When OpenEvidence took the US Medical Licensing Exam recently, it was wrong 9% of the time
The passing score for USMLE is ~200 out of 300… how many “wrong times” is that?
OpenEvidence Sounds Promising, but is it Reliable?
Submitted 2 months ago by liv@beehaw.org to technology@beehaw.org
https://medium.com/@underwaterchimp/openevidence-sounds-promising-but-is-it-reliable-0b5f49fb8d5c
Comments
jarfil@beehaw.org 2 months ago
liv@lemmy.nz 2 months ago
When we look at passing scores, is there any way to quantitatively grade them for magnitude?
Not all bad advice is created equal.
jarfil@beehaw.org 2 months ago
The grading is a mess. It goes about qualitative, quantitative… and statistical corrections “to make it fair”.
Anyway, there is ~30% margin on the scores for passing, so chances are that 9% is better than the worst doctor who still “passed”.
technocrit@lemmy.dbzer0.com 2 months ago
It’s not reliable. The name itself is misleading. The “evidence” is apparently already open. Is the statistical model actually open? Probably not.
More accurate name: ClosedSummary
liv@beehaw.org 2 months ago
Article about an AI that aims to give treatment suggestions to doctors.