 12 weeks. Participants were categorized as "remitters" (≤12 on the IDS-C), nonresponders (drop in IDS-C), or neither. The least absolute shrinkage and selection operator (LASSO) and random forests were used to evaluate 30 variables as predictors of both remission and nonresponse. Predictors were used to model treatment outcomes using logistic regression. Of the 122 participants, 36 were categorized as remitters (29.5%), 56 as nonresponders (45.9%), and 30 as neither (24.6%). Predictors of remission were higher levels of brain-derived neurotrophic factor (BDNF) and IL-1B, greater depressive symptom severity, and higher postexercise positive affect. Predictors of treatment nonresponse were low cardiorespiratory fitness, lower levels of IL-6 and BDNF, and lower postexercise positive affect. Models including these predictors resulted in predictive values greater than 70% (true predicted remitters/all predicted remitters) with specificities greater than 25% (true predicted remitters/all remitters). Results indicate feasibility in identifying patients who will either remit or not respond to exercise as a treatment for MDD utilizing a clinical decision model that incorporates multiple patient characteristics. © 2017 Wiley Periodicals, Inc.

Early EEG for outcome prediction of postanoxic coma: prospective cohort study with cost-minimization analysis.

Science.gov (United States)

Sondag, Lotte; Ruijter, Barry J; Tjepkema-Cloostermans, Marleen C; Beishuizen, Albertus; Bosch, Frank H; van Til, Janine A; van Putten, Michel J A M; Hofmeijer, Jeannette

2017-05-15

We recently showed that electroencephalography (EEG) patterns within the first 24 hours robustly contribute to multimodal prediction of poor or good neurological outcome of comatose patients after cardiac arrest. Here, we confirm these results and present a cost-minimization analysis. Early prognosis contributes to communication between doctors and family, and may prevent inappropriate treatment. A prospective cohort study including 430 subsequent comatose patients after cardiac arrest was conducted at intensive care units of two teaching hospitals. Continuous EEG was started within 12 hours after cardiac arrest and continued up to 3 days. EEG patterns were visually classified as unfavorable (isoelectric, low-voltage, or burst suppression with identical bursts) or favorable (continuous patterns) at 12 and 24 hours after cardiac arrest. Outcome at 6 months was classified as good (cerebral performance category (CPC) 1 or 2) or poor (CPC 3, 4, or 5). Predictive values of EEG measures and cost-consequences from a hospital perspective were investigated, assuming EEG-based decision- making about withdrawal of life-sustaining treatment in the case of a poor predicted outcome. Poor outcome occurred in 197 patients (51% of those included in the analyses). Unfavorable EEG patterns at 24 hours predicted a poor outcome with specificity of 100% (95% CI 98-100%) and sensitivity of 29% (95% CI 22-36%). Favorable patterns at 12 hours predicted good outcome with specificity of 88% (95% CI 81-93%) and sensitivity of 51% (95% CI 42-60%). Treatment withdrawal based on an unfavorable EEG pattern at 24 hours resulted in a reduced mean ICU length of stay without increased mortality in the long term. This gave small cost reductions, depending on the timing of withdrawal. Early EEG contributes to reliable prediction of good or poor outcome of postanoxic coma and may lead to reduced length of ICU stay. In turn, this may bring small cost reductions.

The use of presurgical psychological screening to predict the outcome of spine surgery.

Science.gov (United States)

Block, A R; Ohnmeiss, D D; Guyer, R D; Rashbaum, R F; Hochschuler, S H

2001-01-01

Several previous studies have shown that psychosocial factors can influence the outcome of elective spine surgery. The purpose of the current study was to determine how well a presurgical screening instrument could predict surgical outcome. The study was conducted by staff of a psychologist's office. They performed preoperative screening for spine surgery candidates and collected the follow-up data. Presurgical screening and follow-up data collection was performed on 204 patients who underwent laminectomy/discectomy (n=118) or fusion (n=86) of the lumbar spine. The outcome measures used in the study were visual analog pain scales, the Oswestry Disability Questionnaire, and medication use. A semi-structured interview and psychometric testing were used to identify specific, quantifiable psychological, and "medical" risk factors for poor surgical outcome. A presurgical psychological screening (PPS) scorecard was completed for each patient, assessing whether the patient had a high or low level of risk on these psychological and medical dimensions. Based on the scorecard, an overall surgical prognosis of "good," "fair," or "poor" was generated. Results showed spine surgery led to significant overall improvements in pain, functional ability, and medication use. Medical and psychological risk levels were significantly related to outcome, with the poorest results obtained by patients having both high psychological and medical risk. Further, the accuracy of PPS surgical prognosis in predicting overall outcome was 82%. Only 9 of 53 patients predicted to have poor outcome achieved fair or good results from spine surgery. These findings suggest that PPS should become a more routine part of the evaluation of chronic pain patients in whom spine surgery is being considered.

A comparison of the Full Outline of UnResponsiveness (FOUR) score and Glasgow Coma Score (GCS) in predictive modelling in traumatic brain injury.

Science.gov (United States)

Kasprowicz, Magdalena; Burzynska, Malgorzata; Melcer, Tomasz; Kübler, Andrzej

2016-01-01

To compare the performance of multivariate predictive models incorporating either the Full Outline of UnResponsiveness (FOUR) score or Glasgow Coma Score (GCS) in order to test whether substituting GCS with the FOUR score in predictive models for outcome in patients after TBI is beneficial. A total of 162 TBI patients were prospectively enrolled in the study. Stepwise logistic regression analysis was conducted to compare the prediction of (1) in-ICU mortality and (2) unfavourable outcome at 3 months post-injury using as predictors either the FOUR score or GCS along with other factors that may affect patient outcome. The areas under the ROC curves (AUCs) were used to compare the discriminant ability and predictive power of the models. The internal validation was performed with bootstrap technique and expressed as accuracy rate (AcR). The FOUR score, age, the CT Rotterdam score, systolic ABP and being placed on ventilator within day one (model 1: AUC: 0.906 ± 0.024; AcR: 80.3 ± 4.8%) performed equally well in predicting in-ICU mortality as the combination of GCS with the same set of predictors plus pupil reactivity (model 2: AUC: 0.913 ± 0.022; AcR: 81.1 ± 4.8%). The CT Rotterdam score, age and either the FOUR score (model 3) or GCS (model 4) equally well predicted unfavourable outcome at 3 months post-injury (AUC: 0.852 ± 0.037 vs. 0.866 ± 0.034; AcR: 72.3 ± 6.6% vs. 71.9%±6.6%, respectively). Adding the FOUR score or GCS at discharge from ICU to predictive models for unfavourable outcome increased significantly their performances (AUC: 0.895 ± 0.029, p = 0.05; AcR: 76.1 ± 6.5%; p model 3; and AUC: 0.918 ± 0.025, p model 4), but there was no benefit from substituting GCS with the FOUR score. Results showed that FOUR score and GCS perform equally well in multivariate predictive modelling in TBI.

Predictability and Prediction for an Experimental Cultural Market

Science.gov (United States)

Colbaugh, Richard; Glass, Kristin; Ormerod, Paul

Individuals are often influenced by the behavior of others, for instance because they wish to obtain the benefits of coordinated actions or infer otherwise inaccessible information. In such situations this social influence decreases the ex ante predictability of the ensuing social dynamics. We claim that, interestingly, these same social forces can increase the extent to which the outcome of a social process can be predicted very early in the process. This paper explores this claim through a theoretical and empirical analysis of the experimental music market described and analyzed in [1]. We propose a very simple model for this music market, assess the predictability of market outcomes through formal analysis of the model, and use insights derived through this analysis to develop algorithms for predicting market share winners, and their ultimate market shares, in the very early stages of the market. The utility of these predictive algorithms is illustrated through analysis of the experimental music market data sets [2].

