Large Language Models for Pediatric Differential Diagnoses in Rural Health Care: Multicenter Retrospective Cohort Study Comparing GPT-3 With Pediatrician Performance
This study demonstrates that a fine-tuned GPT-3 model can provide diagnostic support comparable to pediatricians, particularly for common presentations, in rural health care. Further validation in diverse populations is necessary before clinical implementation.
Authors
- Andrew M. Ibrahim (ORCID: https://orcid.org/0000-0001-5516-8378)
- Masab Mansoor (ORCID: https://orcid.org/0009-0007-4501-7016)
- David Grindem
Institutions
- Texas Tech University (US)
- Columbia University Irving Medical Center (US)
- Mayo Clinic in Arizona (US)
- Edward Via College of Osteopathic Medicine (US)
- Texas Tech University Health Sciences Center (US)
Publication Details
- Journal
- JMIRx Med
- Published
- 2025-03-19
- DOI
- https://doi.org/10.2196/65263
- Citations
- 9
- Primary Topic
- Machine Learning in Healthcare
- Type
- article
- Field-Weighted Citation Impact
- 22.33