Artificial Intelligence in Orthopaedics: Performance of ChatGPT on Text and Image Questions on a Complete AAOS Orthopaedic In-Training Examination (OITE)
ChatGT performed below all resident classes on the 2019 OITE. Performance on text only questions and questions with images was nearly equal if the image was described by a trained orthopaedic specialist but decreased when using an AI generated description. Recognizing the performance abilities of AI software may provide insight into the current and future applications of this technology into medical education.
Authors
- Brian K. Foster (ORCID: https://orcid.org/0000-0001-6319-5018)
- Louis C. Grandizio (ORCID: https://orcid.org/0000-0002-3551-3266)
- Joel C. Klena (ORCID: https://orcid.org/0000-0002-3435-6035)
- Gabriel S. Makar (ORCID: https://orcid.org/0000-0002-0402-5577)
- Mason J. Shultz
- Daniel S. Hayes (ORCID: https://orcid.org/0000-0002-9512-8319)
- Shahid Manzar
Institutions
- Geisinger Commonwealth School of Medicine (US)
Publication Details
- Journal
- Journal of surgical education
- Published
- 2024-09-14
- DOI
- https://doi.org/10.1016/j.jsurg.2024.08.002
- Citations
- 11
- Primary Topic
- Artificial Intelligence in Healthcare and Education
- Type
- article
- Field-Weighted Citation Impact
- 1.32