Kagawa Y. Clinical implications of a machine learning model predicting colorectal polyp recurrence after endoscopic mucosal resection. World J Gastroenterol 2025; 31(22): 107197 [DOI: 10.3748/wjg.v31.i22.107197]
Corresponding Author of This Article
Yoshinori Kagawa, MD, PhD, Chief Physician, Department of Gastroenterological Surgery, Osaka International Cancer Institute, 3-1-69 Otemae, Chuo-ku, Osaka 541-8567, Japan. yoshinori.kagawa@oici.jp
Research Domain of This Article
Oncology
Article-Type of This Article
Letter to the Editor
Open-Access Policy of This Article
This article is an open-access article which was selected by an in-house editor and fully peer-reviewed by external reviewers. It is distributed in accordance with the Creative Commons Attribution Non Commercial (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: http://creativecommons.org/licenses/by-nc/4.0/
World J Gastroenterol. Jun 14, 2025; 31(22): 107197 Published online Jun 14, 2025. doi: 10.3748/wjg.v31.i22.107197
Clinical implications of a machine learning model predicting colorectal polyp recurrence after endoscopic mucosal resection
Yoshinori Kagawa
Yoshinori Kagawa, Department of Gastroenterological Surgery, Osaka International Cancer Institute, Osaka 541-8567, Japan
Author contributions: Kagawa Y wrote the full manuscript of this letter, read and approved the final version of the manuscript to be published.
Conflict-of-interest statement: I have no conflict of interest.
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: Yoshinori Kagawa, MD, PhD, Chief Physician, Department of Gastroenterological Surgery, Osaka International Cancer Institute, 3-1-69 Otemae, Chuo-ku, Osaka 541-8567, Japan. yoshinori.kagawa@oici.jp
Received: March 19, 2025 Revised: April 11, 2025 Accepted: April 23, 2025 Published online: June 14, 2025 Processing time: 85 Days and 18.5 Hours
Abstract
The machine learning model developed by Shi et al for predicting colorectal polyp recurrence after endoscopic mucosal resection represents a significant advancement in the field of clinical gastroenterology. By integrating patient-specific factors, such as age, smoking history, and Helicobacter pylori infection, the eXtreme Gradient Boosting algorithm enables precise personalised colonoscopy follow-up planning and risk assessment. This predictive tool offers substantial benefits by optimising surveillance intervals and directing healthcare resources more efficiently toward high-risk individuals. However, real-world implementation requires consideration of the generalisability of our findings across diverse patient populations and clinician training backgrounds.
Core Tip: This predictive model notably enhanced clinical decision-making for colorectal polyp surveillance, demonstrating high accuracy and ease of clinical implementation through a user-friendly online risk calculator. Although promising, its real-world utility depends on external validation, clinician training, and integration with the existing clinical guidelines.
