Summary ROC curve based on a weighted Youden index for selecting an optimal cutpoint in meta‐analysis of diagnostic accuracy
- 16 December 2010
- journal article
- Published by Wiley in Statistics in Medicine
- Vol. 29 (30), 3069-3078
- https://doi.org/10.1002/sim.3937
Abstract
Established approaches for analyzing meta‐analyses of diagnostic accuracy model the bivariate distribution of the observed pairs of specificity Sp and sensitivity Se, thus accounting for across‐study correlation. However, it is still a matter of debate how to define a summary ROC (SROC) curve. It was recently pointed out that the SROC curve is in principle unidentifiable if only one (Sp, Se) pair per study is known. We evaluate an alternative approach, modeling the study‐specific ROC curves based on the assumption of linearity in logit space. A setting is considered in which the pair (Sp, Se) that is selected for publication in a particular study maximizes a weighted Youden index λSe+(1−λ)Sp with a given weight λ.This leads to a fixed slope (1−λ)/λ of the ROC curve in (1−Sp, Se), equivalent to a slope of (1−λ)Sp(1−Sp)/(λSe(1−Se)) for the corresponding straight line in logit space. While the slope depends on the variance ratio of the underlying distributions, the intercept is a function of the mean difference. Our approach leads in a natural way to a new, model‐based proposal for a summary ROC curve. It is illustrated using an example from the literature. Copyright © 2010 John Wiley & Sons, Ltd.Keywords
This publication has 31 references indexed in Scilit:
- Evaluating diagnostic tests: The area under the ROC curve and the balance of errorsStatistics in Medicine, 2010
- oA novel nonparametric approach for estimating cut-offs in continuous risk indicators with application to diabetes epidemiologyBMC Medical Research Methodology, 2009
- The Performance of Risk Prediction ModelsBiometrical Journal, 2008
- Letter to the editorBiostatistics, 2008
- Bias in Sensitivity and Specificity Caused by Data-Driven Selection of Optimal Cutoff Values: Mechanisms, Magnitude, and SolutionsClinical Chemistry, 2008
- Peirce, Youden, and Receiver Operating Characteristic CurvesThe American Statistician, 2007
- Meta-Analysis of Binary Data Based upon Dichotomized CriteriaZeitschrift für Psychologie / Journal of Psychology, 2007
- REGRET GRAPHS, DIAGNOSTIC UNCERTAINTY AND YOUDEN'S INDEXStatistics in Medicine, 1996
- Basic principles of ROC analysisSeminars in Nuclear Medicine, 1978