Assessing Interrater Reliability of ChatGPT-4 and Orthopaedic Clinicians in Radiographic Fracture Classification
Although ChatcGPT-4 showed promise in classifying basic fracture features, it was not yet at a level comparable to experts, especially with more nuanced interpretations. These findings suggest that the use of AI is more effective as an adjunct to the judgment of trained clinicians rather than a replacement for it.
Authors
- Hania Shahzad (ORCID: https://orcid.org/0000-0002-1643-0828)
- Om Prakash Patel (ORCID: https://orcid.org/0000-0002-5295-4880)
- Samuel K. Simister (ORCID: https://orcid.org/0000-0001-6441-7815)
- Patrick Wise (ORCID: https://orcid.org/0000-0001-7618-3681)
- Augustine M. Saiz (ORCID: https://orcid.org/0000-0002-1955-8667)
- Shannon Tse (ORCID: https://orcid.org/0000-0003-0370-2377)
- Zachary C. Lum (ORCID: https://orcid.org/0000-0002-5871-8539)
- Aliyah N. Walker
- James B. Smith (ORCID: https://orcid.org/0009-0005-6967-1632)
- Michelle Scott
- Soham Choudhary
- Michael Seidu
- David Dallas‐Orr
Institutions
- University of California Davis Medical Center (US)
- University of California, Davis (US)
Publication Details
- Journal
- Journal of Orthopaedic Trauma
- Published
- 2025-09-19
- DOI
- https://doi.org/10.1097/bot.0000000000003079
- Primary Topic
- Artificial Intelligence in Healthcare and Education
- Type
- article
- Field-Weighted Citation Impact
- 0.00