
Dr. Hashim Azeez
145 posts




Preprint out today that tests o1-preview's medical reasoning experiments against a baseline of 100s of clinicians. In this case the title says it all: Superhuman performance of a large language model on the reasoning tasks of a physician Link: arxiv.org/abs/2412.10849 A 🧵⬇️




@manikbasha2197 Nothing wrong in knowing it. Knowledge is great! Nothing wrong in not knowing it too!!! It’s inconsequential. That’s the point. You should be able to detect a murmur! That improves PPV of Echo. Beyond that - if you don’t know it’s ESM - doesn’t matter in today’s world!

MD finals, gastro viva: My examiner asked, ‘What does the scleral color tell you about jaundice type?’ I fumbled. He smirked & said: Lemon-yellow = hemolysis Orange-Y = hepatocellular Green-Y = obstructive Nice trivia, but TBH, no one diagnoses jaundice by its ‘shade.’












Because surgical specialities treat juniors as free labour, expecting them to move mountains while not letting them operate enough to be confident. The problem is with the outdated system of training and not the candidates.







