All Times EDT
Keywords: Real word evidence, Historical data, Dynamic information borrowing, Elastic prior, Bayesian method, Adaptive design
Use of historical data and real world evidence holds great potential to improve the efficiency of clinical trials. One major challenge is how to efficiently borrow information from historical data while maintaining reasonable type I error. We propose the elastic prior to address this challenge and achieve dynamic information borrowing. Unlike existing approaches, the proposed method proactively controls the behavior of dynamic information borrowing and type I error through an elastic function, which is a monotonic function of a congruence measure between historical data and trial data. The elastic function is constructed to satisfy a set of information borrowing constraints prespecified by researchers or regulatory agencies such that the prior will borrow information when historical and trial data are congruent, and refrain from information borrowing when historical and trial data are incongruent. By doing so, the elastic prior dramatically reduce the risk of data dredging and bias. Simulation study shows that compared to existing methods, the elastic prior has better type I error control, and yields competitive or higher power.