Artificial intelligence as a surgical advisor before a DIEP breast reconstruction. A blinded comparative study of three large language models
Each LLM showed distinct strength ChatGPT produced the most accurate answers, Copilot the most informative, and Gemini the simplest language. No model was uniformly superior. These findings support supervised, task-specific use of LLMs in patient education for breast reconstruction.
Authors
- Sebastian Holm (ORCID: https://orcid.org/0000-0002-2234-992X)
- Oriana Haran (ORCID: https://orcid.org/0000-0001-8848-4529)
- Åsa Edsander-Nord
- Nathalie Mobargha (ORCID: https://orcid.org/0000-0001-6442-3430)
- Mattias Lidén
- Johann Zdolsek
- Stina Rittri (ORCID: https://orcid.org/0000-0002-2711-1216)
- Karin Säljö
- Tava Barivan
- Reza Tabrisi
- Ann-Charlott Docherty Skogh
Institutions
- Karolinska University Hospital (SE)
- Örebro University (SE)
- Sahlgrenska University Hospital (SE)
- Karolinska Institutet (SE)
- Texas Plastic Surgery (US)
- University of Gothenburg (SE)
Publication Details
- Journal
- JPRAS Open
- Published
- 2026-01-05
- DOI
- https://doi.org/10.1016/j.jpra.2025.12.029
- Citations
- 1
- Primary Topic
- Artificial Intelligence in Healthcare and Education
- Type
- article
- Field-Weighted Citation Impact
- 17.70