Abstract: Clinical trials are the gatekeeper and bottleneck of medicine. In the first half of the talk, I discuss lessons learned from our systematic analysis of all the FDA-approved medical AI devices, which reveals key limitations in how AIs are evaluated (Wu et al. Nature Medicine 2021). Motivated by this, I share the design and results from our recent randomized prospective clinical trial evaluating EchoNet, a computer vision AI for assessing cardiac conditions. In the second half, I will discuss how to use AI (Trial Pathfinder) to make clinical trials more diverse and efficient (Liu et al. Nature 2021, Nature Medicine 2022). Trial Pathfinder is used by pharma companies to guide new trials and was selected as a Top Ten Clinical Research Achievement.
Bio: James Zou is an assistant professor of Biomedical Data Science, CS and EE at Stanford University. He develops machine learning methods for biology and medicine. He works on both improving the foundations of ML–-by making models more trustworthy and reliable–-as well as in-depth scientific and clinical applications. He has received a Sloan Fellowship, an NSF CAREER Award, two Chan-Zuckerberg Investigator Awards, a Top Ten Clinical Achievement Award, several best paper awards, and faculty awards from Google, Amazon, Tencent and Adobe.