adabay: an R package for rapid evaluation and calibration of Bayesian group sequential designs across common endpoint types

2026-08-02

AI Summary

This study addresses the computational burden of Bayesian group sequential designs in confirmatory trials, which typically require embedding expensive posterior inference methods—such as MCMC—within Monte Carlo simulations. To overcome this, the authors propose a semi-simulation framework that generates trial trajectories via Monte Carlo simulation while rapidly evaluating design properties using analytic posteriors or low-dimensional numerical integration. A key innovation is the approximation of arbitrary priors by conjugate mixture distributions, complemented by tail-probability diagnostics and precomputed decoupled thresholds for calibrating decision boundaries and timing of interim analyses. The approach accommodates continuous, binary, count, and time-to-event endpoints and is implemented via a unified API enabling efficient parallelization. In multiple case studies, the method reproduces results from BATSS, adaptr, and gsbDesign within Monte Carlo error margins, achieving speedups of 4–5 orders of magnitude over BATSS and 1–2 orders over adaptr on an 8-core system per virtual trial.

Abstract

Bayesian group sequential designs (GSDs) combine the efficiency of frequentist GSDs with clinically interpretable probability statements and principled external evidence incorporation. However, their uptake in confirmatory trials has been held back by the cost of evaluating frequentist operating characteristics at the design stage, which often nests Markov chain Monte Carlo or another approximate posterior inference within a Monte Carlo trial-simulation loop. We introduce adabay, an open-source R package implementing a semi-simulation framework for the rapid evaluation and calibration of Bayesian GSDs. Trial data paths are simulated by Monte Carlo, while per-look posteriors and posterior tail probabilities are computed analytically or by low-dimensional deterministic quadrature. Flexible prior specification is achieved by approximating any user-specified prior with a finite mixture of conjugate components, with tail-probability diagnostics that flag inadequate approximations at the decision thresholds. The package offers a unified application programming interface for continuous, binary, count and time-to-event endpoints, supports posterior-probability decision rules with one or more efficacy and futility criteria under binding or non-binding regimes, and includes a precomputation strategy that decouples threshold calibration and look-time selection from the simulation pass. adabay reproduces the operating characteristics of BATSS and adaptr in the continuous and binary case studies, the analytic gsbDesign values in the continuous case, and the BATSS results in the count case, all within Monte Carlo error, while running approximately four to five orders of magnitude faster than BATSS and one to over two orders of magnitude faster than adaptr per virtual trial on eight cores. The package is distributed under an MIT licence.

Problem

• Bayesian group sequential designs
• operating characteristics
• computational efficiency
• clinical trials
• Monte Carlo simulation

Innovation

• Bayesian group sequential design
• semi-simulation framework
• deterministic quadrature
• conjugate prior mixture
• operating characteristics