Home About us Contact
|
Home About us Contact | ||
|
|
||
Model Discrimination (model + discrimination)
Selected AbstractsCT15 RISK STRATIFICATION MODELS FOR HEART VALVE SURGERYANZ JOURNAL OF SURGERY, Issue 2007C. H. Yap Purpose Risk stratification models may be useful in aiding surgical decision-making, preoperative informed consent, quality assurance and healthcare management. While several overseas models exist, no model has been well-validated for use in Australia. We aimed to assess the performance of two valve surgery risk stratification models in an Australian patient cohort. Method The Society of Cardiothoracic Surgeons of Great Britain and Ireland (SCTS) and Northern New England (NNE) models were applied to all patients undergoing valvular heart surgery at St Vincent's Hospital Melbourne and The Geelong Hospital between June 2001 and November 2006. Observed and predicted early mortalities were compared using the chi-square test. Model discrimination was assessed by the area under the receiver operating characteristic (ROC) curve. Model calibration was tested by applying the chi-square test to risk tertiles. Results SCTS model (n = 1095) performed well. Observed mortality was 4.84%, expected mortality 6.64% (chi-square p = 0.20). Model discrimination (area under ROC curve 0.835) and calibration was good (chi-square p = 0.9). the NNE model (n = 1015) over-predicted mortality. Observed mortality 4.83% and expected 7.54% (chi-square p < 0.02). Model discrimination (area under ROC curve 0.835) and calibration was good (chi-square p = 0.9). Conclusion Both models showed good model discrimination and calibration. The NNE model over-predicted early mortality whilst the SCTS model performed well in our cohort of patients. The SCTS model may be useful for use in Australia for risk stratification. [source] Design of follow-up experiments for improving model discrimination and parameter estimationNAVAL RESEARCH LOGISTICS: AN INTERNATIONAL JOURNAL, Issue 8 2004Szu Hui Ng Abstract One goal of experimentation is to identify which design parameters most significantly influence the mean performance of a system. Another goal is to obtain good parameter estimates for a response model that quantifies how the mean performance depends on influential parameters. Most experimental design techniques focus on one goal at a time. This paper proposes a new entropy-based design criterion for follow-up experiments that jointly identifies the important parameters and reduces the variance of parameter estimates. We simplify computations for the normal linear model by identifying an approximation that leads to a closed form solution. The criterion is applied to an example from the experimental design literature, to a known model and to a critical care facility simulation experiment. © 2004 Wiley Periodicals, Inc. Naval Research Logistics, 2004 [source] Weaknesses of goodness-of-fit tests for evaluating propensity score models: the case of the omitted confounder,PHARMACOEPIDEMIOLOGY AND DRUG SAFETY, Issue 4 2005Sherry Weitzen PhD Abstract Purpose Propensity scores are used in observational studies to adjust for confounding, although they do not provide control for confounders omitted from the propensity score model. We sought to determine if tests used to evaluate logistic model fit and discrimination would be helpful in detecting the omission of an important confounder in the propensity score. Methods Using simulated data, we estimated propensity scores under two scenarios: (1) including all confounders and (2) omitting the binary confounder. We compared the propensity score model fit and discrimination under each scenario, using the Hosmer,Lemeshow goodness-of-fit (GOF) test and the c-statistic. We measured residual confounding in treatment effect estimates adjusted by the propensity score omitting the confounder. Results The GOF statistic and discrimination of propensity score models were the same for models excluding an important predictor of treatment compared to the full propensity score model. The GOF test failed to detect poor model fit for the propensity score model omitting the confounder. C-statistics under both scenarios were similar. Residual confounding was observed from using the propensity score excluding the confounder (range: 1,30%). Conclusions Omission of important confounders from the propensity score leads to residual confounding in estimates of treatment effect. However, tests of GOF and discrimination do not provide information to detect missing confounders in propensity score models. Our findings suggest that it may not be necessary to compute GOF statistics or model discrimination when developing propensity score models. Copyright © 2004 John Wiley & Sons, Ltd. [source] Principles for modeling propensity scores in medical research: a systematic literature review,PHARMACOEPIDEMIOLOGY AND DRUG SAFETY, Issue 12 2004Sherry Weitzen PhD Abstract Purpose To document which established criteria for logistic regression modeling researchers consider when using propensity scores in observational studies. Methods We performed a systematic review searching Medline and Science Citation to identify