Statistical innovations in the medical device world sparked by the FDA

Abstract

The world of medical devices while highly diverse is extremely innovative, and this facilitates the adoption of innovative statistical techniques. Statisticians in the Center for Devices and Radiological Health (CDRH) at the Food and Drug Administration (FDA) have provided leadership in implementing statistical innovations. The innovations discussed include: the incorporation of Bayesian methods in clinical trials, adaptive designs, the use and development of propensity score methodology in the design and analysis of non-randomized observational studies, the use of tipping-point analysis for missing data, techniques for diagnostic test evaluation, bridging studies for companion diagnostic tests, quantitative benefit–risk decisions, and patient preference studies.

Key Words:

• Adaptive designs
• Bayesian statistics
• clinical trials
• diagnostic test evaluation
• missing data
• propensity score
• quantitative benefit–risk

Acknowledgments

It is a pleasure to acknowledge the efforts of Charles (Ted) Peterson in the preparation of this article. The authors also thank the referee for great suggestions and comments which helped to improve the article.