Predicting outcome in term neonates with hypoxic-ischaemic encephalopathy using simplified MR criteria

International Nuclear Information System (INIS)

Jyoti, Rajeev; O'Neil, Ross

2006-01-01

MRI is an established investigation in the evaluation of neonates with suspected hypoxic-ischaemic encephalopathy (HIE). However, its role as a predictor of neurodevelopmental outcome remains complex. To establish reproducible simplified MR criteria and evaluate their role in predicting neurodevelopmental outcome in term neonates with HIE. Term neonates with suspected HIE had MRI at 7-10 days of age. MR scans were interpreted according to new simplified criteria by two radiologists blinded to the clinical course and outcome. The new simplified criteria allocated grade 1 to cases with no central and less than 10% peripheral change, grade 2 to those with less than 30% central and/or 10-30% peripheral area change, and grade 3 to those with more than 30% central or peripheral change. MRI changes were compared with clinical neurodevelopmental outcome evaluated prospectively at 1 year of age. Neurodevelopmental outcome was based upon the DQ score (revised Griffith's) and cerebral palsy on neurological assessment. Of 20 subjects, all those showing severe (grade 3) MR changes (35%) died or had poor neurodevelopmental outcome. Subjects with a normal MR scan or with scans showing only mild (grade 1) MR changes (55%) had normal outcomes. One subject showing moderate (grade 2) changes on MRI had a moderate outcome (5%), while another had an atypical pattern of MR changes with a normal outcome (5%). Assessment of full-term neonates with suspected HIE using the simplified MR criteria is highly predictive of neurodevelopmental outcome. (orig.)

Predicting outcome in term neonates with hypoxic-ischaemic encephalopathy using simplified MR criteria

Energy Technology Data Exchange (ETDEWEB)

Jyoti, Rajeev; O' Neil, Ross [Canberra Hospital, Medical Imaging, Canberra, ACT (Australia)

2006-01-01

MRI is an established investigation in the evaluation of neonates with suspected hypoxic-ischaemic encephalopathy (HIE). However, its role as a predictor of neurodevelopmental outcome remains complex. To establish reproducible simplified MR criteria and evaluate their role in predicting neurodevelopmental outcome in term neonates with HIE. Term neonates with suspected HIE had MRI at 7-10 days of age. MR scans were interpreted according to new simplified criteria by two radiologists blinded to the clinical course and outcome. The new simplified criteria allocated grade 1 to cases with no central and less than 10% peripheral change, grade 2 to those with less than 30% central and/or 10-30% peripheral area change, and grade 3 to those with more than 30% central or peripheral change. MRI changes were compared with clinical neurodevelopmental outcome evaluated prospectively at 1 year of age. Neurodevelopmental outcome was based upon the DQ score (revised Griffith's) and cerebral palsy on neurological assessment. Of 20 subjects, all those showing severe (grade 3) MR changes (35%) died or had poor neurodevelopmental outcome. Subjects with a normal MR scan or with scans showing only mild (grade 1) MR changes (55%) had normal outcomes. One subject showing moderate (grade 2) changes on MRI had a moderate outcome (5%), while another had an atypical pattern of MR changes with a normal outcome (5%). Assessment of full-term neonates with suspected HIE using the simplified MR criteria is highly predictive of neurodevelopmental outcome. (orig.)

Gambling and the Reasoned Action Model: Predicting Past Behavior, Intentions, and Future Behavior.

Science.gov (United States)

Dahl, Ethan; Tagler, Michael J; Hohman, Zachary P

2018-03-01

Gambling is a serious concern for society because it is highly addictive and is associated with a myriad of negative outcomes. The current study applied the Reasoned Action Model (RAM) to understand and predict gambling intentions and behavior. Although prior studies have taken a reasoned action approach to understand gambling, no prior study has fully applied the RAM or used the RAM to predict future gambling. Across two studies the RAM was used to predict intentions to gamble, past gambling behavior, and future gambling behavior. In study 1 the model significantly predicted intentions and past behavior in both a college student and Amazon Mechanical Turk sample. In study 2 the model predicted future gambling behavior, measured 2 weeks after initial measurement of the RAM constructs. This study stands as the first to show the utility of the RAM in predicting future gambling behavior. Across both studies, attitudes and perceived normative pressure were the strongest predictors of intentions to gamble. These findings provide increased understanding of gambling and inform the development of gambling interventions based on the RAM.

Non-invasive prediction of catheter ablation outcome in persistent atrial fibrillation by fibrillatory wave amplitude computation in multiple electrocardiogram leads.

Science.gov (United States)

Zarzoso, Vicente; Latcu, Decebal G; Hidalgo-Muñoz, Antonio R; Meo, Marianna; Meste, Olivier; Popescu, Irina; Saoudi, Nadir

2016-12-01

Catheter ablation (CA) of persistent atrial fibrillation (AF) is challenging, and reported results are capable of improvement. A better patient selection for the procedure could enhance its success rate while avoiding the risks associated with ablation, especially for patients with low odds of favorable outcome. CA outcome can be predicted non-invasively by atrial fibrillatory wave (f-wave) amplitude, but previous works focused mostly on manual measures in single electrocardiogram (ECG) leads only. To assess the long-term prediction ability of f-wave amplitude when computed in multiple ECG leads. Sixty-two patients with persistent AF (52 men; mean age 61.5±10.4years) referred for CA were enrolled. A standard 1-minute 12-lead ECG was acquired before the ablation procedure for each patient. F-wave amplitudes in different ECG leads were computed by a non-invasive signal processing algorithm, and combined into a mutivariate prediction model based on logistic regression. During an average follow-up of 13.9±8.3months, 47 patients had no AF recurrence after ablation. A lead selection approach relying on the Wald index pointed to I, V1, V2 and V5 as the most relevant ECG leads to predict jointly CA outcome using f-wave amplitudes, reaching an area under the curve of 0.854, and improving on single-lead amplitude-based predictors. Analysing the f-wave amplitude in several ECG leads simultaneously can significantly improve CA long-term outcome prediction in persistent AF compared with predictors based on single-lead measures. Copyright © 2016 Elsevier Masson SAS. All rights reserved.

Poor outcome prediction by burst suppression ratio in adults with post-anoxic coma without hypothermia.

Science.gov (United States)

Yang, Qinglin; Su, Yingying; Hussain, Mohammed; Chen, Weibi; Ye, Hong; Gao, Daiquan; Tian, Fei

2014-05-01

Burst suppression ratio (BSR) is a quantitative electroencephalography (qEEG) parameter. The purpose of our study was to compare the accuracy of BSR when compared to other EEG parameters in predicting poor outcomes in adults who sustained post-anoxic coma while not being subjected to therapeutic hypothermia. EEG was registered and recorded at least once within 7 days of post-anoxic coma onset. Electrodes were placed according to the international 10-20 system, using a 16-channel layout. Each EEG expert scored raw EEG using a grading scale adapted from Young and scored amplitude-integrated electroencephalography tracings, in addition to obtaining qEEG parameters defined as BSR with a defined threshold. Glasgow outcome scales of 1 and 2 at 3 months, determined by two blinded neurologists, were defined as poor outcome. Sixty patients with Glasgow coma scale score of 8 or less after anoxic accident were included. The sensitivity (97.1%), specificity (73.3%), positive predictive value (82.5%), and negative prediction value (95.0%) of BSR in predicting poor outcome were higher than other EEG variables. BSR1 and BSR2 were reliable in predicting death (area under the curve > 0.8, P coma who do not undergo therapeutic hypothermia when compared to other qEEG parameters.

