Download PDF
CC BY-NC-ND 4.0 · Endosc Int Open 2024; 12(06): E811
DOI: 10.1055/a-2335-8405
Letter to the editor

Reply to Daungsupawong and Wiwanitkit

Yuri Gorelik 
1   Department of Internal Medicine D, Gastroenterology, Rambam Health Care Campus, Haifa, Israel (Ringgold ID: RIN58878)
› Author Affiliations
› Further Information
Also available at
   Permissions and Reprints

Letter to:

Comment on “Using a customized GPT to provide guideline-based recommendations for management of pancreatic cystic lesions”Endosc Int Open 2024; 12(06): E810-E810
DOI: 10.1055/a-2335-8369

Dear Editor, Dr. Ray, and Dr. Wiwanitkit

I have carefully read your letter and the important issues raised in it regarding our work on the evaluation of custom ChatGPT agents in the management of pancreatic cystic lesions [1] [2]. I agree with the limitations you have pointed out, keeping in mind that this study is intended as a proof of concept for a novel feature of large language models (LLMs). Although 60 scenarios is not a large sample size, most similar studies in the field of gastroenterology and LLMs studied a similar number of scenarios [3] [4] [5]. The issue of interrogation of discrepancies as part of a systemic approach to the development and training of LLMs should indeed be further implemented and improved. An example of such a systemic approach is described in a recent work that evaluated various setups using ChatGPT for management of hepatitis C infection [5]. The ethical considerations including bias and error handling and user responsibility should also be explored. Hopefully, these issues will be addressed gradually in future studies as this field of currently novel research progresses from generated scenarios to evaluation on clinical data and prospective interventional studies.



Publication History

Received: 07 May 2024

Accepted: 24 May 2024

Article published online:
20 June 2024

© 2024. The Author(s). This is an open access article published by Thieme under the terms of the Creative Commons Attribution-NonDerivative-NonCommercial-License, permitting copying and reproduction so long as the original work is given appropriate credit. Contents may not be used for commercial purposes, or adapted, remixed, transformed or built upon. (https://creativecommons.org/licenses/by-nc-nd/4.0/).

Georg Thieme Verlag KG
Rüdigerstraße 14, 70469 Stuttgart, Germany

 

  • References

  • 1 Daungsupawong H, Wiwanitkit V. Comment on “Using a customized GPT to provide guideline-based recommendations for management of pancreatic cystic lesions” Title. Endosc Int Open 2024; 12: 810
    Article in Thieme ConnectPubMedGoogle Scholar
  • 2 Gorelik Y, Ghersin I, Arraf T. et al. Using a customized GPT to provide guideline-based recommendations for management of pancreatic cystic lesions. Endosc Int Open 2024; 12: E600-E603 DOI: 10.1055/a-2289-9334. (PMID: 38681146)
    Article in Thieme ConnectPubMedGoogle Scholar
  • 3 Pugliese N, Wai-Sun Wong V, Schattenberg JM. et al. Accuracy, reliability, and comprehensibility of ChatGPT-generated medical responses for patients with nonalcoholic fatty liver disease. Clin Gastroenterol Hepatol 2024; 22: 886-889.e5
    CrossrefPubMedGoogle Scholar
  • 4 Levartovsky A, Ben-Horin S, Kopylov U. et al. Towards AI-augmented clinical decision-making: An examination of ChatGPT’s utility in acute ulcerative colitis presentations. Am J Gastroenterol 2023; 118: 2283-2289 DOI: 10.14309/ajg.0000000000002483. (PMID: 37611254)
    CrossrefPubMedGoogle Scholar
  • 5 Kresevic S, Giuffrè M, Ajcevic M. et al. Optimization of hepatological clinical guidelines interpretation by large language models: a retrieval augmented generation-based framework. NPJ Digit Med 2024 71 2024; 7: 1-9 DOI: 10.1038/s41746-024-01091-y. (PMID: 38654102)
    CrossrefPubMedGoogle Scholar