Copyright
©The Author(s) 2025. Published by Baishideng Publishing Group Inc. All rights reserved.
World J Gastrointest Oncol. Dec 15, 2025; 17(12): 114341
Published online Dec 15, 2025. doi: 10.4251/wjgo.v17.i12.114341
Published online Dec 15, 2025. doi: 10.4251/wjgo.v17.i12.114341
Cost vs clinical utility on application of large language models in clinical practice: A double-edged sword
Sunny Chi Lik Au, School of Clinical Medicine, The University of Hong Kong, Hong Kong 999077, China
Author contributions: Au SCL drafted the manuscript, acquired and analyzed the data, and revised the manuscript.
Conflict-of-interest statement: The author reports no relevant conflicts of interest for this article.
Open Access: This article is an open-access article that was selected by an in-house editor and fully peer-reviewed by external reviewers. It is distributed in accordance with the Creative Commons Attribution NonCommercial (CC BY-NC 4.0) license, which permits others to distribute, remix, adapt, build upon this work non-commercially, and license their derivative works on different terms, provided the original work is properly cited and the use is non-commercial. See: https://creativecommons.org/Licenses/by-nc/4.0/
Corresponding author: Sunny Chi Lik Au, Chief Physician, Clinical Assistant Professor (Honorary), Research Fellow, School of Clinical Medicine, The University of Hong Kong, 9/F, MO Office, Lo Ka Chow Memorial Ophthalmic Centre, No. 19 Eastern Hospital Road, Causeway Bay, Hong Kong 999077, China. kilihcua@gmail.com
Received: September 16, 2025
Revised: September 26, 2025
Accepted: October 27, 2025
Published online: December 15, 2025
Processing time: 86 Days and 0.2 Hours
Revised: September 26, 2025
Accepted: October 27, 2025
Published online: December 15, 2025
Processing time: 86 Days and 0.2 Hours
Core Tip
Core Tip: As large language models increasingly permeate medical workflows, this study offers insight into 3 areas: Performance parity, cost democratization, and clinical readiness. Perhaps one potentially compelling finding was cost efficiency. Yet cost-effectiveness alone does not ensure clinical utility. Notably, the study relied exclusively on text-based prompts, omitting multimodal data such as photographs or scans. This is an important limitation in a domain like endoscopy, which often can be driven visually. Large language model performance can drop precipitously when deprived of image context. Without multimodal integration, artificial intelligence tools may inevitably fail to capture key diagnostic signals.