Predicting Outcome in Comatose Patients: The Role of EEG Reactivity to Quantifiable Electrical Stimuli

Directory of Open Access Journals (Sweden)

Gang Liu

2016-01-01

Full Text Available Objective. To test the value of quantifiable electrical stimuli as a reliable method to assess electroencephalogram reactivity (EEG-R for the early prognostication of outcome in comatose patients. Methods. EEG was recorded in consecutive adults in coma after cardiopulmonary resuscitation (CPR or stroke. EEG-R to standard electrical stimuli was tested. Each patient received a 3-month follow-up by the Glasgow-Pittsburgh cerebral performance categories (CPC or modified Rankin scale (mRS score. Results. Twenty-two patients met the inclusion criteria. In the CPR group, 6 of 7 patients with EEG-R had good outcomes (positive predictive value (PPV, 85.7% and 4 of 5 patients without EEG-R had poor outcomes (negative predictive value (NPV, 80%. The sensitivity and specificity were 85.7% and 80%, respectively. In the stroke group, 6 of 7 patients with EEG-R had good outcomes (PPV, 85.7%; all of the 3 patients without EEG-R had poor outcomes (NPV, 100%. The sensitivity and specificity were 100% and 75%, respectively. Of all patients, the presence of EEG-R showed 92.3% sensitivity, 77.7% specificity, 85.7% PPV, and 87.5% NPV. Conclusion. EEG-R to quantifiable electrical stimuli might be a good positive predictive factor for the prognosis of outcome in comatose patients after CPR or stroke.

Executive function processes predict mobility outcomes in older adults.

Science.gov (United States)

Gothe, Neha P; Fanning, Jason; Awick, Elizabeth; Chung, David; Wójcicki, Thomas R; Olson, Erin A; Mullen, Sean P; Voss, Michelle; Erickson, Kirk I; Kramer, Arthur F; McAuley, Edward

2014-02-01

To examine the relationship between performance on executive function measures and subsequent mobility outcomes in community-dwelling older adults. Randomized controlled clinical trial. Champaign-Urbana, Illinois. Community-dwelling older adults (N = 179; mean age 66.4). A 12-month exercise trial with two arms: an aerobic exercise group and a stretching and strengthening group. Established cognitive tests of executive function (flanker task, task switching, and a dual-task paradigm) and the Wisconsin card sort test. Mobility was assessed using the timed 8-foot up and go test and times to climb up and down a flight of stairs. Participants completed the cognitive tests at baseline and the mobility measures at baseline and after 12 months of the intervention. Multiple regression analyses were conducted to determine whether baseline executive function predicted postintervention functional performance after controlling for age, sex, education, cardiorespiratory fitness, and baseline mobility levels. Selective baseline executive function measurements, particularly performance on the flanker task (β = 0.15-0.17) and the Wisconsin card sort test (β = 0.11-0.16) consistently predicted mobility outcomes at 12 months. The estimates were in the expected direction, such that better baseline performance on the executive function measures predicted better performance on the timed mobility tests independent of intervention. Executive functions of inhibitory control, mental set shifting, and attentional flexibility were predictive of functional mobility. Given the literature associating mobility limitations with disability, morbidity, and mortality, these results are important for understanding the antecedents to poor mobility function that well-designed interventions to improve cognitive performance can attenuate. © 2014, Copyright the Authors Journal compilation © 2014, The American Geriatrics Society.

Prediction of extubation outcome in preterm infants by composite extubation indices.

Science.gov (United States)

Dimitriou, Gabriel; Fouzas, Sotirios; Vervenioti, Aggeliki; Tzifas, Sotirios; Mantagos, Stefanos

2011-11-01

To determine whether composite extubation indices can predict extubation outcome in preterm infants. Prospective observational study. Level III neonatal intensive care unit. Fifty-six preterm infants cared for in the neonatal intensive care unit of a tertiary teaching hospital during 2007 and 2008. None. The study consisted of two parts. In the first part, different extubation indices were evaluated in a group of 28 neonates (derivation group). These indices included the diaphragmatic pressure-time index, the respiratory muscle pressure-time index, the maximal transdiaphragmatic pressure, the maximal inspiratory pressure, the airway pressure generated 100 milliseconds after an occlusion/maximal transdiaphragmatic pressure ratio, the airway pressure generated 100 milliseconds after an occlusion/maximal inspiratory pressure ratio, the tidal volume, and the respiratory rate to tidal volume ratio. After exploratory analysis, the best performing indices and the optimal threshold values to predict extubation outcome were selected. In the second part of the study, these indices were validated at the predetermined threshold values in an additional group of 28 preterm neonates (validation group). Four infants (14.3%) in the derivation group and four in the validation group (14.3%) failed extubation. Receiver operator characteristic curve analysis revealed that a diaphragmatic pressure-time index of ≤0.12, a respiratory muscle pressure-time index ≤0.10, a airway pressure generated 100 milliseconds after an occlusion/maximal transdiaphragmatic pressure of ≤0.14, and a airway pressure generated 100 milliseconds after an occlusion/maximal inspiratory pressure of ≤0.09 were the most accurate predictors of extubation outcome in the derivation group. In the validation group, a diaphragmatic pressure-time index of ≤0.12 and a respiratory muscle pressure-time index of ≤0.10 both had zero false-positive results, predicting with accuracy successful extubation. Composite

Cluster analysis as a prediction tool for pregnancy outcomes.

Science.gov (United States)

Banjari, Ines; Kenjerić, Daniela; Šolić, Krešimir; Mandić, Milena L

2015-03-01

Considering specific physiology changes during gestation and thinking of pregnancy as a "critical window", classification of pregnant women at early pregnancy can be considered as crucial. The paper demonstrates the use of a method based on an approach from intelligent data mining, cluster analysis. Cluster analysis method is a statistical method which makes possible to group individuals based on sets of identifying variables. The method was chosen in order to determine possibility for classification of pregnant women at early pregnancy to analyze unknown correlations between different variables so that the certain outcomes could be predicted. 222 pregnant women from two general obstetric offices' were recruited. The main orient was set on characteristics of these pregnant women: their age, pre-pregnancy body mass index (BMI) and haemoglobin value. Cluster analysis gained a 94.1% classification accuracy rate with three branch- es or groups of pregnant women showing statistically significant correlations with pregnancy outcomes. The results are showing that pregnant women both of older age and higher pre-pregnancy BMI have a significantly higher incidence of delivering baby of higher birth weight but they gain significantly less weight during pregnancy. Their babies are also longer, and these women have significantly higher probability for complications during pregnancy (gestosis) and higher probability of induced or caesarean delivery. We can conclude that the cluster analysis method can appropriately classify pregnant women at early pregnancy to predict certain outcomes.

BIOMARKERS S100B AND NSE PREDICT OUTCOME IN HYPOTHERMIA-TREATED ENCEPHALOPATHIC NEWBORNS

Science.gov (United States)

Massaro, An N.; Chang, Taeun; Baumgart, Stephen; McCarter, Robert; Nelson, Karin B.; Glass, Penny

2014-01-01

Objective To evaluate if serum S100B protein and neuron specific enolase (NSE) measured during therapeutic hypothermia are predictive of neurodevelopmental outcome at 15 months in children with neonatal encephalopathy (NE). Design Prospective longitudinal cohort study Setting A level IV neonatal intensive care unit in a free-standing children’s hospital. Patients Term newborns with moderate to severe NE referred for therapeutic hypothermia during the study period. Interventions Serum NSE and S100B were measured at 0, 12, 24 and 72 hrs of hypothermia. Measurements and Main Reseults Of the 83 infants were enrolled, fifteen (18%) died in the newborn period. Survivors were evaluated by the Bayley Scales of Infant Development (BSID-II) at 15 months of age. Outcomes were assessed in 49/68 (72%) survivors at a mean age of 15.2±2.7 months. Neurodevelopmental outcome was classified by BSID-II Mental (MDI) and Psychomotor (PDI) Developmental Index scores, reflecting cognitive and motor outcomes respectively. Four-level outcome classifications were defined a priori: normal= MDI/PDI within 1SD (>85), mild= MDI/PDI <1SD (70–85), moderate/severe= MDI/PDI <2SD (<70), or died. Elevated serum S100B and NSE levels measured during hypothermia were associated with increasing outcome severity after controlling for baseline and soceioeconomic characteristics in ordinal regression models. Adjusted odds ratios for cognitive outcome were: S100B 2.5 (95% CI 1.3–4.8) and NSE 2.1 (1.2–3.6); for motor outcome: S100B 2.6 (1.2–5.6) and NSE 2.1 (1.2–3.6). Conclusions Serum S100B and NSE levels in babies with NE are associated with neurodevelopmental outcome at 15 months. These putative biomarkers of brain injury may help direct care during therapeutic hypothermia. PMID:24777302

Sputum biomarkers and the prediction of clinical outcomes in patients with cystic fibrosis.

