JAMA: AI outperforms doctors in complex diagnostic accuracy
HealthcareAIGuy · x · 2026-08-23
A JAMA Perspective argues AI already rivals or beats physicians in cognitive medical tasks. ChatGPT o3 ranked the correct diagnosis first in 60% of complex cases vs. 15.9% for doctors, and another AI system diagnosed correctly 4x more often with 19% less testing. The authors suggest human oversight could sometimes worsen results if AI is superior, with autonomous AI workflows potentially ready by 2030. While medicine requires judgment and empathy often missing in simulations, the focus should remain on better, cheaper care.
Related event: JAMA Perspective: AI Diagnosis Outperforms Doctors(2 posts)→
More from Research
- False Collatz Proof via a Lean Bug: Talk Probes Proof Assistants as LLM-Found Bug Targets — marc_lelarge · 2026-10-16
- Goodfire's Nick Cammarata argues neural networks are 'already clean' in new interpretability essay — ctjlewis · 2026-10-16
- NEJM AI: prompt tuning cuts LLM clinical test-order cost ratio to 1.4x across 19 systems — dvir_a · 2026-10-16
- Prompting cuts LLM over-testing costs across 19 systems, but diagnosis agreement drops — dvir_a · 2026-10-16
- AI Recommends 3.2x Costlier Care; Models Add Tests in 2/3 of Visits Physicians Ordered None — dvir_a · 2026-10-16
- 24 AI Systems Recommend $314 Per Visit in Care vs Physicians' $97, a 3.2x Gap — dvir_a · 2026-10-16