AI in Medicine: Should You Trust This Tool? Evaluating AI Evidence and Claims– Hosted by the Geisel Academy of Educators and Scholars

Overview

Clinicians are trained to appraise a randomized trial. The equivalent habit for AI evidence, applied to validation studies, vendor claims, and regulatory filings, does not yet exist. This session builds it. It covers what AUC, sensitivity, specificity, positive predictive value, and calibration establish and what they leave open; what it means that nearly all cleared AI devices reached the market through the 510(k) pathway; and how to judge whether a tool validated at three academic centers will hold up in a rural practice. A six-part framework is applied to two published studies.

Please see the event website for further details.

Accreditation

Please see the event website for accreditation information.