Deep historical borrowing framework to prospectively and simultaneously synthesize control information in confirmatory clinical trials with multiple endpoints. Issue 1 (2nd January 2022)

• Record Type: Journal Article
• Authors: Zhan, Tianyu; Zhou, Yiwang; Geng, Ziqian; Gu, Yihua; Kang, Jian; Wang, Li; Huang, Xiaohong; Slate, Elizabeth H.
• Is Part Of: Journal of biopharmaceutical statistics. Volume 32:Issue 1(2022)
• Page Start: 90
• Page End: 106
• Publication Date: 2022-01-02
• Subjects: Bayesian hierarchical model -- deep learning -- family-wise error rate control -- power preservation -- prospective algorithm; Pharmacy -- Statistical methods -- Periodicals; Drugs -- Testing -- Statistical methods -- Periodicals; Biometry -- Periodicals; Biopharmaceutics -- Periodicals; Pharmacokinetics -- Periodicals; 615.19
• DOI: 10.1080/10543406.2021.1975128
• Languages: English
• ISSNs: 1054-3406

Abstract

ABSTRACT: In current clinical trial development, historical information is receiving more attention as it provides utility beyond sample size calculation. Meta-analytic-predictive (MAP) priors and robust MAP priors have been proposed for prospectively borrowing historical data on a single endpoint. To simultaneously synthesize control information from multiple endpoints in confirmatory clinical trials, we propose to approximate posterior probabilities from a Bayesian hierarchical model and estimate critical values by deep learning to construct pre-specified strategies for hypothesis testing. This feature is important to ensure study integrity by establishing prospective decision functions before the trial conduct. Simulations are performed to show that our method properly controls family-wise error rate and preserves power as compared with a typical practice of choosing constant critical values given a subset of null space. Satisfactory performance under prior-data conflict is also demonstrated. We further illustrate our method using a case study in Immunology.