Advancements in large language model accuracy for answering physical medicine and rehabilitation board review questions
LLM technology is rapidly advancing, with the more recent GPT-4o model performing much better on PM&R knowledge questions compared to GPT-3.5. There is potential for LLMs in augmenting clinical practice, medical training, and patient education. However, the technology has limitations and physicians should remain cautious in using it in practice at this time.
Authors
- Alexander D’Angelo
- Jason Bitterman
- James E. Eubanks (ORCID: https://orcid.org/0000-0003-2108-0524)
- Alexandra Holachek
Institutions
- Hartford Hospital (US)
- Medical University of South Carolina (US)
- University of Pittsburgh Medical Center (US)
- Hartford Financial Services (United States)
- University of Nebraska Medical Center (US)
Publication Details
- Journal
- PM&R
- Published
- 2025-05-02
- DOI
- https://doi.org/10.1002/pmrj.13386
- Citations
- 3
- Primary Topic
- Artificial Intelligence in Healthcare and Education
- Type
- article
- Field-Weighted Citation Impact
- 1.96