Bayesian Medical Device Clinical Studies in the Regulatory Setting
*Telba Z. Irony, Center for Devices and Radiological Health, FDA 

Keywords: Bayesian methods, medical devices, clinical trials

Bayesian methods have been used in the design and analysis of medical device clinical trials for submission to the Food and Drug Administration for over 10 years. They have been particularly helpful, not only due to the availability of prior information, but also because they provide flexibility with respect to interim analyses, prediction, meta-analysis, and dealing with missing data. Currently, the Center for Devices and Radiological Health at the FDA is also exploring the use of formal Decision Analysis methodology, which is inherent to the Bayesian approach. In this presentation we will discuss the designs and techniques that have been successfully used in premarket applications, highlight the peculiar problems and solutions for implementation of such techniques in the regulatory setting and summarize what has been happening at the Center for Devices and Radiological Health at the FDA since the Bayesian initiative was launched at CDRH.