Evaluating the Evolution of ChatGPT as an Information Resource in Shoulder and Elbow Surgery
ChatGPT 3.5 and 4 exceeded the proficiency threshold. ChatGPT 4 performed better than ChatGPT 3.5, showing an increased capability to correctly answer shoulder and elbow-focused questions. Further refinement of ChatGPT's training may improve its performance and utility as a resource. Currently, ChatGPT remains unable to answer questions at a high enough accuracy to replace clinical decision-making. [<i>Orthopedics</i>. 2025;48(2):e69-e74.].
Authors
- Christopher S. Klifto (ORCID: https://orcid.org/0000-0001-8046-2085)
- Bradley S. Schoch (ORCID: https://orcid.org/0000-0002-9355-5069)
- Keith T. Aziz (ORCID: https://orcid.org/0000-0003-4034-1750)
- Alexandra Bechtle (ORCID: https://orcid.org/0000-0002-3155-3981)
- Jennifer Traverse
- Benjamin Nieves-Lopez
Institutions
- Mayo Clinic in Florida (US)
Publication Details
- Journal
- Orthopedics
- Published
- 2025-01-29
- DOI
- https://doi.org/10.3928/01477447-20250123-03
- Citations
- 4
- Primary Topic
- Artificial Intelligence in Healthcare and Education
- Type
- article
- Field-Weighted Citation Impact
- 2.62