Directory of Open Access Journals (Sweden)

Theodore G Liou

Full Text Available Lung function, acute pulmonary exacerbations (APE, and weight are the best clinical predictors of survival in cystic fibrosis (CF; however, underlying mechanisms are incompletely understood. Biomarkers of current disease state predictive of future outcomes might identify mechanisms and provide treatment targets, trial endpoints and objective clinical monitoring tools. Such CF-specific biomarkers have previously been elusive. Using observational and validation cohorts comprising 97 non-transplanted consecutively-recruited adult CF patients at the Intermountain Adult CF Center, University of Utah, we identified biomarkers informative of current disease and predictive of future clinical outcomes. Patients represented the majority of sputum producers. They were recruited March 2004-April 2007 and followed through May 2011. Sputum biomarker concentrations were measured and clinical outcomes meticulously recorded for a median 5.9 (interquartile range 5.0 to 6.6 years to study associations between biomarkers and future APE and time-to-lung transplantation or death. After multivariate modeling, only high mobility group box-1 protein (HMGB-1, mean=5.84 [log ng/ml], standard deviation [SD] =1.75 predicted time-to-first APE (hazard ratio [HR] per log-unit HMGB-1=1.56, p-value=0.005, number of future APE within 5 years (0.338 APE per log-unit HMGB-1, p<0.001 by quasi-Poisson regression and time-to-lung transplantation or death (HR=1.59, p=0.02. At APE onset, sputum granulocyte macrophage colony stimulating factor (GM-CSF, mean 4.8 [log pg/ml], SD=1.26 was significantly associated with APE-associated declines in lung function (-10.8 FEV(1% points per log-unit GM-CSF, p<0.001 by linear regression. Evaluation of validation cohorts produced similar results that passed tests of mutual consistency. In CF sputum, high HMGB-1 predicts incidence and recurrence of APE and survival, plausibly because it mediates long-term airway inflammation. High APE-associated GM

Predicting Social Anxiety Treatment Outcome based on Therapeutic Email Conversations

NARCIS (Netherlands)

Hoogendoorn, M.; Berger, Thomas; Schulz, Ava; Stolz, Timo; Szolovits, Peter

2016-01-01

Predicting therapeutic outcome in the mental health domain is of utmost importance to enable therapists to provide the most effective treatment to a patient. Using information from the writings of a patient can potentially be a valuable source of information, especially now that more and more

External Validation Study of First Trimester Obstetric Prediction Models (Expect Study I): Research Protocol and Population Characteristics.

Science.gov (United States)

Meertens, Linda Jacqueline Elisabeth; Scheepers, Hubertina Cj; De Vries, Raymond G; Dirksen, Carmen D; Korstjens, Irene; Mulder, Antonius Lm; Nieuwenhuijze, Marianne J; Nijhuis, Jan G; Spaanderman, Marc Ea; Smits, Luc Jm

2017-10-26

A number of first-trimester prediction models addressing important obstetric outcomes have been published. However, most models have not been externally validated. External validation is essential before implementing a prediction model in clinical practice. The objective of this paper is to describe the design of a study to externally validate existing first trimester obstetric prediction models, based upon maternal characteristics and standard measurements (eg, blood pressure), for the risk of pre-eclampsia (PE), gestational diabetes mellitus (GDM), spontaneous preterm birth (PTB), small-for-gestational-age (SGA) infants, and large-for-gestational-age (LGA) infants among Dutch pregnant women (Expect Study I). The results of a pilot study on the feasibility and acceptability of the recruitment process and the comprehensibility of the Pregnancy Questionnaire 1 are also reported. A multicenter prospective cohort study was performed in The Netherlands between July 1, 2013 and December 31, 2015. First trimester obstetric prediction models were systematically selected from the literature. Predictor variables were measured by the Web-based Pregnancy Questionnaire 1 and pregnancy outcomes were established using the Postpartum Questionnaire 1 and medical records. Information about maternal health-related quality of life, costs, and satisfaction with Dutch obstetric care was collected from a subsample of women. A pilot study was carried out before the official start of inclusion. External validity of the models will be evaluated by assessing discrimination and calibration. Based on the pilot study, minor improvements were made to the recruitment process and online Pregnancy Questionnaire 1. The validation cohort consists of 2614 women. Data analysis of the external validation study is in progress. This study will offer insight into the generalizability of existing, non-invasive first trimester prediction models for various obstetric outcomes in a Dutch obstetric population

Synchrony-desynchrony in the tripartite model of fear: Predicting treatment outcome in clinically phobic children.

Science.gov (United States)

Benoit Allen, Kristy; Allen, Ben; Austin, Kristin E; Waldron, Jonathan C; Ollendick, Thomas H

2015-08-01

The tripartite model of fear posits that the fear response entails three loosely coupled components: subjective distress, behavioral avoidance, and physiological arousal. The concept of synchrony vs. desynchrony describes the degree to which changes in the activation of these components vary together (synchrony), independently, or inversely (both forms of desynchrony) over time. The present study assessed synchrony-desynchrony and its relationship to treatment outcome in a sample of 98 children with specific phobias both prior to and 1 week after receiving one-session treatment, a 3 h cognitive-behavioral intervention. The results suggest an overall pattern of desynchronous change whereby youth improved on behavioral avoidance and subjective distress following treatment, but their level of cardiovascular reactivity remained stable. However, we found evidence that synchronous change on the behavioral avoidance and subjective distress components was related to better treatment outcome, whereas desynchronous change on these components was related to poorer treatment outcome. These findings suggest that a fuller understanding of the three response systems and their interrelations in phobic youth may assist us in the assessment and treatment of these disorders, potentially leading to a more person-centered approach and eventually to enhanced treatment outcomes. Copyright © 2015 Elsevier Ltd. All rights reserved.

A simple score to predict fetal outcomes in gestational diabetes mellitus

Directory of Open Access Journals (Sweden)

Kushal Naha

2015-04-01

Full Text Available Background: Strict glycemic control is critical in preventing adverse maternal and fetal outcomes with gestational diabetes mellitus (GDM, but frequently results in recurrent maternal hypoglycemia and is often impracticable. This study was done to determine whether a more lenient strategy might provide satisfactory outcomes and to formulate a glycemic score for prognostication of fetal outcomes. Methods: A prospective non-interventional study was conducted on consecutive patients admitted with GDM between May 2007 and August 2009. Patients with pre-gestational diabetes were excluded. All patients received treatment at the discretion of treating consultants. Glycemic control was estimated by recording mean values of all glucose profiles performed. Fasting and postprandial blood glucose levels below 95 mg/dl and 120 mg/dl, respectively, were considered controlled. A glycemic score was calculated based on the number of mean blood glucose values controlled. Fetal outcomes were noted. Results: Ninety-four patients with GDM were included. The glycemic score was significantly predictive of adverse fetal outcomes (p < 0.001. Analysis by receiver operating characteristic (ROC curve showed good sensitivity and specificity for macrosomia (78.3% and 81.8%, respectively and congenital anomalies (73.9% and 66.7%, respectively with a glycemic score of 2 or less [area under curve (AUC 0.768; odds ratio (OR, 11.17; 95% Confidence Interval (CI, 2.58-48.35; p < 0.001; and AUC 0.765; OR, 2.22; 95% CI, 0.71-6.92; p = 0.055, respectively]. Binomial logistic regression confirmed the glycemic score to be independently predictive of fetal outcome (p = 0.015. Conclusion: The glycemic score is a sensitive and specific prognostic marker. Tight control of three of four values of blood glucose within the glucose profile appears sufficient to prevent adverse fetal outcomes.

