Retrospective Study
Copyright ©The Author(s) 2025. Published by Baishideng Publishing Group Inc. All rights reserved.
World J Diabetes. Jul 15, 2025; 16(7): 104789
Published online Jul 15, 2025. doi: 10.4239/wjd.v16.i7.104789
Predictive model and risk analysis for outcomes in diabetic foot ulcer using eXtreme Gradient Boosting algorithm and SHapley Additive exPlanation
Lei Gao, Zi-Xuan Liu, Jiang-Ning Wang
Lei Gao, Jiang-Ning Wang, Department of Orthopedics Surgery, Beijing Shijitan Hospital Affiliated to Capital Medical University, Beijing 100038, China
Zi-Xuan Liu, Department of Clinical Medicine, Capital Medical University, Beijing 100038, China
Co-first authors: Lei Gao and Zi-Xuan Liu.
Author contributions: Gao L conducted experiments and guided the writing of the manuscript; Liu ZX collected and analyzed the data; Wang JN is the corresponding author of this manuscript; Wang JN designed the experimental program and chaired the seminar. This manuscript has been read and approved by all the co-authors. Gao L and Liu ZX contributed equally to this work and they are co-first authors.
Institutional review board statement: This study was performed in accordance with the International Conference on Harmonization Good Clinical Practice Guidelines and the Declaration of Helsinki and approved by the Ethical Review Committee of Beijing Shijitan Hospital, Capital Medical University, No. IIT2025-049-001.
Informed consent statement: This study was a retrospective analysis of anonymized clinical data. Ethical approval was obtained from the Institutional Review Board, and the requirement for informed consent was waived.
Conflict-of-interest statement: The authors declare that they have no conflicts of interest.
Data sharing statement: The original contributions presented in the study are included in the article. Further inquiries can be directed to the corresponding author.
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: Jiang-Ning Wang, MD, Chief Physician, Department of Orthopedics Surgery, Beijing Shijitan Hospital Affiliated to Capital Medical University, No. 10 Tieyi Road, Yangfangdian, Haidian District, Beijing 100038, China. wangjn@bjsjth.cn
Received: January 2, 2025
Revised: April 22, 2025
Accepted: June 13, 2025
Published online: July 15, 2025
Processing time: 195 Days and 7 Hours
Core Tip

Core Tip: This study developed and validated an eXtreme Gradient Boosting-based predictive model for stratifying amputation risk in patients with diabetic foot ulcers. By integrating 29 clinical variables and applying SHapley Additive exPlanation for interpretability, the model achieved high predictive accuracy, especially for major amputations (area under the curve = 0.977). Key predictors included Wagner grade, albumin, infection markers, and vascular intervention. The model allows for the early identification of high-risk patients and supports individualized treatment decisions, offering a clinically interpretable tool for improving diabetic foot management.