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. Mar 15, 2026; 17(3): 115097
Published online Mar 15, 2026. doi: 10.4239/wjd.v17.i3.115097
Published online Mar 15, 2026. doi: 10.4239/wjd.v17.i3.115097
Machine learning and deep learning in predicting the risk of diabetic kidney disease: A systematic review and meta-analysis
Qing Chen, Kai-Kai Meng, Jun-Bei Zhang, Department of Endocrinology, The Yiwu Central Hospital, Yiwu 322000, Zhejiang Province, China
Hua-Wei Peng, Department of Clinical Laboratory, The Yiwu Maternity and Children Hospital, Yiwu 322000, Zhejiang Province, China
Chen-Xiao Fu, Department of General Practice, Chengxi Community Health Service Center, Yiwu 322000, Zhejiang Province, China
Author contributions: Chen Q and Peng HW contribution to investigated; Chen Q and Fu CX contribution to analyzed the data; Chen Q and Meng KK contribution to wrote the original draft; Peng HW, Fu CX, and Meng KK contribution to collected the data; Zhang JB contribution to reviewed and edited the manuscript and supervised the study; and all authors have read and approved the final manuscript.
Conflict-of-interest statement: All the authors report no relevant conflicts of interest for this article.
PRISMA 2009 Checklist statement: The authors have read the PRISMA 2009 Checklist, and the manuscript was prepared and revised according to the PRISMA 2009 Checklist.
Corresponding author: Jun-Bei Zhang, Department of Endocrinology, The Yiwu Central Hospital, No. 699 Jiangdong Road, Yiwu 322000, Zhejiang Province, China.
Received: October 9, 2025
Revised: November 18, 2025
Accepted: February 4, 2026
Published online: March 15, 2026
Processing time: 154 Days and 20 Hours
Revised: November 18, 2025
Accepted: February 4, 2026
Published online: March 15, 2026
Processing time: 154 Days and 20 Hours
Core Tip
Core Tip: Machine learning and deep learning algorithms show great performance in predicting diabetic kidney disease (DKD) among type 2 diabetes mellitus patients. Predictors, such as age, body mass index, estimated glomerular filtration rate, serum creatinine, urinary albumin, glycated hemoglobin, systolic blood pressure, low-density lipoprotein cholesterol, high-density lipoprotein cholesterol, and triglycerides, play significant roles in DKD prediction. Models employing cross-validation methods exhibit superior predictive capability for DKD compared to those using holdout validation approaches.