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

Re:OpenAI's o1 correctly diagnosed 67% of ER patients vs. 50... by dyauspitr on Sunday May 03, 2026 @04:55PM (#48001378)

I think the bigger takeaway here is that 50% of the time doctors will miss what you have.

[ Parent | on HN ]

Re:OpenAI's o1 correctly diagnosed 67% of ER patients vs. 50... by gpm on Sunday May 03, 2026 @04:58PM (#48001413)

That's not a takeaway here at all.

It's 50% of the time ER doctors working solely from notes, something they never do, in a situation they know is only for a study, will miss what you have.

In real clinical situations the doctors see, hear, smell, and interact with the patients.

[ Parent | on HN ]

Re:OpenAI's o1 correctly diagnosed 67% of ER patients vs. 50... by lokar on Sunday May 03, 2026 @05:53PM (#48001946)

Also, it just says they did not make the "correct" call, but that could mean they ordered an extra test, or took a more conservative route for treatment.

[ Parent | on HN ]

Re:OpenAI's o1 correctly diagnosed 67% of ER patients vs. 50... by ngokevin on Sunday May 03, 2026 @04:58PM (#48001406)

I believe in modern medicine but I lost some faith in the American institutions around it when I "diagnosed" my partner with the correct disease that the first rheumatologist dismissed and told them to just stretch. It was officially diagnosed years later, and we lost a lot of time because of it.

[ Parent | on HN ]

Re:OpenAI's o1 correctly diagnosed 67% of ER patients vs. 50... by oofbey on Sunday May 03, 2026 @07:27PM (#48002712)

I’m so sorry. American medical institutions are a very long way from the best way to practice medicine.

[ Parent | on HN ]

Re:OpenAI's o1 correctly diagnosed 67% of ER patients vs. 50... by rrr_oh_man on Monday May 04, 2026 @02:38AM (#48005376)

Why is this being downvoted?

And which institutions are best?

[ Parent | on HN ]