Online Program

Return to main conference page
Tuesday, September 24
Tue, Sep 24, 2:45 PM - 4:00 PM
Recent Development of Artificial Intelligence in Regulatory Science

A Unified Machine Learning Procedure for Defining Clinically Meaningful Change (301018)

*Jiwei Zhao, State University of New York at Buffalo 

Keywords: Minimal clinically important difference, Data adaptive, Surrogate loss, Nonconvex optimization.

Understanding the limitation of solely relying on statistical significance, researchers have proposed methods to draw biomedical conclusions based on clinical significance. The minimal clinically important significance (MCID) is one of the most fundamental concepts to study clinical significance. Based on an anchor question usually available in the patients' reported outcome, Hedayat, Wang and Xu (2015) presented a method to estimate MCID using the classification technique. However, their method implicitly requires that the binary outcome of the anchor question is equally likely, i.e., the balanced outcome assumption. This assumption can not be guaranteed a priori when one designs the study; hence, it can not be satisfied in general. In this paper, we propose a data adaptive method, which can overcome this limitation. Compared to Hedayat, Wang and Xu (2015), our method uses a faster gradient based algorithm and adopts a more flexible structure of the MCID at the individual level. We conduct comprehensive simulation studies and apply our method to the ChAMP study to demonstrate its usefulness and also its outperformance.