EUVIMEDEUVIMED entdecken
Crossref

Training ChatGPT for surgical decisions: Bariatric surgery analysis using algorithms and evidence

Sergi Sanchez-Cordero, Ruth Lopez-Gonzalez, Helena Fernandez, Jordi Pujol-Gebellí

Obesity Research & Clinical Practice · 2025

DOI: 10.1016/j.orcp.2025.08.002 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Obesity Research & Clinical Practice, 2025. Verfasst von Sergi Sanchez-Cordero und 3 weiteren Autor:innen. Beteiligte Einrichtung: Bariatric Surgery, Moises Broggi University Hospital, Barcelona, Spain. Hauptthemen laut MEDLINE: Bariatric Surgery, Obesity, Morbid, Algorithms, Clinical Decision-Making. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 12 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

BACKGROUND: Selecting the most appropriate bariatric surgery (BS) technique is a complex, individualized process. Artificial intelligence (AI) tools like ChatGPT may assist, but their clinical utility is unclear. This study evaluates whether ChatGPT's recommendations for BS improve after exposure to scientific literature and how they align with real-world clinical decisions. METHODS: A retrospective single-center study included 283 patients who underwent primary BS between 2023 and 2025. No exclusion criteria were applied. Clinical variables (age, sex, BMI, comorbidities, and preoperative data) were collected. ChatGPT was asked to recommend the most suitable BS technique for each patient profile, first without context and then after being exposed to 412 open-access scientific articles. Recommendations were compared with actual clinical decisions using percentage agreement and Cohen's Kappa. RESULTS: Initially, ChatGPT favored sleeve gastrectomy (SG, 56.8 %), followed by Roux-en-Y gastric bypass (RYGB, 26.8 %) and one-anastomosis gastric bypass (OAGB, 16.4 %); SADI-S was never suggested. Concordance with clinical practice was 20.0 % (Kappa = 0.003; p = 0.96). After training, SG recommendations decreased (35.7 %), RYGB increased (30.3 %), SADI-S emerged (17.1 %), and dual options appeared in 4 %. Concordance improved modestly to 25.8 % (Kappa = 0.068; p = 0.29), with a significant shift in global distribution (p < 0.00001). CONCLUSIONS: ChatGPT adapts its recommendations after contextual training, but concordance with clinical judgment remains low. While potentially useful as an educational tool, ChatGPT is not yet reliable for autonomous surgical decision-making.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Bariatric SurgeryObesity, MorbidAlgorithmsClinical Decision-MakingArtificial IntelligenceHumansMaleFemaleRetrospective StudiesAdultMiddle AgedGenerative Artificial Intelligence

Stichwörter der Autor:innen

Artificial intelligenceBariatric surgeryChatGPTClinical concordanceContextual trainingSurgical decision-making

Autor:innen und Institutionen

  • Bariatric Surgery, Moises Broggi University Hospital, Barcelona, Spain.
  • Bariatric Surgery, Moises Broggi University Hospital, Barcelona, Spain. Electronic address: ruthlopez013@gmail.com.
  • General and Digestive Surgery, Moises Broggi University Hospital, Barcelona, Spain.

Zitieren

APA

Sanchez-Cordero, S., Lopez-Gonzalez, R., Fernandez, H., & Pujol-Gebellí, J. (2025). Training ChatGPT for surgical decisions: Bariatric surgery analysis using algorithms and evidence. Obesity Research & Clinical Practice. https://doi.org/10.1016/j.orcp.2025.08.002

Vancouver

Sanchez-Cordero S, Lopez-Gonzalez R, Fernandez H, Pujol-Gebellí J. Training ChatGPT for surgical decisions: Bariatric surgery analysis using algorithms and evidence. Obesity Research & Clinical Practice. 2025. doi:10.1016/j.orcp.2025.08.002

BibTeX
@article{SanchezCordero2025,
  author = {Sanchez-Cordero, Sergi and Lopez-Gonzalez, Ruth and Fernandez, Helena and Pujol-Gebellí, Jordi},
  title = {Training ChatGPT for surgical decisions: Bariatric surgery analysis using algorithms and evidence},
  journal = {Obesity Research & Clinical Practice},
  year = {2025},
  doi = {10.1016/j.orcp.2025.08.002}
}
Kostenlos starten →