Magnetic resonance imaging-detected tumor response for locally advanced rectal cancer predicts survival outcomes: MERCURY experience.

Science.gov (United States)

Patel, Uday B; Taylor, Fiona; Blomqvist, Lennart; George, Christopher; Evans, Hywel; Tekkis, Paris; Quirke, Philip; Sebag-Montefiore, David; Moran, Brendan; Heald, Richard; Guthrie, Ashley; Bees, Nicola; Swift, Ian; Pennert, Kjell; Brown, Gina

2011-10-01

To assess magnetic resonance imaging (MRI) and pathologic staging after neoadjuvant therapy for rectal cancer in a prospectively enrolled, multicenter study. In a prospective cohort study, 111 patients who had rectal cancer treated by neoadjuvant therapy were assessed for response by MRI and pathology staging by T, N and circumferential resection margin (CRM) status. Tumor regression grade (TRG) was also assessed by MRI. Overall survival (OS) was estimated by using the Kaplan-Meier product-limit method, and Cox proportional hazards models were used to determine associations between staging of good and poor responders on MRI or pathology and survival outcomes after controlling for patient characteristics. On multivariate analysis, the MRI-assessed TRG (mrTRG) hazard ratios (HRs) were independently significant for survival (HR, 4.40; 95% CI, 1.65 to 11.7) and disease-free survival (DFS; HR, 3.28; 95% CI, 1.22 to 8.80). Five-year survival for poor mrTRG was 27% versus 72% (P = .001), and DFS for poor mrTRG was 31% versus 64% (P = .007). Preoperative MRI-predicted CRM independently predicted local recurrence (LR; HR, 4.25; 95% CI, 1.45 to 12.51). Five-year survival for poor post-treatment pathologic T stage (ypT) was 39% versus 76% (P = .001); DFS for the same was 38% versus 84% (P = .001); and LR for the same was 27% versus 6% (P = .018). The 5-year survival for involved pCRM was 30% versus 59% (P = .001); DFS, 28 versus 62% (P = .02); and LR, 56% versus 10% (P = .001). Pathology node status did not predict outcomes. MRI assessment of TRG and CRM are imaging markers that predict survival outcomes for good and poor responders and provide an opportunity for the multidisciplinary team to offer additional treatment options before planning definitive surgery. Postoperative histopathology assessment of ypT and CRM but not post-treatment N status were important postsurgical predictors of outcome.

Candidate Prediction Models and Methods

DEFF Research Database (Denmark)

Nielsen, Henrik Aalborg; Nielsen, Torben Skov; Madsen, Henrik

2005-01-01

This document lists candidate prediction models for Work Package 3 (WP3) of the PSO-project called ``Intelligent wind power prediction systems'' (FU4101). The main focus is on the models transforming numerical weather predictions into predictions of power production. The document also outlines...... the possibilities w.r.t. different numerical weather predictions actually available to the project....

Web-based tool for dynamic functional outcome after acute ischemic stroke and comparison with existing models.

Science.gov (United States)

Ji, Ruijun; Du, Wanliang; Shen, Haipeng; Pan, Yuesong; Wang, Penglian; Liu, Gaifen; Wang, Yilong; Li, Hao; Zhao, Xingquan; Wang, Yongjun

2014-11-25

Acute ischemic stroke (AIS) is one of the leading causes of death and adult disability worldwide. In the present study, we aimed to develop a web-based risk model for predicting dynamic functional status at discharge, 3-month, 6-month, and 1-year after acute ischemic stroke (Dynamic Functional Status after Acute Ischemic Stroke, DFS-AIS). The DFS-AIS was developed based on the China National Stroke Registry (CNSR), in which eligible patients were randomly divided into derivation (60%) and validation (40%) cohorts. Good functional outcome was defined as modified Rankin Scale (mRS) score ≤ 2 at discharge, 3-month, 6-month, and 1-year after AIS, respectively. Independent predictors of each outcome measure were obtained using multivariable logistic regression. The area under the receiver operating characteristic curve (AUROC) and plot of observed and predicted risk were used to assess model discrimination and calibration. A total of 12,026 patients were included and the median age was 67 (interquartile range: 57-75). The proportion of patients with good functional outcome at discharge, 3-month, 6-month, and 1-year after AIS was 67.9%, 66.5%, 66.9% and 66.9%, respectively. Age, gender, medical history of diabetes mellitus, stroke or transient ischemic attack, current smoking and atrial fibrillation, pre-stroke dependence, pre-stroke statins using, admission National Institutes of Health Stroke Scale score, admission blood glucose were identified as independent predictors of functional outcome at different time points after AIS. The DFS-AIS was developed from sets of predictors of mRS ≤ 2 at different time points following AIS. The DFS-AIS demonstrated good discrimination in the derivation and validation cohorts (AUROC range: 0.837-0.845). Plots of observed versus predicted likelihood showed excellent calibration in the derivation and validation cohorts (all r = 0.99, P discrimination for good functional outcome and mortality at discharge, 3-month, 6

Evaluation of CROES Nephrolithometry Nomogram as a Preoperative Predictive System for Percutaneous Nephrolithotomy Outcomes.

Science.gov (United States)

Kumar, Sumit; Sreenivas, Jayaram; Karthikeyan, Vilvapathy Senguttuvan; Mallya, Ashwin; Keshavamurthy, Ramaiah

2016-10-01

Scoring systems have been devised to predict outcomes of percutaneous nephrolithotomy (PCNL). CROES nephrolithometry nomogram (CNN) is the latest tool devised to predict stone-free rate (SFR). We aim to compare predictive accuracy of CNN against Guy stone score (GSS) for SFR and postoperative outcomes. Between January 2013 and December 2015, 313 patients undergoing PCNL were analyzed for predictive accuracy of GSS, CNN, and stone burden (SB) for SFR, complications, operation time (OT), and length of hospitalization (LOH). We further stratified patients into risk groups based on CNN and GSS. Mean ± standard deviation (SD) SB was 298.8 ± 235.75 mm 2 . SB, GSS, and CNN (area under curve [AUC]: 0.662, 0.660, 0.673) were found to be predictors of SFR. However, predictability for complications was not as good (AUC: SB 0.583, GSS 0.554, CNN 0.580). Single implicated calix (Adj. OR 3.644; p = 0.027), absence of staghorn calculus (Adj. OR 3.091; p = 0.044), single stone (Adj. OR 3.855; p = 0.002), and single puncture (Adj. OR 2.309; p = 0.048) significantly predicted SFR on multivariate analysis. Charlson comorbidity index (CCI; p = 0.020) and staghorn calculus (p = 0.002) were independent predictors for complications on linear regression. SB and GSS independently predicted OT on multivariate analysis. SB and complications significantly predicted LOH, while GSS and CNN did not predict LOH. CNN offered better risk stratification for residual stones than GSS. CNN and GSS have good preoperative predictive accuracy for SFR. Number of implicated calices may affect SFR, and CCI affects complications. Studies should incorporate these factors in scoring systems and assess if predictability of PCNL outcomes improves.

Machine learning models in breast cancer survival prediction.

