News for hackers. Stuff that matters.

A comment on OpenAI's o1 correctly diagnosed 67% of ER patients vs. 50-55% by triage doctors. Parent comment

Re:OpenAI's o1 correctly diagnosed 67% of ER patients vs. 50... by brikym on Sunday May 03, 2026 @05:30PM (#48001712)
I think it's plausible since doctors tend to have human cognitive biases and miss things. People tend to fixate on patterns they're most familiar with.
[ Parent | on HN ]
Re:OpenAI's o1 correctly diagnosed 67% of ER patients vs. 50... by namuol on Sunday May 03, 2026 @05:34PM (#48001757)
A bold claim to suggest that LLMs aren’t prone to biases of their own which are less understood.
[ Parent | on HN ]
Re:OpenAI's o1 correctly diagnosed 67% of ER patients vs. 50... by mitkebes on Sunday May 03, 2026 @09:42PM (#48003668)
LLMs are having pretty consistent studies into their biases. Obviously this doesn't mean we know all the biases, but it's being actively worked on.

Meanwhile with human doctors, every one of them is a unique person with a completely different set of biases. In my experience, getting a correct diagnosis or treatment plan often involves trying multiple doctors, because many of them will jump to a common diagnosis even if the symptoms don't line up and the treatment doesn't actually help.

[ Parent | on HN ]