Class in Session: Analysis of GPT-4-created Plastic Surgery In-service Examination Questions
Our study found that GPT-4 can be adapted to generate practice questions for the 2022 PSITE, but its questions are of poor quality. The program can offer general explanations for both the correct and incorrect answer options but was observed to generate false information and poor-quality explanations. Although trainees should navigate with caution as the technology develops, GPT-4 has the potential to serve as an effective educational adjunct under the supervision of trained plastic surgeons.
Authors
- Leonard Knoedler (ORCID: https://orcid.org/0000-0002-8949-3168)
- Daniel Najafali (ORCID: https://orcid.org/0000-0003-1509-9229)
- Victoria Stoffel (ORCID: https://orcid.org/0000-0003-2223-3705)
- Justin M. Camacho
- Isabel Herzog (ORCID: https://orcid.org/0000-0001-7491-5746)
- Logan Galbraith (ORCID: https://orcid.org/0009-0000-4508-4445)
- Stephanie L. Taiberg (ORCID: https://orcid.org/0009-0003-4416-7101)
- Civanni Moss
Institutions
- University Hospital Regensburg (DE)
- Drexel University (US)
- Northeast Ohio Medical University (US)
Publication Details
- Journal
- Plastic & Reconstructive Surgery Global Open
- Published
- 2024-09-01
- DOI
- https://doi.org/10.1097/gox.0000000000006185
- Citations
- 5
- Primary Topic
- Artificial Intelligence in Healthcare and Education
- Type
- article
- Field-Weighted Citation Impact
- 0.60