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).

Journal: Pediatric surgery international
Published Date: Aug 8, 2025

Abstract

OBJECTIVE: Large language models (LLMs) have advanced rapidly, but their utility in pediatric surgery remains uncertain. This study assessed the performance of three AI models-DeepSeek, Microsoft Copilot (GPT-4) and Google Bard-on the European Pediatric Surgery In-Training Examination (EPSITE).

Authors

  • Richard Gnatzy
    Department of Pediatric Surgery, Leipzig University, Leipzig, Germany.
  • Martin Lacher
    Department of Pediatric Surgery, Leipzig University, Leipzig, Germany.
  • Salvatore Cascio
    Department of Pediatric Surgery, School of Medicine, University College Dublin and Children's Health Ireland at Temple Street, Dublin, Ireland.
  • Oliver Münsterer
    Department of Pediatric Surgery, Dr. Von Hauner Children's Hospital, LMU University Hospital, Munich, Germany.
  • Richard Wagner
    Department of Pediatric Surgery, Leipzig University, Leipzig, Germany.
  • Ophelia Aubert
    Department of Pediatric Surgery, Leipzig University, Leipzig, Germany.

Keywords

External Resources

Popular Topics
Recent Journals