Currently submitted to: JMIR AI
Date Submitted: Aug 21, 2026
Open Peer Review Period: Aug 28, 2026 - Oct 23, 2026
(currently open for review)
Warning: This is an author submission that is not peer-reviewed or edited. Preprints - unless they show as "accepted" - should not be relied on to guide clinical practice or health-related behavior and should not be reported in news media as established information.
Use of large language models by academic hospitalists: results of a multicenter survey
ABSTRACT
Background:
Large language models (LLMs) are increasingly available in clinical settings, yet little is known about how hospitalists use them at the point of care.
Objective:
We sought to understand how hospitalists use LLMs, what tools they prefer, and the perceived barriers to using LLMs in their practice.
Methods:
We surveyed academic hospitalists across eight institutions in a multicenter network to characterize LLM use, preferred tools, and perceived barriers.
Results:
Of 255 respondents, 170 (67.1%) reported ever using an LLM clinically, though only half of LLM users reported doing so frequently. OpenEvidence was the tool most commonly used. LLMs were applied primarily to diagnostic (77.1%) and management (77.6%) questions, and less often to documentation or patient communication. The most frequently cited barriers were lack of trust in outputs (49.8%), uncertainty about institutional policy (48.6%), and limited access to tools approved for protected health information (43.1%).
Conclusions:
LLM use among academic hospitalists is common and centered on clinical reasoning, but broader adoption is constrained by concerns about trust, governance, and secure access.
Citation
Request queued. Please wait while the file is being generated. It may take some time.
Copyright
© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.