ORIGINAL RESEARCH article
Front. Public Health
Sec. Public Mental Health
Volume 13 - 2025 | doi: 10.3389/fpubh.2025.1606316
This article is part of the Research TopicMental Health Dynamics for Vulnerable Populations in the Digital Era: Opportunities and ChallengesView all 3 articles
A Risk Prediction System for Depression in Middle-Aged and Elderly Grounded in Machine Learning and Visualization Technology: A Cohort Study
Provisionally accepted
Jinsong Du1,2,3
Xinru Tao1Le Zhu1Wenhao Qi2Xiaoqiang Min3,4Hongyan Deng1Shujie Wei5Xiaoyan Zhang6Xiao Chang2*- 1Zaozhuang University, Zaozhuang, China
- 2Hangzhou Normal University, Hangzhou, Zhejiang Province, China
- 3Shandong Coal Health School, Zaozhuang, China
- 4Shandong Healthcare Group Xinwen Central Hospital, Taian, China
- 5Zaozhuang Municipal Hospital, Zaozhuang, China
- 6Shandong Healthcare Group Zaozhuang Central Hospital, Zaozhuang, 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
Middle-aged and elderly individuals are highly susceptible to depression. For this reason, early identification and intervention can substantially reduce its prevalence. This study innovatively put forth a visual risk prediction system for depressive symptoms and depression in middle-aged and elderly adults rooted in machine learning and visualization technologies. Using cohort data from the China Health and Retirement Longitudinal Study (CHARLS) database, involving 8,839 middle-aged and elderly participants, the study constructed predictive models with eight machine learning algorithms, predominantly encompassing LightGBM, XGBoost, and AdaBoost. The XGBoost model yielded the most satisfactory performance, achieving an average ROC-AUC of 0.69. On this basis, it was ultimately selected as the predictive model for depressive symptoms and depression risk in this population. In an effort to reinforce the interpretability of the XGBoost model, SHAP technology was utilized to visualize the prediction results, while the model was deployed on a web platform to establish the risk prediction system. The system can output the probability of users developing depressive symptoms or depression within five years and explain the prediction results, rendering it easier for users to understand and use. Rooted in China's national longitudinal cohort, this platform integrates machine learning analytics with interactive visualization, with web deployment enhancing clinical translational value. By enabling early depression detection and evidence-based interventions for middle-aged/elderly populations, it establishes a novel health management paradigm with demonstrated life quality enhancement potential.
Keywords: Depression, machine learning, CHARLS, risk prediction, visualization
Received: 05 Apr 2025; Accepted: 15 May 2025.
Copyright: © 2025 Du, Tao, Zhu, Qi, Min, Deng, Wei, Zhang and Chang. 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: Xiao Chang, Hangzhou Normal University, Hangzhou, Zhejiang Province, 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.