TY - JOUR

T1 - A Bayesian model to estimate the cutoff and the clinical utility of a biomarker assay

AU - Vradi, Eleni

AU - Jaki, Thomas Friedrich

AU - Vonk, Richardus

AU - Brannath, Werner

N1 - The final, definitive version of this article has been published in the Journal, Statistical Methods in Medical Research, 28 (8), 2018, © SAGE Publications Ltd, 2018 by SAGE Publications Ltd at the Statistical Methods in Medical Research page: http://journals.sagepub.com/home/smm on SAGE Journals Online: http://journals.sagepub.com/

PY - 2019/8/1

Y1 - 2019/8/1

N2 - To enable targeted therapies and enhance medical decision-making, biomarkers are increasingly used as screening and diagnostic tests. When using quantitative biomarkers for classification purposes, this often implies that an appropriate cutoff for the biomarker has to be determined and its clinical utility must be assessed. In the context of drug development, it is of interest how the probability of response changes with increasing values of the biomarker. Unlike sensitivity and specificity, predictive values are functions of the accuracy of the test, depend on the prevalence of the disease and therefore are a useful tool in this setting. In this paper, we propose a Bayesian method to not only estimate the cutoff value using the negative and positive predictive values, but also estimate the uncertainty around this estimate. Using Bayesian inference allows us to incorporate prior information, and obtain posterior estimates and credible intervals for the cut-off and associated predictive values. The performance of the Bayesian approach is compared with alternative methods via simulation studies of bias, interval coverage and width and illustrations on real data with binary and time-to-event outcomes are provided.

AB - To enable targeted therapies and enhance medical decision-making, biomarkers are increasingly used as screening and diagnostic tests. When using quantitative biomarkers for classification purposes, this often implies that an appropriate cutoff for the biomarker has to be determined and its clinical utility must be assessed. In the context of drug development, it is of interest how the probability of response changes with increasing values of the biomarker. Unlike sensitivity and specificity, predictive values are functions of the accuracy of the test, depend on the prevalence of the disease and therefore are a useful tool in this setting. In this paper, we propose a Bayesian method to not only estimate the cutoff value using the negative and positive predictive values, but also estimate the uncertainty around this estimate. Using Bayesian inference allows us to incorporate prior information, and obtain posterior estimates and credible intervals for the cut-off and associated predictive values. The performance of the Bayesian approach is compared with alternative methods via simulation studies of bias, interval coverage and width and illustrations on real data with binary and time-to-event outcomes are provided.

KW - Bayesian model

KW - cutoff estimation

KW - predictive values

KW - step function

KW - diagnostic tests

KW - clinical utility

KW - response rates

U2 - 10.1177/0962280218784778

DO - 10.1177/0962280218784778

M3 - Journal article

VL - 28

SP - 2538

EP - 2556

JO - Statistical Methods in Medical Research

JF - Statistical Methods in Medical Research

SN - 0962-2802

IS - 8

ER -