Abstract
This non-technical review discusses the use of historical data in the design and analysis of randomized controlled trials using a Bayesian approach. The focus is on comparing the philosophy behind different approaches and practical considerations for their use. The two main approaches, that is, the power prior and the meta-analytic-predictive prior, are illustrated using fictitious and real data sets. Such methods, which are known as dynamic borrowing methods, are becoming increasingly popular in pharmaceutical research because they may imply an important reduction in costs. In some cases, e.g. in pediatric studies, they may be indispensable to address the clinical research question. In addition to the two original approaches, this review also covers various extensions and variations of the methods. The usefulness and acceptance of the approaches by regulatory agencies is also critically evaluated. Finally, references to relevant software are provided.
Funding Statement
The authors acknowledge the BOF bilateral cooperation of UHasselt for the financial support to the third author.
Acknowledgments
A preliminary version of this review paper was presented by the first author at the Annual South African Statistical Association (SASA) meeting in 2021 in Stellenbosch, South Africa.
The authors thank Brad Carlin and David Dejardin for the interesting and helpful discussions during the preparation of the paper. The authors are indebted to Tim Friede whose comments on a previous version of the paper improved the review considerably.
Citation
Emmanuel Lesaffre. Hongchao Qi. Akalu Banbeta. Joost van Rosmalen. "A review of dynamic borrowing methods with applications in pharmaceutical research." Braz. J. Probab. Stat. 38 (1) 1 - 31, March 2024. https://doi.org/10.1214/24-BJPS598
Information
