Copyright
©The Author(s) 2025. Published by Baishideng Publishing Group Inc. All rights reserved.
World J Gastrointest Surg. Sep 27, 2025; 17(9): 107977
Published online Sep 27, 2025. doi: 10.4240/wjgs.v17.i9.107977
Published online Sep 27, 2025. doi: 10.4240/wjgs.v17.i9.107977
Prediction of parastomal hernia in patients undergoing preventive ostomy after rectal cancer resection using machine learning
Wang-Shuo Yang, Yan-Qi Li, Jun-Bo Hu, Lu Liu, Department of Gastrointestinal Surgery Center, Tongji Hospital, Wuhan 430060, Hubei Province, China
Yang Su, Department of Thoracic Surgery, Zhongnan Hospital of Wuhan University, Wuhan 430071, Hubei Province, China
Meng-Die Liu, Department of Biliary-Pancreatic Surgery, Affiliated Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan 430030, Hubei Province, China
Co-corresponding authors: Yang Su and Meng-Die Liu.
Author contributions: Yang WS wrote the first draft, developed the main ideas, curated the data, designed the methodology, created visualizations, and contributed to review and editing; Su Y developed the main ideas, designed the methodology, performed formal analysis, and contributed to review and editing; Li YQ curated the data and performed formal analysis; Hu JB acquired the funding; Liu L acquired the funding and contributed to review and editing; Liu MD curated the data and supervised the project. This study is a multidisciplinary collaborative project involving clinical surgery, artificial intelligence algorithms, and data analysis. Professor Su Y was responsible for the clinical design and acquisition of patient data, ensuring the clinical relevance and feasibility of the research. Liu MD led the development and optimization of the machine learning models, playing a key role in model selection and performance evaluation. All two authors played indispensable roles in the study and are required to communicate externally to address academic inquiries and technical details. Therefore, designating all three as corresponding authors allows for more comprehensive responses to peer reviews and post-publication queries, ultimately enhancing the quality and impact of the paper.
Institutional review board statement: The study was conducted in strict accordance with the principles outlined in the Declaration of Helsinki and received ethical approval from the local Ethics Committee at Tongji Hospital, Huazhong University of Science and Technology. All procedures adhered to relevant regulations and guidelines. The study was approved under protocol number 202410039, with ethical clearance granted on October 8, 2024.
Informed consent statement: Given the retrospective nature of the study, the requirement for informed consent was waived. To ensure patient confidentiality, all datasets were de-identified.
Conflict-of-interest statement: The authors declare no conflict of interest.
Data sharing statement: The data utilized in this study can be obtained from the corresponding author upon reasonable request.
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: Yang Su, Department of Thoracic Surgery, Zhongnan Hospital of Wuhan University, No. 169 Donghu Road, Wuchang District, Wuhan 430071, Hubei Province, China. yangsueinfo@163.com
Received: April 2, 2025
Revised: May 14, 2025
Accepted: July 31, 2025
Published online: September 27, 2025
Processing time: 175 Days and 19.9 Hours
Revised: May 14, 2025
Accepted: July 31, 2025
Published online: September 27, 2025
Processing time: 175 Days and 19.9 Hours
Core Tip
Core Tip: This research proposed and validated a predictive model based on machine learning techniques to assess the risk of parastomal hernia following prophylactic ostomy in individuals with rectal cancer. Among multiple algorithms, the random forest (RF) model achieved the best performance. SHapley Additive exPlanations identified tumor distance from the anal verge, body mass index, and preoperative hypertension as key predictors. An online risk prediction tool based on the RF model has been created to support early screening and individualized postoperative management, offering practical value for clinical decision-making.