In Harvard study, AI offered more accurate diagnoses than emergency room doctors
SMRTR summary
OpenAI's o1 model correctly diagnosed ER patients 67% of the time, beating internal medicine doctors at 55–50%. Experts caution the AI wasn't tested against ER specialists and lacks accountability for real-world use.
SMRTR provides this summary for quick context. The original article belongs to TechCrunch.
Read the original article