Science.gov (United States)

Montazeri, Mitra; Montazeri, Mohadeseh; Montazeri, Mahdieh; Beigzadeh, Amin

2016-01-01

Breast cancer is one of the most common cancers with a high mortality rate among women. With the early diagnosis of breast cancer survival will increase from 56% to more than 86%. Therefore, an accurate and reliable system is necessary for the early diagnosis of this cancer. The proposed model is the combination of rules and different machine learning techniques. Machine learning models can help physicians to reduce the number of false decisions. They try to exploit patterns and relationships among a large number of cases and predict the outcome of a disease using historical cases stored in datasets. The objective of this study is to propose a rule-based classification method with machine learning techniques for the prediction of different types of Breast cancer survival. We use a dataset with eight attributes that include the records of 900 patients in which 876 patients (97.3%) and 24 (2.7%) patients were females and males respectively. Naive Bayes (NB), Trees Random Forest (TRF), 1-Nearest Neighbor (1NN), AdaBoost (AD), Support Vector Machine (SVM), RBF Network (RBFN), and Multilayer Perceptron (MLP) machine learning techniques with 10-cross fold technique were used with the proposed model for the prediction of breast cancer survival. The performance of machine learning techniques were evaluated with accuracy, precision, sensitivity, specificity, and area under ROC curve. Out of 900 patients, 803 patients and 97 patients were alive and dead, respectively. In this study, Trees Random Forest (TRF) technique showed better results in comparison to other techniques (NB, 1NN, AD, SVM and RBFN, MLP). The accuracy, sensitivity and the area under ROC curve of TRF are 96%, 96%, 93%, respectively. However, 1NN machine learning technique provided poor performance (accuracy 91%, sensitivity 91% and area under ROC curve 78%). This study demonstrates that Trees Random Forest model (TRF) which is a rule-based classification model was the best model with the highest level of

Comparing predictive models of glioblastoma multiforme built using multi-institutional and local data sources.

Science.gov (United States)

Singleton, Kyle W; Hsu, William; Bui, Alex A T

2012-01-01

The growing amount of electronic data collected from patient care and clinical trials is motivating the creation of national repositories where multiple institutions share data about their patient cohorts. Such efforts aim to provide sufficient sample sizes for data mining and predictive modeling, ultimately improving treatment recommendations and patient outcome prediction. While these repositories offer the potential to improve our understanding of a disease, potential issues need to be addressed to ensure that multi-site data and resultant predictive models are useful to non-contributing institutions. In this paper we examine the challenges of utilizing National Cancer Institute datasets for modeling glioblastoma multiforme. We created several types of prognostic models and compared their results against models generated using data solely from our institution. While overall model performance between the data sources was similar, different variables were selected during model generation, suggesting that mapping data resources between models is not a straightforward issue.

The orbitofrontal oracle: cortical mechanisms for the prediction and evaluation of specific behavioral outcomes

Science.gov (United States)

Rudebeck, Peter H.; Murray, Elisabeth A.

2014-01-01

The orbitofrontal cortex (OFC) has long been associated with the flexible control of behavior and concepts such as behavioral inhibition, self-control and emotional regulation. These ideas emphasize the suppression of behaviors and emotions, but OFC’s affirmative functions have remained enigmatic. Here we review recent work that has advanced our understanding of this prefrontal area and how its functions are shaped through interaction with subcortical structures such as the amygdala. Recent findings have overturned theories emphasizing behavioral inhibition as OFC’s fundamental function. Instead, new findings indicate that OFC provides predictions about specific outcomes associated with stimuli, choices and actions, especially their moment-to-moment value based on current internal states. OFC function thereby encompasses a broad representation or model of an individual’s sensory milieu and potential actions, along with their relationship to likely behavioral outcomes. PMID:25521376

The orbitofrontal oracle: cortical mechanisms for the prediction and evaluation of specific behavioral outcomes.

Science.gov (United States)

Rudebeck, Peter H; Murray, Elisabeth A

2014-12-17

The orbitofrontal cortex (OFC) has long been associated with the flexible control of behavior and concepts such as behavioral inhibition, self-control, and emotional regulation. These ideas emphasize the suppression of behaviors and emotions, but OFC's affirmative functions have remained enigmatic. Here we review recent work that has advanced our understanding of this prefrontal area and how its functions are shaped through interaction with subcortical structures such as the amygdala. Recent findings have overturned theories emphasizing behavioral inhibition as OFC's fundamental function. Instead, new findings indicate that OFC provides predictions about specific outcomes associated with stimuli, choices, and actions, especially their moment-to-moment value based on current internal states. OFC function thereby encompasses a broad representation or model of an individual's sensory milieu and potential actions, along with their relationship to likely behavioral outcomes. Copyright © 2014 Elsevier Inc. All rights reserved.

Wind power prediction models

Science.gov (United States)

Levy, R.; Mcginness, H.

1976-01-01

Investigations were performed to predict the power available from the wind at the Goldstone, California, antenna site complex. The background for power prediction was derived from a statistical evaluation of available wind speed data records at this location and at nearby locations similarly situated within the Mojave desert. In addition to a model for power prediction over relatively long periods of time, an interim simulation model that produces sample wind speeds is described. The interim model furnishes uncorrelated sample speeds at hourly intervals that reproduce the statistical wind distribution at Goldstone. A stochastic simulation model to provide speed samples representative of both the statistical speed distributions and correlations is also discussed.

Development and external validation of a risk-prediction model to predict 5-year overall survival in advanced larynx cancer.

Science.gov (United States)

Petersen, Japke F; Stuiver, Martijn M; Timmermans, Adriana J; Chen, Amy; Zhang, Hongzhen; O'Neill, James P; Deady, Sandra; Vander Poorten, Vincent; Meulemans, Jeroen; Wennerberg, Johan; Skroder, Carl; Day, Andrew T; Koch, Wayne; van den Brekel, Michiel W M

2018-05-01

TNM-classification inadequately estimates patient-specific overall survival (OS). We aimed to improve this by developing a risk-prediction model for patients with advanced larynx cancer. Cohort study. We developed a risk prediction model to estimate the 5-year OS rate based on a cohort of 3,442 patients with T3T4N0N+M0 larynx cancer. The model was internally validated using bootstrapping samples and externally validated on patient data from five external centers (n = 770). The main outcome was performance of the model as tested by discrimination, calibration, and the ability to distinguish risk groups based on tertiles from the derivation dataset. The model performance was compared to a model based on T and N classification only. We included age, gender, T and N classification, and subsite as prognostic variables in the standard model. After external validation, the standard model had a significantly better fit than a model based on T and N classification alone (C statistic, 0.59 vs. 0.55, P statistic to 0.68. A risk prediction model for patients with advanced larynx cancer, consisting of readily available clinical variables, gives more accurate estimations of the estimated 5-year survival rate when compared to a model based on T and N classification alone. 2c. Laryngoscope, 128:1140-1145, 2018. © 2017 The American Laryngological, Rhinological and Otological Society, Inc.

Hemizona Assay and Sperm Penetration Assay in the Prediction of IVF Outcome: A Systematic Review

Directory of Open Access Journals (Sweden)

Paraskevi Vogiatzi

2013-01-01

Full Text Available The limited predictive value of semen analysis in achieving natural conception or in IVF outcome confirms the need for sperm function tests to determine optimal management. We reviewed HZA and SPA predictive power in IVF outcome, with statistical significance of diagnostic power of the assays. HZA was readily efficient in predicting IVF outcome, while evident inconsistency among the studies analysed framed the SPA’s role in male fertility evaluation. Considerable variation was noted in the diagnostic accuracy values of SPA with wide sensitivity (52–100%, specificity (0–100%, and PPV (18–100% and NPV (0–100% together with fluctuation and notable differentiation in methodology and cutoff values employed by each group. HZA methodology was overall consistent with minor variation in cutoff values and oocyte source, while data analysis reported strong correlation between HZA results with IVF outcome, high sensitivity (75–100%, good specificity (57–100%, and high PPV (79–100% and NPV (68–100%. HZA correlated well with IVF outcome and demonstrated better sensitivity/specificity and positive/negative predictive power. Males with normal or slightly abnormal semen profiles could benefit by this intervention and could be evaluated prior to referral to assisted reproduction. HZA should be used in a sequential fashion with semen analysis and potentially other bioassays in an IVF setting.

