A Comparison of Ten Large Language Models and a Conventional Search Engine for Clinical Decision Support in Anesthesiology: Expert Agreement and Physician Perceptions
Although LLM-generated responses differed in quality, DeepSeek R1 and Claude-Sonnet 3.5 produced answers most consistent with expert clinical judgment. The poor performance of several models, coupled with clinician skepticism, underscores the need for further validation before integrating AI into routine anesthesiology decision support.
Authors
- Thomas M. Hemmerling (ORCID: https://orcid.org/0000-0002-1447-0703)
- Pascal Laferrière-Langlois (ORCID: https://orcid.org/0000-0003-3347-1581)
- Sean Jeffries
- Anil K. Sinha (ORCID: https://orcid.org/0000-0003-2844-7368)
- Robert Harutyunyan (ORCID: https://orcid.org/0000-0003-0982-6741)
- Oliver Cafferty
- Eric D. Pelletier
- Louis-Pierre Poulin
Institutions
- McGill University (CA)
- Université de Montréal (CA)
Publication Details
- Journal
- Anesthesia & Analgesia
- Published
- 2026-01-29
- DOI
- https://doi.org/10.1213/ane.0000000000007864
- Primary Topic
- Artificial Intelligence in Healthcare and Education
- Type
- article
- Field-Weighted Citation Impact
- 0.00