Large Language Models in Surgery: Promise, Pitfalls, and Practical Use
Journal of Abdominal Wall Surgery · 26.03.2026 · 5
DOI: 10.3389/jaws.2026.16349 ↗Kurz gefasst
Übersichtsarbeit in der Zeitschrift Journal of Abdominal Wall Surgery, online erschienen am 26.03.2026. Verfasst von Danette T Denham und 4 weiteren Autor:innen. Beteiligte Einrichtung: Division of Gastrointestinal and General Surgery, Department of Surgery, Endeavor Health, Evanston, IL, United States. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 87 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Background
Large Language Models (LLMs) represent a transformative advancement in artificial intelligence (AI) with rapidly expanding applications in medicine. While AI-related medical publications increased 36-fold between 2000–2022, practical guidance for surgeons remains limited. This mini-review delineates pragmatic applications of LLMs in surgical practice while addressing key limitations, implementation considerations, and ethical considerations.
Methods
We reviewed contemporary LLM platforms and their integration into clinical workflows, patient communication, surgical research and academic writing, evaluating both benefits, constraints and risk mitigation relevant to practicing surgeons.
Findings
LLMs demonstrate significant utility across multiple domains. In clinical workflows, ambient documentation and chart summarization may reduce documentation burden and support rapid synthesis of complex patient data. For patient communication, these tools can simplify complex medical information, tailor or translate patient instructions to appropriate reading levels or languages, and generate empathetic responses to patient messages with improved efficiency. In research, LLMs assist with literature summarization, study design optimization, and risk of bias assessment in RCT, allowing surgeons to focus on higher-level scientific reasoning. Despite promising applications, several constraints demand attention. Effective prompting requires specific techniques including clear clinical objectives, explicit instructions, and iterative refinement. LLM outputs require verification to prevent “hallucinations” - fabricated or inaccurate information. Protected health information (PHI) must never be entered into public LLM platforms to maintain HIPAA compliance. Liability frameworks for AI-generated errors remain ambiguous, with unclear responsibility deferred amongst providers, institutions, and developers.
Conclusion
LLMs offer surgeons valuable tools for enhancing workflow efficiency and patient communication when deployed with appropriate oversight. Success requires understanding prompt engineering principles, maintaining rigorous fact-checking protocols, protecting patient privacy, and recognizing that human judgment remains irreplaceable in clinical decision-making.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Division of Gastrointestinal and General Surgery, Department of Surgery, Endeavor Health, Evanston, IL, United States.
Zitieren
APA
Denham, D. T., Wang, C. Y., Maric, E., Hinton, L. R., & Heniford, B. T. (2026). Large Language Models in Surgery: Promise, Pitfalls, and Practical Use. Journal of Abdominal Wall Surgery, 5. https://doi.org/10.3389/jaws.2026.16349
Vancouver
Denham DT, Wang CY, Maric E, Hinton LR, Heniford BT. Large Language Models in Surgery: Promise, Pitfalls, and Practical Use. Journal of Abdominal Wall Surgery. 2026;5. doi:10.3389/jaws.2026.16349
BibTeX
@article{Denham2026,
author = {Denham, Danette T and Wang, Colin Y and Maric, Emil and Hinton, Lucy R and Heniford, B Todd},
title = {Large Language Models in Surgery: Promise, Pitfalls, and Practical Use},
journal = {Journal of Abdominal Wall Surgery},
year = {2026},
volume = {5},
doi = {10.3389/jaws.2026.16349}
}
EUVIMED