Artificial Intelligence Augmentation: Performance of GPT-4 and GPT-3.5 on the Plastic Surgery In-service Examination
GPT-4 outperformed its predecessor but only scored in the 15th percentile compared with postgraduate year-6 residents. More refinement is needed to achieve performance metrics equivalent to an attending plastic surgeon and become a valuable tool for surgical education.
Authors
- Erik Reiche (ORCID: https://orcid.org/0009-0009-0578-0011)
- Paige M. Fox (ORCID: https://orcid.org/0000-0002-4166-8547)
- Sthefano Araya (ORCID: https://orcid.org/0000-0002-8245-8036)
- Farrah C. Liu
- Daniel Najafali (ORCID: https://orcid.org/0000-0003-1509-9229)
- Manuel Orellana (ORCID: https://orcid.org/0000-0002-3242-6271)
- Amir H. Dorafshar (ORCID: https://orcid.org/0000-0001-7045-3601)
- Justin M. Camacho
- Sameer A. Patel (ORCID: https://orcid.org/0000-0002-1924-9215)
- Shane Douglas Morrison (ORCID: https://orcid.org/0000-0003-3868-3532)
- Justin M. Broyles (ORCID: https://orcid.org/0000-0003-0277-8046)
- Leonard Knoedler (ORCID: https://orcid.org/0009-0009-4279-5669)
Institutions
- Brigham and Women's Hospital (US)
- Rush University Medical Center (US)
- Fox Chase Cancer Center (US)
- Harvard University (US)
- University of Illinois Urbana-Champaign (US)
- Illinois College (US)
- University of Washington (US)
- UCLA Medical Center (US)
- University of Washington Medical Center (US)
- Harborview Medical Center (US)
- University Hospital Regensburg (DE)
- Harbor–UCLA Medical Center (US)
- Temple University (US)
- Stanford University (US)
Publication Details
- Journal
- Plastic & Reconstructive Surgery Global Open
- Published
- 2025-04-01
- DOI
- https://doi.org/10.1097/gox.0000000000006645
- Citations
- 4
- Primary Topic
- Artificial Intelligence in Healthcare and Education
- Type
- article
- Field-Weighted Citation Impact
- 2.62