Retrospective Cohort Study
Copyright ©The Author(s) 2024. Published by Baishideng Publishing Group Inc. All rights reserved.
World J Gastrointest Oncol. Dec 15, 2024; 16(12): 4597-4613
Published online Dec 15, 2024. doi: 10.4251/wjgo.v16.i12.4597
Prognostic prediction models for postoperative patients with stage I to III colorectal cancer based on machine learning
Xiao-Lin Ji, Shuo Xu, Xiao-Yu Li, Jin-Huan Xu, Rong-Shuang Han, Ying-Jie Guo, Li-Ping Duan, Zi-Bin Tian
Xiao-Lin Ji, Li-Ping Duan, Department of Gastroenterology, Beijing Key Laboratory for Helicobacter Pylori Infection and Upper Gastrointestinal Diseases, Peking University Third Hospital, Beijing 100191, China
Shuo Xu, Beijing Aerospace Wanyuan Science Technology Co., Ltd., China Academy of Launch Vehicle Technology, Beijing 100176, China
Xiao-Yu Li, Rong-Shuang Han, Ying-Jie Guo, Zi-Bin Tian, Department of Gastroenterology, The Affiliated Hospital of Qingdao University, Qingdao 266003, Shandong Province, China
Jin-Huan Xu, Institute of Automation, Qilu University of Technology (Shandong Academy of Sciences), Jinan 250014, Shandong Province, China
Co-first authors: Xiao-Lin Ji and Shuo Xu.
Co-corresponding authors: Zi-Bin Tian and Li-Ping Duan.
Author contributions: Ji XL and Xu S designed the study, acquired and analyzed the data, and wrote the manuscript; Ji XL and Xu S contributed equally to this work; Li XY prepared the materials; Xu JH provided methods; Han RS, and Guo YJ participated in the data acquisition and analysis; Tian ZB and Duan LP managed and designed the project, and performed critical revisions of the manuscript; Tian ZB and Duan LP contributed equally to this work; All authors have read and approve the final manuscript. Ji XL and Xu S contributed equally to this work as co-first authors. The designation of Tian ZB and Duan LP as co-corresponding authors of this work is primarily based on the following three reasons. First, this research project spans multiple disciplines. As the main provider of data, Tian ZB ensures the reliability and integrity of the research. His work in data collection, collation and analysis is crucial to the quality of the paper, while Duan LP ensures the comprehensiveness and depth of the research. Second, Duan LP was the main provider of the core ideas of the paper, setting the foundation for the direction and framework of the entire research and promoting the innovation and scientific value of the research. Moreover, Tian ZB put forward suggestions during this process. The two co-corresponding authors have similar contributions to the project and work closely together. Balancing their contributions is crucial for fairness and transparency. Third, Tian ZB and Duan LP jointly undertook the task of revising the manuscript, reducing the burden of a single corresponding author and ensuring timely and efficient responses. In short, designating two corresponding authors helps promote cooperation, enhance academic influence, and improve the quality of research results. The contributions of Tian ZB and Duan LP are equally important at different stages, so being co-corresponding authors more fairly reflects their collaboration and contribution to this research.
Supported by National Natural Science Foundation of China, No. 81802777.
Institutional review board statement: The study was reviewed and approved for publication by the Ethics Committee of the Affiliate Hospital of Qingdao University (Grant No. QYFYWZLL26957).
Informed consent statement: All study participants or their legal guardians provided informed verbal consent for personal and medical data collection prior to study enrollment.
Conflict-of-interest statement: The authors have no conflicts of interest related to the manuscript.
Data sharing statement: The original anonymized dataset is available upon request from the corresponding author at duanlp@bjmu.edu.cn.
STROBE statement: The authors have read the STROBE Statement-checklist of items, and the manuscript was prepared and revised according to the STROBE Statement-checklist of items.
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: Li-Ping Duan, MD, PhD, Chief Physician, Professor, Department of Gastroenterology, Beijing Key Laboratory for Helicobacter Pylori Infection and Upper Gastrointestinal Diseases, Peking University Third Hospital, No. 49 Garden Road, Haidian District, Beijing 100191, China. duanlp@bjmu.edu.cn
Received: March 19, 2024
Revised: September 7, 2024
Accepted: September 14, 2024
Published online: December 15, 2024
Processing time: 237 Days and 23.7 Hours
Core Tip

Core Tip: We developed and validated a promising machine learning architecture for predicting the 3-category survival times (cutoff values of 3 years and 5 years) for four survival times (overall, disease-free, recurrence-free, and distant metastasis-free survival) and screened corresponding important variables. Fivefold cross validation and bootstrap validation were conducted. The models were evaluated with the area under the curve (AUC); moreover, the effectiveness of our variable screening methods was evaluated by comparing the models’ pre- and post-screening AUCs. SHapley Additive exPlanations were used to explain the decision-making process. Nomograms were drawn for various applications.