Could infarct location predict the long-term functional outcome in childhood arterial ischemic stroke?

Directory of Open Access Journals (Sweden)

Mauricio López-Espejo

Full Text Available ABSTRACT Objective: To explore the influence of infarct location on long-term functional outcome following a first-ever arterial ischemic stroke (AIS in non-neonate children. Method: The MRIs of 39 children with AIS (median age 5.38 years; 36% girls; mean follow-up time 5.87 years were prospectively evaluated. Infarct location was classified as the absence or presence of subcortical involvement. Functional outcome was measured using the modified Rankin scale (mRS for children after the follow-up assessment. We utilized multivariate logistic regression models to estimate the odds ratios (ORs for the outcome while adjusting for age, sex, infarct size and middle cerebral artery territory involvement (significance < 0.05. Results: Both infarcts ≥ 4% of total brain volume (OR 9.92; CI 1.76 – 55.9; p 0.009 and the presence of subcortical involvement (OR 8.36; CI 1.76 – 53.6; p 0.025 independently increased the risk of marked functional impairment (mRS 3 to 5. Conclusion: Infarct extension and location can help predict the extent of disability after childhood AIS.

Inverse and Predictive Modeling

Energy Technology Data Exchange (ETDEWEB)

Syracuse, Ellen Marie [Los Alamos National Lab. (LANL), Los Alamos, NM (United States)

2017-09-27

The LANL Seismo-Acoustic team has a strong capability in developing data-driven models that accurately predict a variety of observations. These models range from the simple – one-dimensional models that are constrained by a single dataset and can be used for quick and efficient predictions – to the complex – multidimensional models that are constrained by several types of data and result in more accurate predictions. Team members typically build models of geophysical characteristics of Earth and source distributions at scales of 1 to 1000s of km, the techniques used are applicable for other types of physical characteristics at an even greater range of scales. The following cases provide a snapshot of some of the modeling work done by the Seismo- Acoustic team at LANL.

Magnetic resonance imaging of injuries to the ankle joint: can it predict clinical outcome?

Science.gov (United States)

Zanetti, M; De Simoni, C; Wetz, H H; Zollinger, H; Hodler, J

1997-02-01

To predict clinical outcome after ankle sprains on the basis of magnetic resonance (MR) findings. Twenty-nine consecutive patients (mean age 32.9 years, range 13-60 years) were examined clinically and with MR imaging both after trauma and following standardized conservative therapy. Various MR abnormalities were related to a clinical outcome score. There was a tendency for a better clinical outcome in partial, rather than complete, tears of the anterior talofibular ligament and when there was no fluid within the peroneal tendon sheath at the initial MR examination (P = 0.092 for either abnormality). A number of other MR features did not significantly influence clinical outcome, including the presence of a calcaneofibular ligament lesion and a bone bruise of the talar dome. Clinical outcome after ankle sprain cannot consistently be predicted by MR imaging, although MR imaging may be more accurate when the anterior talofibular ligament is only partially torn and there are no signs of injury to the peroneal tendon sheath.

Systematic review of prognostic factors predicting outcome in non-surgically treated patients with sciatica.

Science.gov (United States)

Verwoerd, A J H; Luijsterburg, P A J; Lin, C W C; Jacobs, W C H; Koes, B W; Verhagen, A P

2013-09-01

Identification of prognostic factors for surgery in patients with sciatica is important to be able to predict surgery in an early stage. Identification of prognostic factors predicting persistent pain, disability and recovery are important for better understanding of the clinical course, to inform patient and physician and support decision making. Consequently, we aimed to systematically review prognostic factors predicting outcome in non-surgically treated patients with sciatica. A search of Medline, Embase, Web of Science and Cinahl, up to March 2012 was performed for prospective cohort studies on prognostic factors for non-surgically treated sciatica. Two reviewers independently selected studies for inclusion and assessed the risk of bias. Outcomes were pain, disability, recovery and surgery. A best evidence synthesis was carried out in order to assess and summarize the data. The initial search yielded 4392 articles of which 23 articles reporting on 14 original cohorts met the inclusion criteria. High clinical, methodological and statistical heterogeneity among studies was found. Reported evidence regarding prognostic factors predicting the outcome in sciatica is limited. The majority of factors that have been evaluated, e.g., age, body mass index, smoking and sensory disturbance, showed no association with outcome. The only positive association with strong evidence was found for leg pain intensity at baseline as prognostic factor for subsequent surgery. © 2013 European Federation of International Association for the Study of Pain Chapters.

Ford Class Aircraft Carrier: Poor Outcomes Are the Predictable Consequences of the Prevalent Acquisition Culture

Science.gov (United States)

2015-10-01

FORD CLASS AIRCRAFT CARRIER Poor Outcomes Are the Predictable Consequences of the Prevalent Acquisition Culture...2. REPORT TYPE 3. DATES COVERED 00-00-2015 to 00-00-2015 4. TITLE AND SUBTITLE Ford Class Aircraft Carrier: Poor Outcomes Are the Predictable...This Study The Navy set ambitious goals for the Ford -class program, including an array of new technologies and design features that were intended

Combining multiple models to generate consensus: Application to radiation-induced pneumonitis prediction

Energy Technology Data Exchange (ETDEWEB)

Das, Shiva K.; Chen Shifeng; Deasy, Joseph O.; Zhou Sumin; Yin Fangfang; Marks, Lawrence B. [Department of Radiation Oncology, Duke University Medical Center, Durham, North Carolina 27710 (United States); Department of Radiation Oncology, Washington University School of Medicine, St. Louis, Missouri 63110 (United States); Department of Radiation Oncology, Duke University Medical Center, Durham, North Carolina 27710 (United States); Department of Radiation Oncology, University of North Carolina School of Medicine, Chapel Hill, North Carolina 27599 (United States)

2008-11-15

The fusion of predictions from disparate models has been used in several fields to obtain a more realistic and robust estimate of the ''ground truth'' by allowing the models to reinforce each other when consensus exists, or, conversely, negate each other when there is no consensus. Fusion has been shown to be most effective when the models have some complementary strengths arising from different approaches. In this work, we fuse the results from four common but methodologically different nonlinear multivariate models (Decision Trees, Neural Networks, Support Vector Machines, Self-Organizing Maps) that were trained to predict radiation-induced pneumonitis risk on a database of 219 lung cancer patients treated with radiotherapy (34 with Grade 2+ postradiotherapy pneumonitis). Each model independently incorporated a small number of features from the available set of dose and nondose patient variables to predict pneumonitis; no two models had all features in common. Fusion was achieved by simple averaging of the predictions for each patient from all four models. Since a model's prediction for a patient can be dependent on the patient training set used to build the model, the average of several different predictions from each model was used in the fusion (predictions were made by repeatedly testing each patient with a model built from different cross-validation training sets that excluded the patient being tested). The area under the receiver operating characteristics curve for the fused cross-validated results was 0.79, with lower variance than the individual component models. From the fusion, five features were extracted as the consensus among all four models in predicting radiation pneumonitis. Arranged in order of importance, the features are (1) chemotherapy; (2) equivalent uniform dose (EUD) for exponent a=1.2 to 3; (3) EUD for a=0.5 to 1.2, lung volume receiving >20-30 Gy; (4) female sex; and (5) squamous cell histology. To facilitate

Archaeological predictive model set.

Science.gov (United States)

2015-03-01

This report is the documentation for Task 7 of the Statewide Archaeological Predictive Model Set. The goal of this project is to : develop a set of statewide predictive models to assist the planning of transportation projects. PennDOT is developing t...