observational studies published in 2001 that addressed clinical questions using propensity score methods to adjust for treatment assignment. We abstracted aspects of propensity score model development (e.g. variable selection criteria, continuous variables included in correct functional form, interaction inclusion criteria), model discrimination and goodness of fit for 47 studies meeting inclusion criteria. Results We found few studies reporting on the propensity score model development or evaluation of model fit. Conclusions Reporting of aspects related to propensity score model development is limited and raises questions about the value of these principles in developing propensity scores from which unbiased treatment effects are estimated. Copyright © 2004 John Wiley & Sons, Ltd. [source] CT15 RISK STRATIFICATION MODELS FOR HEART VALVE SURGERYANZ JOURNAL OF SURGERY, Issue 2007C. H. Yap Purpose Risk stratification models may be useful in aiding surgical decision-making, preoperative informed consent, quality assurance and healthcare management. While several overseas models exist, no model has been well-validated for use in Australia. We aimed to assess the performance of two valve surgery risk stratification models in an Australian patient cohort. Method The Society of Cardiothoracic Surgeons of Great Britain and Ireland (SCTS) and Northern New England (NNE) models were applied to all patients undergoing valvular heart surgery at St Vincent's Hospital Melbourne and The Geelong Hospital between June 2001 and November 2006. Observed and predicted early mortalities were compared using the chi-square test. Model discrimination was assessed by the area under the receiver operating characteristic (ROC) curve. Model calibration was tested by applying the chi-square test to risk tertiles. Results SCTS model (n = 1095) performed well. Observed mortality was 4.84%, expected mortality 6.64% (chi-square p = 0.20). Model discrimination (area under ROC curve 0.835) and calibration was good (chi-square p = 0.9). the NNE model (n = 1015) over-predicted mortality. Observed mortality 4.83% and expected 7.54% (chi-square p < 0.02). Model discrimination (area under ROC curve 0.835) and calibration was good (chi-square p = 0.9). Conclusion Both models showed good model discrimination and calibration. The NNE model over-predicted early mortality whilst the SCTS model performed well in our cohort of patients. The SCTS model may be useful for use in Australia for risk stratification. [source] Vascular cell adhesion molecule 1 as a predictor of severe osteoarthritis of the hip and knee jointsARTHRITIS & RHEUMATISM, Issue 8 2009Georg Schett Objective Osteoarthritis (OA) is a leading cause of pain and physical disability in middle-aged and older individuals. We undertook this study to determine predictors of the development of severe OA, apart from age and overweight. Methods Joint replacement surgery due to severe hip or knee OA was recorded over a 15-year period in the prospective Bruneck cohort study. Demographic characteristics and lifestyle and biochemical variables, including the level of soluble vascular cell adhesion molecule 1 (VCAM-1), were assessed at the 1990 baseline visit and tested as predictors of joint replacement surgery. Results Between 1990 and 2005, hip or knee joint replacement due to OA was performed in 60 subjects. VCAM-1 level emerged as a highly significant predictor of the risk of joint replacement surgery. Intervention rates were 1.9, 4.2, and 10.1 per 1,000 person-years in the first, second, and third tertiles, of the VCAM-1 level, respectively. In multivariable logistic regression analysis, the adjusted relative risk of joint replacement surgery in the highest versus the lowest tertile group of VCAM-1 level was 3.9 (95% confidence interval 1.7,8.7) (P < 0.001). Findings were robust in various sensitivity analyses and were consistent in subgroups. Addition of the VCAM-1 level to a risk model already including age, sex, and body mass index resulted in significant gains in model discrimination (C statistic) and calibration and in more accurate risk classification of individual participants. Conclusion The level of soluble VCAM-1 emerged as a strong and independent predictor of the risk of hip and knee joint replacement due to severe OA. If our findings can be reproduced in other epidemiologic cohorts, they will assist in routine risk classification and will contribute to a better understanding of the etiology of OA. [source] PROBABILITY-BASED OPTIMAL DESIGNAUSTRALIAN & NEW ZEALAND JOURNAL OF STATISTICS, Issue 1 2008J. M. McGree Summary Optimal design of experiments has generally concentrated on parameter estimation and, to a much lesser degree, on model discrimination. Often an experimenter is interested in a particular outcome and wishes to maximize in some way the probability of this outcome. We propose a new class of compound criteria and designs that address this issue for generalized linear models. The criteria offer a method of achieving designs that possess the properties of efficient parameter estimation and a high probability of a desired outcome. [source] | |||||||||||||