ORIGINAL RESEARCH article
Front. Med.
Sec. Precision Medicine
Volume 12 - 2025 | doi: 10.3389/fmed.2025.1553274
This article is part of the Research TopicAdvances in Precision Medicine for Minimally Invasive Treatment of Pelvis/Hip Fractures: Integration of Digital and Intelligent TechnologiesView all 4 articles
A Risk Prediction Model for Poor Joint Function Recovery after Ankle Fracture Surgery Based on Interpretable Machine Learning
Provisionally accepted
- 1Orthopaedics, Lu'an Hospital of Anhui Medical University, Lu 'an City, China
- 2Wound stoma care clinic, Lu'an Hospital of Anhui Medical University, Lu 'an City, China
- 3Department of Science and Education, Lu'an Hospital of Anhui Medical University, Lu 'an City, China
- 4Nursing Department, Lu'an Hospital of Anhui Medical University, Lu 'an City, China
Select one of your emails
You have multiple emails registered with Frontiers:
Notify me on publication
Please enter your email address:
If you already have an account, please login
You don't have a Frontiers account ? You can register here
Objective: Currently, there is no individualized prediction model for joint function recovery after ankle fracture surgery. This study aims to develop a prediction model for poor recovery after ankle fracture surgery using different machine learning algorithms, to facilitate early identification of highrisk patients.Methods: A total of 750 patients who underwent ankle fracture surgery at Lu'an Hospital Affiliated to Anhui Medical University from January 2018 to December 2023 were followed up. The collected data were chronologically divided into a training set (599 cases) and a test set (151 cases). Feature variables were selected using the Boruta algorithm, and five machine learning algorithms (Logistic Regression, Random Forest, Extreme Gradient Boosting, Support Vector Machine, and Lasso-Stacking) were employed to construct models. The performance of these models was compared in both the training and test sets to select the best model. The decision basis of the optimal model was analyzed using SHAP interpretability analysis and LIME local interpretability analysis.Results: Twelve characteristic variables were identified using the Boruta algorithm. Among the five machine learning models, random forest model: AUC (training set: 0.
Keywords: Ankle fracture, Poor functional recovery, machine learning, Interpretability analysis, prediction
Received: 30 Dec 2024; Accepted: 16 Jun 2025.
Copyright: © 2025 Li, Wang, Zhang, Zheng, Shi, Li and Shi. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
* Correspondence:
Li Li, Department of Science and Education, Lu'an Hospital of Anhui Medical University, Lu 'an City, China
Xuezhi Shi, Nursing Department, Lu'an Hospital of Anhui Medical University, Lu 'an City, China
Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.