Abstract
Due to differential treatment responses of patients to pharmacotherapy, drug development and practice in medicine are concerned with personalized medicine, which includes identifying subgroups of population that exhibit differential treatment effect. For time–to–event data, available methods only focus on detecting and testing treatment–by–covariate interactions and may not consider multiplicity. In this work, we introduce the Bayesian credible subgroups approach for time–to–event endpoints. It provides two bounding subgroups for the true benefiting subgroup: one which is likely to be contained by the benefiting subgroup and one which is likely to contain the benefiting subgroup. A personalized treatment effect is estimated by two common measures of survival time: the hazard ratio and restricted mean survival time. We apply the method to identify benefiting subgroups in a case study of prostate carcinoma patients and a simulated large clinical dataset.
Highlights
A goal of clinical trials is to evaluate primary endpoints that describe comprehensive characteristics of the disease under study and allow for comparisons of treatments in an entire population
Schnell et al [14] proposed a Bayesian credible subgroups methods for continuous endpoints which addressed both simultaneous inference and multiplicity. We extend their approach to survival endpoints by using two summaries commonly used in clinical trials: the log hazard ratio (HR) and RMSTd
We have presented a Bayesian credible subgroup method for survival endpoints by using two common summaries: log HR and RMSTd
Summary
A goal of clinical trials is to evaluate primary endpoints that describe comprehensive characteristics of the disease under study and allow for comparisons of treatments in an entire population. Trial populations are often heterogeneous due to different demographics, medical history or genetic makeup among patients. The efficacy of marketed treatments could not be replicated in follow–up clinical trials [1]. The inability to replicate study results in follow-up trials may be caused by different proportions of benefiting and non– benefiting subgroups of patients from experimental treatment compared to control. Regulators and health technology assessment agencies worldwide have had a growing interest in identifying subgroups of patients who benefit from a treatment. Several methods to find such subgroups in clinical trials have been proposed in the literature [2,3,4]
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have