Reposted by Michael Oberst
Public datasets of Chest X-Rays (CXRs) are a popular benchmark for ML computer vision models, which often report strong average-case performance. But does this aggregate performance reflect actual utility in the clinic?
Michael Oberst
@moberst.bsky.social
1.3K followers 209 following 32 posts
Assistant Prof. of CS at Johns Hopkins Visiting Scientist at Abridge AI Causality & Machine Learning in Healthcare Prev: PhD at MIT, Postdoc at CMU
