Bayesian multiregional clinical trials using model averaging

Abstract

Multiregional clinical trials (MRCTs) provide the benefit of more rapidly introducing drugs to the global market; however, small regional sample sizes can lead to poor estimation quality of region-specific effects when using current statistical methods. With the publication of the International Conference for Harmonisation E17 guideline in 2017, the MRCT design is recognized as a viable strategy that can be accepted by regional regulatory authorities, necessitating new statistical methods that improve the quality of region-specific inference. In this article, we develop a novel methodology for estimating region-specific and global treatment effects for MRCTs using Bayesian model averaging. This approach can be used for trials that compare two treatment groups with respect to a continuous outcome, and it allows for the incorporation of patient characteristics through the inclusion of covariates. We propose an approach that uses posterior model probabilities to quantify evidence in favor of consistency of treatment effects across all regions, and this metric can be used by regulatory authorities for drug approval. We show through simulations that the proposed modeling approach results in lower MSE than a fixed-effects linear regression model and better control of type I error rates than a Bayesian hierarchical model.

Keywords: Bayesian clinical trials; Bayesian model averaging; Global consistency; Global treatment effect; Local consistency; Multiregional clinical trials; Region-specific treatment effects.

Fig. 1.

Global rejection rates (Panel A), true positive rates for alternative regions (Panel B), false positive rates for null regions (Panel C), relative MSE (FELM as reference) for alternative regions (Panel D), and relative MSE for null regions (Panel E) for simulations with equal regional sample sizes. Alternative regions have a treatment effect of 0.034 L.

Fig. 2.

Average -level global consistency probabilities for varying values of , , and . We compare (top row) vs. (bottom row) across three different sample sizes: (left column), (middle column), and (right column).

Fig. 3.

Global and regional rejection rates (left column) and relative MSE with the FELM as the reference method (right column) for simulations with equal regional sample size allocation and varying positive treatment effects across regions. We consider cases with five distinct effects ranging between 0.017 and 0.051 (top row), two distinct effects of 0.017 and 0.034 (middle row), and three distinct effects ranging between 0.017 and 0.051 (bottom row).