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

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.

Object Details

• Location: Deutsche Nationalbibliothek Frankfurt am Main
• Extent: Online-Ressource
• Language: Englisch

References and Relationships

• Bibliographic citation: Using a customized GPT to provide guideline-based recommendations for management of pancreatic cystic lesions ; volume:12 ; number:04 ; year:2024 ; pages:E600-E603 ; Endoscopy International Open ; 12, Heft 04 (2024), E600-E603

Contributors, Places and Time

• Contributor: Gorelik, Yuri ; Ghersin, Itai ; Arraf, Tarek ; Ben-Ishay, Offir ; Klein, Amir ; Khamaysi, Iyad

Further information

• DOI: 10.1055/a-2289-9334
• URN: urn:nbn:de:101:1-2406201019523.348014223937
• Rights: Open Access; Der Zugriff auf das Objekt ist unbeschränkt möglich.
• Last update: 14.08.2025, 10:52 AM CEST