Copyright: ©Author(s) 2026. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution-NonCommercial (CC BY-NC 4.0) license. No commercial re-use. See permissions. Published by Baishideng Publishing Group Inc.
World J Gastroenterol. Dec 14, 2026; 32(46): 121223
Published online Dec 14, 2026. doi: 10.3748/wjg.121223
Predicting three-year risk of incident colorectal precancerous conditions using non-invasive predictors and machine-learning algorithms: A multi-center retrospective study
Xiao-Yang Huang, Li Zhao, Hui He, Rui Peng, Han Xue, Si-Min Lai, Wei-Xing Wu, Xiang-Xiang Qiu, Xu-Hao Cai, Jia-Hui He, Wen-Jian Qin, Wen-Ting Zhou, Wei-Qing Wu, Yong-Ping Lin
Xiao-Yang Huang, Si-Min Lai, Wei-Xing Wu, Xiang-Xiang Qiu, Yong-Ping Lin, Clinical Laboratory, National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital and Shenzhen Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Shenzhen 518116, Guangdong Province, China
Xiao-Yang Huang, Jia-Hui He, Wen-Jian Qin, Institute of Biomedical and Health Engineering, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen 518055, Guangdong Province, China
Xiao-Yang Huang, Department of Medicine, Shenzhen Ellen-Sven Precision Medicine Institute, Shenzhen 518110, Guangdong Province, China
Li Zhao, Hui He, Rui Peng, Han Xue, Wei-Qing Wu, Department of Health Management, Shenzhen People’s Hospital (The First Affiliated Hospital, Southern University of Science and Technology, The Second Clinical Medical College, Jinan University), Shenzhen 518020, Guangdong Province, China
Xu-Hao Cai, Department of Gastroenterology, National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital and Shenzhen Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Shenzhen 518116, Guangdong Province, China
Wen-Ting Zhou, Department of Pathology, West China Longquan Hospital Sichuan University/The First People’s Hospital of Longquanyi District Chengdu, Chengdu 610100, Sichuan Province, China
Yong-Ping Lin, Clinical Laboratory, The Affiliated Cancer Hospital, School of Medicine, Southern University of Science and Technology, Shenzhen 518055, Guangdong Province, China
Co-first authors: Xiao-Yang Huang and Li Zhao.
Co-corresponding authors: Wen-Ting Zhou and Wei-Qing Wu.
Author contributions: Huang XY and Zhao L were responsible for conceptualization, methodology, formal analysis, visualization, and writing original draft as co-first authors; He H, Peng R, Xue H and Zhou WT were responsible for data curation and investigation; Lai SM, Wu WX, Qiu XX and Cai XH were responsible for writing-reviewing and editing; He JH and Qin WJ were responsible for software; Zhou WT and Wu WQ were responsible for resources, supervision and project administration as co-corresponding authors; Lin YP was responsible for funding acquisition, writing-reviewing and editing; all authors critically reviewed and provided final approval of the manuscript, were responsible for the decision to submit the manuscript for publication.
AI contribution statement: Grammarly was used for language polishing and DeepL was used for translation of the answering-reviewers.
Supported by Sanming Project of Medicine in Shenzhen, No. SZSM202311002; Shenzhen Longhua District 2024 Science and Technology Innovation Special Fund, No. 2548A20241107A140254; and Shenzhen Health Economics Society, No. 202675.
Institutional review board statement: This study was approved by the Shenzhen People’s Hospital Research Ethics Committee (No. LL-KY-2019375).
Informed consent statement: The need for patient consent was waived due to the retrospective nature of the study.
Conflict-of-interest statement: All authors declare no conflict of interest in publishing the manuscript.
Data sharing statement: Statistical code and dataset available from the corresponding author at
wweiqing007@sina.com. Consent was not obtained but the presented data are anonymized and risk of identification is low
Corresponding author: Wei-Qing Wu, MD, PhD, Director, Professor, Department of Health Management, Shenzhen People’s Hospital (The First Affiliated Hospital, Southern University of Science and Technology, The Second Clinical Medical College, Jinan University), No. 1017 Dongmenbei Street, Shenzhen 518020, Guangdong Province, China.
wweiqing007@sina.com
Received: March 24, 2026
Revised: April 29, 2026
Accepted: June 4, 2026
Published online: December 14, 2026
Processing time: 212 Days and 22.8 Hours
BACKGROUND
Current screening guidelines recommend a three-year follow-up for patients with non-advanced adenoma (non-AA), making it challenging to capture rapidly evolving precancerous conditions and provide timely preventive interventions.
AIM
To develop and validate a model using non-invasive predictors to predict the three-year risk of developing advanced adenoma (AA) among non-AA patients.
METHODS
This study retrospectively included 1808 Chinese patients from two hospitals aged 30-80 years who had newly diagnosed non-AA lesions. The patients were divided into a training cohort (n = 761), an internal validation cohort (n = 762), and an external validation cohort (n = 285). The least absolute shrinkage and selection operator (LASSO) procedure was used to select predictors from 65 non-invasive parameters. Five machine learning models and a stepwise logistic regression were applied to predict incident AA diagnosed within three years after the baseline screening.
RESULTS
The LASSO procedure selected seven predictors: (1) Serum thymidine kinase 1 protein; (2) Cytokeratin 19 fragment; (3) Carbohydrate antigen 19-9; (4) Age; (5) Diastolic blood pressure; (6) Fecal immunochemical test; and (7) Sex. The EXtreme Gradient Boosting (XGBOOST) machine-learning model achieved an area under the receiver operating characteristic curve of 0.988 (95%CI: 0.980-0.996) in the training cohort, 0.825 (0.766-0.883) in the internal validation cohort, and 0.767 (0.642-0.892) in the external validation cohort, higher than other models (P < 0.05). SHapley Additive exPlanations analysis was applied to quantify the contribution of each included predictor to the XGBOOST model’s output. An open-access web application was deployed for the XGBOOST model.
CONCLUSION
The XGBOOST model included seven non-invasive predictors for precise prediction of three-year AA risk and was validated internally and externally, providing a feasible tool to guide more intensive follow-up for high-risk non-AA patients.
Core Tip: This retrospective study developed and validated a machine learning model using seven non-invasive predictors, serum thymidine kinase 1 protein, cytokeratin 19 fragment, carbohydrate antigen 19-9, age, diastolic blood pressure, fecal immunochemical test, and sex, to predict the three-year risk of incident advanced adenoma (AA) in patients with non-AA. The model achieved high discriminative performance [area under the receiver operating characteristic: (1) 0.988 in training; and (2) 0.767 in external validation] and superior clinical utility over traditional methods. An open-access web application was deployed to enable precise detection of patients at high-risk of developing AA, offering a novel tool to guide more intensive follow-up for this high-risk subgroup.
