Pediatric surgical trainees and artificial intelligence: a comparative analysis of DeepSeek, Copilot, Google Bard and pediatric surgeons’ performance on the European Pediatric Surgical In-Training Examinations (EPSITE)
LLMs show variable performance in pediatric surgery, with newer models like DeepSeek demonstrating marked improvement. These findings highlight the rapid progression of LLM capabilities and emphasize the need for ongoing evaluation before clinical integration, especially in high-stakes decision-making contexts.
Authors
- Ophelia Aubert (ORCID: https://orcid.org/0009-0007-4785-6462)
- Richard Wagner (ORCID: https://orcid.org/0000-0002-3035-2619)
- Martin Lacher (ORCID: https://orcid.org/0000-0002-4616-9464)
- Richard Gnatzy
- Salvatore Cascio
- Oliver Münsterer
Institutions
- University College Dublin (IE)
- Heidelberg University (DE)
- University Hospital Heidelberg (DE)
- Children's Health Ireland at Crumlin (IE)
- University Children's Hospital Tübingen (DE)
- University Hospital Leipzig (DE)
- University Medical Centre Mannheim (DE)
- Ludwig-Maximilians-Universität München (DE)
Publication Details
- Journal
- Pediatric Surgery International
- Published
- 2025-08-08
- DOI
- https://doi.org/10.1007/s00383-025-06104-9
- Citations
- 3
- Primary Topic
- Artificial Intelligence in Healthcare and Education
- Type
- article
- Field-Weighted Citation Impact
- 1.96