Bayesian response adaptive randomization design with a composite endpoint of mortality and morbidity

TL;DR

This paper introduces a Bayesian response adaptive randomization design for ICU patients using a composite endpoint of mortality and morbidity, optimizing patient allocation based on ongoing trial data.

Contribution

It proposes a novel Bayesian mixture model for adaptive randomization targeting a composite endpoint, improving patient allocation efficiency in clinical trials.

Findings

Allocates more patients to better performing treatments.

Maintains adequate statistical power and error control.

Outperforms existing adaptive rules in simulations.

Abstract

Allocating patients to treatment arms during a trial based on the observed responses accumulated prior to the decision point, and sequential adaptation of this allocation,, could minimize the expected number of failures or maximize total benefit to patients. In this study, we developed a Bayesian response adaptive randomization (RAR) design targeting the endpoint of organ support-free days (OSFD) for patients admitted to the intensive care units (ICU). The OSFD is a mixture of mortality and morbidity assessed by the number of days of free of organ support within a predetermined time-window post-randomization. In the past, researchers treated OSFD as an ordinal outcome variable where the lowest category is death. We propose a novel RAR design for a composite endpoint of mortality and morbidity, e.g., OSFD, by using a Bayesian mixture model with a Markov chain Monte Carlo sampling to estimate the posterior probability of OSFD and determine treatment allocation ratios at each interim. Simulations were conducted to compare the performance of our proposed design under various randomization rules and different alpha spending functions. The results show that our RAR design using Bayesian inference allocated more patients to the better performing arm(s) compared to other existing adaptive rules while assuring adequate power and type I error rate control for the across a range of plausible clinical scenarios.