Dossier
clinical LLMs
Coverage of clinical LLMs in the Nexus archive.
- STAT+: Why benchmarking clinical LLMs from OpenEvidence, Doximity is complicated
A study in Nature Medicine compared clinical AI systems OpenEvidence and UpToDate Expert AI against general LLMs, sparking debate in the clinical AI community. The article discusses challenges in benchmarking these systems, emphasizing that headline-driven summaries often oversimplify complex results.