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 Diabetes. Sep 15, 2026; 17(9): 122555
Published online Sep 15, 2026. doi: 10.4239/wjd.122555
Published online Sep 15, 2026. doi: 10.4239/wjd.122555
Development and validation of an interpretable machine learning model for predicting progression from prediabetes to type 2 diabetes
Zhi-Yuan Fan, Xian-Hui Ran, Na Wang, Tian-Yi Zhao, Hui Li, Jin Wu, Zhen Yang, Gang Chen, Xiao Ma, Health Checkup Center, China-Japan Friendship Hospital, Beijing 100029, China
Xiao Liu, Department of Pharmacy, China-Japan Friendship Hospital, Beijing 100029, China
Lei Yang, Health Checkup Center, Henan Honliv Hospital, Xinxiang 453499, Henan Province, China
Xiao Ma, State Key Laboratory of Respiratory Health and Multimorbidity, China-Japan Friendship Hospital, Beijing 100029, China
Co-first authors: Zhi-Yuan Fan and Xian-Hui Ran.
Co-corresponding authors: Lei Yang and Xiao Ma.
Author contributions: Fan ZY and Ran XH contributed equally to this study, including study design, data analysis, and manuscript preparation, wrote the original manuscript and revised the paper as co-first authors; Fan ZY, Ran XH, Wang N, Zhao TY, Li H, Liu X, Wu J, Yang Z, Chen G, and Yang L were responsible for data curation, methodology, and participated in formal analysis; Yang L and Ma X were the guarantor of the study and were responsible for conceptualization, project administration, supervision, methodology, writing review and editing as co-corresponding authors; all authors have read and approved the final manuscript.
AI contribution statement: Portions of this manuscript were edited using AI tools solely for language refinement. The authors carefully reviewed and verified all AI-assisted outputs and take full responsibility for the scientific content of the manuscript.
Supported by National High Level Hospital Clinical Research Funding, Elite Medical Professionals Initiative of China-Japan Friendship Hospital, No. ZRJY2025-QMPY41; Non-profit Central Research Institute Fund of Chinese Academy of Medical Sciences, No. 2022-ZHCH330-01; National High Level Hospital Clinical Research Funding, No. 2023-NHLHCRF-YXHZ-ZRMS-06; and National High Level Hospital Clinical Research Funding, No. 2025-NHLHCRF-PY-13.
Institutional review board statement: The study was approved by the Ethics Committee of China-Japan Friendship Hospital (No. 2025-KY-353).
Informed consent statement: The ethics committee agrees to waive informed consent.
Conflict-of-interest statement: All authors declare no conflict of interest in publishing the manuscript.
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.
Data sharing statement: De-identified data in this study may be provided to qualified researchers upon reasonable request.
Corresponding author: Xiao Ma, MD, PhD, Dean, Health Checkup Center, China-Japan Friendship Hospital, No. 2 Yinghuayuan East Street, Chaoyang District, Beijing 100029, China. maxiaocjfh@163.com
Received: April 23, 2026
Revised: June 11, 2026
Accepted: July 15, 2026
Published online: September 15, 2026
Processing time: 131 Days and 5.8 Hours
Revised: June 11, 2026
Accepted: July 15, 2026
Published online: September 15, 2026
Processing time: 131 Days and 5.8 Hours
Core Tip
Core Tip: We developed and externally validated an interpretable machine learning model to predict progression from prediabetes to type 2 diabetes mellitus using routine health checkup data. In a multicenter Chinese cohort, gradient boosting survival analysis demonstrated favorable discrimination (concordance index: 0.813 in temporal validation and 0.759 in external validation) and effectively stratified high-risk individuals. Shapley Additive exPlanations improved model transparency by identifying key predictors, including fasting blood glucose, age and body mass index. An online risk calculator was developed to support individualized risk assessment in preventive care settings.