Predicting coastal cliff erosion using a Bayesian probabilistic model

Science.gov (United States)

Hapke, Cheryl J.; Plant, Nathaniel G.

2010-01-01

Regional coastal cliff retreat is difficult to model due to the episodic nature of failures and the along-shore variability of retreat events. There is a growing demand, however, for predictive models that can be used to forecast areas vulnerable to coastal erosion hazards. Increasingly, probabilistic models are being employed that require data sets of high temporal density to define the joint probability density function that relates forcing variables (e.g. wave conditions) and initial conditions (e.g. cliff geometry) to erosion events. In this study we use a multi-parameter Bayesian network to investigate correlations between key variables that control and influence variations in cliff retreat processes. The network uses Bayesian statistical methods to estimate event probabilities using existing observations. Within this framework, we forecast the spatial distribution of cliff retreat along two stretches of cliffed coast in Southern California. The input parameters are the height and slope of the cliff, a descriptor of material strength based on the dominant cliff-forming lithology, and the long-term cliff erosion rate that represents prior behavior. The model is forced using predicted wave impact hours. Results demonstrate that the Bayesian approach is well-suited to the forward modeling of coastal cliff retreat, with the correct outcomes forecast in 70–90% of the modeled transects. The model also performs well in identifying specific locations of high cliff erosion, thus providing a foundation for hazard mapping. This approach can be employed to predict cliff erosion at time-scales ranging from storm events to the impacts of sea-level rise at the century-scale.

Developing risk prediction models for kidney injury and assessing incremental value for novel biomarkers.

Science.gov (United States)

Kerr, Kathleen F; Meisner, Allison; Thiessen-Philbrook, Heather; Coca, Steven G; Parikh, Chirag R

2014-08-07

The field of nephrology is actively involved in developing biomarkers and improving models for predicting patients' risks of AKI and CKD and their outcomes. However, some important aspects of evaluating biomarkers and risk models are not widely appreciated, and statistical methods are still evolving. This review describes some of the most important statistical concepts for this area of research and identifies common pitfalls. Particular attention is paid to metrics proposed within the last 5 years for quantifying the incremental predictive value of a new biomarker. Copyright © 2014 by the American Society of Nephrology.

Comparison of Spot Sign, Blend Sign and Black Hole Sign for Outcome Prediction in Patients with Intracerebral Hemorrhage.

Science.gov (United States)

Sporns, Peter B; Schwake, Michael; Kemmling, André; Minnerup, Jens; Schwindt, Wolfram; Niederstadt, Thomas; Schmidt, Rene; Hanning, Uta

2017-09-01

Blend sign (BS) and black hole sign (BHS) on non-contrast computed tomography (NCCT) and spot sign (SS) on CT-angiography (CTA) are indicators of early hematoma expansion in spontaneous intracerebral hemorrhage (ICH). However, their independent contributions to outcome have not been well explored. In this retrospective study, inclusion criteria were: 1) spontaneous ICH and 2) NCCT and CTA performed on admission within 6 hours after onset of symptoms. Discharge outcome was dichotomized as good (modified Rankin Scale [mRS] 0-3) and poor (mRS 4-6) outcomes. The impacts of BHS, BS and SS on outcome were assessed in univariate and multivariable logistic regression models. Of 182 patients with spontaneous ICH, 26 (14.3%) presented with BHS, 37 (20.3%) with BS and 39 (21.4%) with SS. There was a substantial correlation between SS and BS (κ=0.701) and a moderate correlation between SS and BHS (κ=0.424). In univariable logistic regression, higher baseline hematoma volume ( P <0.001), intraventricular hemorrhage ( P =0.002) and the presence of BHS/BS/SS (all P <0.001) on admission CT scan were associated with poor outcome. Multivariable analysis identified intraventricular haemorrhage (odds ratio [OR] 2.22 per mL, P =0.022), baseline hematoma volume (OR 1.03 per mL, P <0.001) and SS on CTA (OR 11.43, P <0.001) as independent predictors of poor outcome, showing that SS compared to BS and BHS was more powerful to predict poor outcome. The NCCT BHS and BS are correlated with the CTA SS and are reliable predictors of poor outcome in patients with ICH. Of the CT variables indicating early hematoma expansion, SS on CTA was the most reliable outcome predictor. However, given their correlation with SS on CTA, BS and BHS on NCCT can be useful for predicting outcome if CTA is not obtainable.

Predicting community composition from pairwise interactions

Science.gov (United States)

Friedman, Jonathan; Higgins, Logan; Gore, Jeff

The ability to predict the structure of complex, multispecies communities is crucial for understanding the impact of species extinction and invasion on natural communities, as well as for engineering novel, synthetic communities. Communities are often modeled using phenomenological models, such as the classical generalized Lotka-Volterra (gLV) model. While a lot of our intuition comes from such models, their predictive power has rarely been tested experimentally. To directly assess the predictive power of this approach, we constructed synthetic communities comprised of up to 8 soil bacteria. We measured the outcome of competition between all species pairs, and used these measurements to predict the composition of communities composed of more than 2 species. The pairwise competitions resulted in a diverse set of outcomes, including coexistence, exclusion, and bistability, and displayed evidence for both interference and facilitation. Most pair outcomes could be captured by the gLV framework, and the composition of multispecies communities could be predicted for communities composed solely of such pairs. Our results demonstrate the predictive ability and utility of simple phenomenology, which enables accurate predictions in the absence of mechanistic details.

Comparing statistical and machine learning classifiers: alternatives for predictive modeling in human factors research.

Science.gov (United States)

Carnahan, Brian; Meyer, Gérard; Kuntz, Lois-Ann

2003-01-01

Multivariate classification models play an increasingly important role in human factors research. In the past, these models have been based primarily on discriminant analysis and logistic regression. Models developed from machine learning research offer the human factors professional a viable alternative to these traditional statistical classification methods. To illustrate this point, two machine learning approaches--genetic programming and decision tree induction--were used to construct classification models designed to predict whether or not a student truck driver would pass his or her commercial driver license (CDL) examination. The models were developed and validated using the curriculum scores and CDL exam performances of 37 student truck drivers who had completed a 320-hr driver training course. Results indicated that the machine learning classification models were superior to discriminant analysis and logistic regression in terms of predictive accuracy. Actual or potential applications of this research include the creation of models that more accurately predict human performance outcomes.

A comparison of published multidimensional indices to predict outcome in idiopathic pulmonary fibrosis

Directory of Open Access Journals (Sweden)

Charles Sharp

2017-03-01

Full Text Available Idiopathic pulmonary fibrosis (IPF has an unpredictable course and prognostic factors are incompletely understood. We aimed to identify prognostic factors, including multidimensional indices from a significant IPF cohort at the Bristol Interstitial Lung Disease Centre in the UK. Patients diagnosed with IPF between 2007 and 2014 were identified. Longitudinal pulmonary physiology and exercise testing results were collated, with all-cause mortality used as the primary outcome. Factors influencing overall, 12- and 24-month survival were identified using Cox proportional hazards modelling and receiver operating characteristic curve analysis. We found in this real-world cohort of 167 patients, diffusing capacity for carbon monoxide (DLCO and initiation of long-term oxygen were independent markers of poor prognosis. Exercise testing results predicted 12-month mortality as well as DLCO, but did not perform as well for overall survival. The Composite Physiological Index was the best performing multidimensional index, but did not outperform DLCO. Our data confirmed that patients who experienced a fall in forced vital capacity (FVC >10% had significantly worse survival after that point (p=0.024. Our data from longitudinal follow-up in IPF show that DLCO is the best individual prognostic marker, outperforming FVC. Exercise testing is important in predicting early poor outcome. Regular and complete review should be conducted to ensure appropriate care is delivered in a timely fashion.

Comparing frailty measures in their ability to predict adverse outcome among older residents of assisted living

Directory of Open Access Journals (Sweden)

Hogan David B

2012-09-01