Marinka Zitnik, Associate Professor at Harvard, shared a post on X:
“Scaling medical AI to infinitely many clinical contexts.
Medical AI does not fail because it lacks scale. It fails because it lacks context.
Models often produce plausible outputs, but fail when the context shifts across specialties, populations, geographies, and care constraints.
Early approaches to context switching, such as prompt engineering, fine-tuning, in-context learning, and re-training, produce great examples of success. But scaling medical AI requires a shift toward context switching at inference time.
Context switching means models adjust how they reason based on what matters in the moment: which data are available, who the user is, where care is delivered, and what decisions are feasible
Many thanks to all collaborators Michelle M. Li, Ben Y. Reis, Adam Rodman, Tianxi Cai, Noa Dagan, Ran Balicer, Joseph Loscalzo, Isaac Kohane.”
Title: Scaling medical AI across clinical contexts
Authors: Michelle M. Li, Ben Y. Reis, Adam Rodman, Tianxi Cai, Noa Dagan, Ran D. Balicer, Joseph Loscalzo, Isaac S. Kohane and Marinka Zitnik
Read the study
More posts on OncoDaily
