#1OpenAI's o1 Correctly Diagnosed 67% of ER Patients vs. 50-55% by Triage Doctors
A Harvard trial found that OpenAI's o1 model correctly diagnosed 67% of emergency room patients, significantly outperforming the 50-55% accuracy rate of human triage doctors. The study represents one of the most rigorous head-to-head comparisons of AI versus physician diagnostic ability in a real clinical setting. The results fuel growing momentum for AI-assisted medical triage, though questions remain about integration into actual ER workflows.