Augmented Binary Method for Basket Trials (ABBA)

TL;DR

This paper introduces ABBA, a Bayesian hierarchical augmented binary method for basket trials that improves statistical power by borrowing information across subtrials, especially when treatment effects are consistent.

Contribution

The paper extends the augmented binary method to basket trials, providing a new Bayesian approach that enhances efficiency and power in multi-subtrial clinical studies.

Findings

Reduces 95% credible interval width for treatment effect estimates.

Increases power when treatment effects are similar across subtrials.

Demonstrates improved estimation accuracy with real clinical data.

Abstract

In several clinical areas, traditional clinical trials often use a responder outcome, a composite endpoint that involves dichotomising a continuous measure. An augmented binary method that improves power whilst retaining the original responder endpoint has previously been proposed. The method leverages information from the the undichotomised component to improve power. We extend this method for basket trials, which are gaining popularity in many clinical areas. For clinical areas where response outcomes are used, we propose the new Augmented Binary method for BAsket trials (ABBA) enhances efficiency by borrowing information on the treatment effect between subtrials. The method is developed within a latent variable framework using a Bayesian hierarchical modelling approach. We investigate the properties of the proposed methodology by analysing point estimates and credible intervals in various simulation scenarios, comparing them to the standard analysis for basket trials that assumes binary outcome. Our method results in a reduction of 95% high density interval of the posterior distribution of the log odds ratio and an increase in power when the treatment effect is consistent across subtrials. We illustrate our approach using real data from two clinical trials in rheumatology.