EUVIMEDEUVIMED entdecken
LeitlinieOpen Access · CC BY-NC-ND 4.0

Using a customized GPT to provide guideline-based recommendations for management of pancreatic cystic lesions

Yuri Gorelik iD, Itai Ghersin, Tarek Arraf, Offir Ben-Ishay iD, Amir Klein, Iyad Khamaysi

Endoscopy International Open · 01.04.2024 · 12 (04) · E600-E603

DOI: 10.1055/a-2289-9334 ↗

Kurz gefasst

Leitlinie in der Zeitschrift Endoscopy International Open, erschienen am 01.04.2024. Verfasst von Yuri Gorelik und 5 weiteren Autor:innen. Beteiligte Einrichtung: Gastroenterology, Department of Internal Medicine D, Rambam Health Care Campus, Haifa, Israel. Die Arbeit wurde bisher 23-mal zitiert (Crossref) und nennt 12 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background and study aims Rising prevalence of pancreatic cysts and inconsistent management guidelines necessitate innovative approaches. New features of large language models (LLMs), namely custom GPT creation, provided by ChatGPT can be utilized to integrate multiple guidelines and settle inconsistencies.

Methods

A custom GPT was developed to provide guideline-based management advice for pancreatic cysts. Sixty clinical scenarios were evaluated by both the custom GPT and gastroenterology experts. A consensus was reached between experts and review of guidelines and the accuracy of recommendations provided by the custom GPT was evaluated and compared with experts.

Results

The custom GPT aligned with expert recommendations in 87% of scenarios. Initial expert recommendations were correct in 97% and 87% of cases, respectively. No significant difference was observed between the accuracy of custom GPT and the experts. Agreement analysis using Cohen's and Fleiss' Kappa coefficients indicated consistency among experts and the custom GPT.

Conclusions

This proof-of-concept study shows the custom GPT's potential to provide accurate, guideline-based recommendations for pancreatic cyst management, comparable to expert opinions. The study highlights the role of advanced features of LLMs in enhancing clinical decision-making in fields with significant practice variability.

Schlagwörter

Stichwörter der Autor:innen

Endoscopic ultrasonographyFine-needle aspiration/biopsyMRCP topicsPancreasPancreatobiliary (ERCP/PTCD)

Autor:innen und Institutionen

  • Gastroenterology, Department of Internal Medicine D, Rambam Health Care Campus, Haifa, Israel.
  • Surgery, Rambam Health Care Campus, Haifa, Israel.
  • Gastroenterology, Rambam MC, Kfar Kana, Israel.

ORCID-Profile: Yuri Gorelik, Offir Ben-Ishay

Zitieren

APA

Gorelik, Y., Ghersin, I., Arraf, T., Ben-Ishay, O., Klein, A., & Khamaysi, I. (2024). Using a customized GPT to provide guideline-based recommendations for management of pancreatic cystic lesions. Endoscopy International Open, 12(04), E600-E603. https://doi.org/10.1055/a-2289-9334

Vancouver

Gorelik Y, Ghersin I, Arraf T, Ben-Ishay O, Klein A, Khamaysi I. Using a customized GPT to provide guideline-based recommendations for management of pancreatic cystic lesions. Endoscopy International Open. 2024;12(04):E600-E603. doi:10.1055/a-2289-9334

BibTeX
@article{Gorelik2024,
  author = {Gorelik, Yuri and Ghersin, Itai and Arraf, Tarek and Ben-Ishay, Offir and Klein, Amir and Khamaysi, Iyad},
  title = {Using a customized GPT to provide guideline-based recommendations for management of pancreatic cystic lesions},
  journal = {Endoscopy International Open},
  year = {2024},
  volume = {12},
  number = {04},
  pages = {E600--E603},
  doi = {10.1055/a-2289-9334}
}
Kostenlos starten →