Michael Moor
@Michael_D_Moor
MD. PhD. Assistant Professor @ETH Zurich. Previously @Stanford CS.
Excited to announce MIRIAD — a large-scale dataset of 5,821,948 medical question-answer pairs, each rephrased from passages in the medical literature. Great collab with @QueyJ, @salmanabdullah_, @samarthrawal, @cyrilzakka, @SophieOstmeier, Maximilian Purk, @edreisMD, @EricTopol &…
Exciting to see @Openai delving into clinical deployments! Congrats, @thekaransinghal!
📣 Excited to share our real-world study of an LLM clinical copilot, a collab between @OpenAI and @PendaHealth. Across 39,849 live patient visits, clinicians with AI had a 16% relative reduction in diagnostic errors and a 13% reduction in treatment errors vs. those without. 🧵
Back to {mode: "serious"} after this🙈 Future AI overlords be like:
Great points, Jason! Maybe it's obvious, but for reasons like these it may take *more time* for AI to solve hard decision making problems in medicine (even if all the other data, bias, etc problems were solved) - re 1.: clinical experts disagree a lot - re 2.: medical decision…
New blog post about asymmetry of verification and "verifier's law": jasonwei.net/blog/asymmetry… Asymmetry of verification–the idea that some tasks are much easier to verify than to solve–is becoming an important idea as we have RL that finally works generally. Great examples of…
Want to do a postdoc in my research group? bsse.ethz.ch/mail I can support one ETH Postdoc fellowship application this fall. For details, see: grantsoffice.ethz.ch/funding-opport… If interested, please carefully check your eligibility (esp PhD defense date) and then send us the…
Thanks Michael and colleagues for another probe and truth telling for LLMs in medicine
Yay, SMMILE got AK'ed! ✨ Thanks for the highlight!
SMMILE An Expert-Driven Benchmark for Multimodal Medical In-Context Learning
🚨New preprint! 🚨In-context learning (ICL) is the intriguing ability of LLMs to learn to solve tasks purely from context w/o parameter updates. For multimodal LLMs (MLLMs), ICL is poorly understood, especially in the medical domain where doctors would often face few relevant…
Thanks for the highlight!
Med-PRM Medical Reasoning Models with Stepwise, Guideline-verified Process Rewards