Artificial Intelligence and Machine Learning -- The perspective from a FDA project

Date/Time: 19 July 2019, 11:00 AM - 12:00 PM
Speaker: Weida Tong, Ph.D.
Speaker Affiliation: Director, Division of Bioinformatics & Biostatistics, NCTR/FDA
Venue: John A. Burns School of Medicine, Medical Education Building Access Grid Room 202

For more info: Youping Deng, dengy@hawaii.edu
Description: Artificial intelligence (AI) has made a significant mark in the past decade and demon-strated its utility in the broad area of predictive medicine. The rapid advancement in AI also poses several challenges and opportunities for regulatory agencies such as FDA: what is the regulatory structure to approve ever evolving nature of AI-based devices and application and how we implement the AI-based framework to improve regulatory pro-cess. Reproducibility is a key element to realize the potential of AI in biomedical applica-tion and regulatory implementation. The FDA has led a large consortium, called MicroAr-ray and Sequencing Quality Control (MAQC/SEQC), which has interrogated various ma-chine learning approaches in developing gene-expression based biomarkers for both clinical and preclinical applications. Specifically, the questions relating to reproducibility have been extensively investigated such as whether a reproducible result is (1) dataset-dependent, (2) AI methodology dependent, (3) experience-dependent, and (4) technolo-gy-dependent. The presentation will conclude with some lessons learned about what is needed to close the gap in reproducibility of AI in predictive medicine.
Additional Document:Click here to download