In Harvard Study, AI Gave More Accurate ER Diagnoses Than Two Doctors
In Harvard study, AI offered more accurate emergency room diagnoses than two human doctors
A Harvard study compared LLMs with two doctors on ER diagnoses; at least one model was more accurate. The post does not disclose model names, sample size, or accuracy rates.
Why it matters: A Harvard Medical School team compared large language models with human doctors on real emergency cases, at least one model beat two physicians, and the study is published in Science.