A Semi-parametric Bayesian Approach to Population Finding with Time-to-Event and Toxicity Data in a Randomized Clinical Trial

TL;DR

This paper extends a Bayesian population finding method to handle time-to-event and toxicity data in clinical trials, using semi-parametric models and random forests to improve patient subgroup identification.

Contribution

The paper introduces BaPoFi-TTE, a semi-parametric Bayesian approach incorporating time-to-event and toxicity data with flexible modeling for clinical trial population finding.

Findings

Effective in identifying predictive covariates in simulation studies.

Successfully applied to oncology trial data.

Improves upon parametric models in preliminary analysis.

Abstract

A utility-based Bayesian population finding (BaPoFi) method was proposed by Morita and M\"uller (2017, Biometrics, 1355-1365) to analyze data from a randomized clinical trial with the aim of identifying good predictive baseline covariates for optimizing the target population for a future study. The approach casts the population finding process as a formal decision problem together with a flexible probability model using a random forest to define a regression mean function. BaPoFi is constructed to handle a single continuous or binary outcome variable. In this paper, we develop BaPoFi-TTE as an extension of the earlier approach for clinically important cases of time-to-event (TTE) data with censoring, and also accounting for a toxicity outcome. We model the association of TTE data with baseline covariates using a semi-parametric failure time model with a P\'olya tree prior for an unknown error term and a random forest for a flexible regression mean function. We define a utility function that addresses a trade-off between efficacy and toxicity as one of the important clinical considerations for population finding. We examine the operating characteristics of the proposed method in extensive simulation studies. For illustration, we apply the proposed method to data from a randomized oncology clinical trial. Concerns in a preliminary analysis of the same data based on a parametric model motivated the proposed more general approach.