A risk prediction system for depression in middle-aged and older adults grounded in machine learning and visualization technology: a cohort study

IntroductionMiddle-aged and older adults are highly susceptible to depression. For this reason, early identification and intervention can substantially reduce its prevalence. This study innovatively proposed a visual risk prediction system for depressive symptoms and depression in middle-aged and ol...

Full description

Saved in:
Bibliographic Details
Main Authors: Jinsong Du, Xinru Tao, Le Zhu, Wenhao Qi, Xiaoqiang Min, Hongyan Deng, Shujie Wei, Xiaoyan Zhang, Xiao Chang
Format: Article
Language:English
Published: Frontiers Media S.A. 2025-06-01
Series:Frontiers in Public Health
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/fpubh.2025.1606316/full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850232869596692480
author Jinsong Du
Jinsong Du
Jinsong Du
Xinru Tao
Le Zhu
Wenhao Qi
Xiaoqiang Min
Xiaoqiang Min
Hongyan Deng
Shujie Wei
Xiaoyan Zhang
Xiao Chang
author_facet Jinsong Du
Jinsong Du
Jinsong Du
Xinru Tao
Le Zhu
Wenhao Qi
Xiaoqiang Min
Xiaoqiang Min
Hongyan Deng
Shujie Wei
Xiaoyan Zhang
Xiao Chang
author_sort Jinsong Du
collection DOAJ
description IntroductionMiddle-aged and older adults are highly susceptible to depression. For this reason, early identification and intervention can substantially reduce its prevalence. This study innovatively proposed a visual risk prediction system for depressive symptoms and depression in middle-aged and older adults, rooted in machine learning and visualization technologies.MethodsUsing cohort data from the China Health and Retirement Longitudinal Study (CHARLS), involving 8,839 middle-aged and older adult participants, the study developed predictive models based on eight machine learning algorithms, primarily including LightGBM, XGBoost, and AdaBoost. To enhance the interpretability of the XGBoost model, SHAP technology was employed to visualize the prediction results. The model was then deployed on a web platform to establish the risk prediction system.ResultsAmong the models, XGBoost demonstrated the best performance, achieving an average ROC-AUC of 0.69, and was ultimately selected as the predictive model for depressive symptoms and depression risk in this population. The developed risk prediction system can output the probability of users developing depressive symptoms or depression within five years and provide explanations for the prediction results, improving user accessibility and interpretability.DiscussionRooted in China's national longitudinal cohort, this platform integrates machine learning analytics with interactive visualization, with web deployment enhancing its clinical translational value. By enabling early depression detection and evidence-based interventions for middle-aged and older adult populations, it establishes a novel health management paradigm with demonstrated potential to improve quality of life.
format Article
id doaj-art-d3cd200fa10f46088fdca3114d02d66f
institution OA Journals
issn 2296-2565
language English
publishDate 2025-06-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Public Health
spelling doaj-art-d3cd200fa10f46088fdca3114d02d66f2025-08-20T02:03:04ZengFrontiers Media S.A.Frontiers in Public Health2296-25652025-06-011310.3389/fpubh.2025.16063161606316A risk prediction system for depression in middle-aged and older adults grounded in machine learning and visualization technology: a cohort studyJinsong Du0Jinsong Du1Jinsong Du2Xinru Tao3Le Zhu4Wenhao Qi5Xiaoqiang Min6Xiaoqiang Min7Hongyan Deng8Shujie Wei9Xiaoyan Zhang10Xiao Chang11School of Health Management, Zaozhuang University, Zaozhuang, ChinaSchool of Public Administration, Hangzhou Normal University, Hangzhou, ChinaDepartment of Teaching and Research, Shandong Coal Health School, Zaozhuang, ChinaSchool of Health Management, Zaozhuang University, Zaozhuang, ChinaSchool of Health Management, Zaozhuang University, Zaozhuang, ChinaSchool of Public Health and Nursing, Hangzhou Normal University, Hangzhou, ChinaDepartment of Teaching and Research, Shandong Coal Health School, Zaozhuang, ChinaDepartment of Geriatics, Shandong Healthcare Group Xinwen Central Hospital, Taian, ChinaSchool of Health Management, Zaozhuang University, Zaozhuang, ChinaImage Center, Zaozhuang Municipal Hospital, Zaozhuang, ChinaMagnetic Resonance Imaging Department, Shandong Healthcare Group Zaozhuang Central Hospital, Zaozhuang, ChinaSchool of Public Administration, Hangzhou Normal University, Hangzhou, ChinaIntroductionMiddle-aged and older adults are highly susceptible to depression. For this reason, early identification and intervention can substantially reduce its prevalence. This study innovatively proposed a visual risk prediction system for depressive symptoms and depression in middle-aged and older adults, rooted in machine learning and visualization technologies.MethodsUsing cohort data from the China Health and Retirement Longitudinal Study (CHARLS), involving 8,839 middle-aged and older adult participants, the study developed predictive models based on eight machine learning algorithms, primarily including LightGBM, XGBoost, and AdaBoost. To enhance the interpretability of the XGBoost model, SHAP technology was employed to visualize the prediction results. The model was then deployed on a web platform to establish the risk prediction system.ResultsAmong the models, XGBoost demonstrated the best performance, achieving an average ROC-AUC of 0.69, and was ultimately selected as the predictive model for depressive symptoms and depression risk in this population. The developed risk prediction system can output the probability of users developing depressive symptoms or depression within five years and provide explanations for the prediction results, improving user accessibility and interpretability.DiscussionRooted in China's national longitudinal cohort, this platform integrates machine learning analytics with interactive visualization, with web deployment enhancing its clinical translational value. By enabling early depression detection and evidence-based interventions for middle-aged and older adult populations, it establishes a novel health management paradigm with demonstrated potential to improve quality of life.https://www.frontiersin.org/articles/10.3389/fpubh.2025.1606316/fulldepressionmachine learningCHARLSrisk predictionvisualization
spellingShingle Jinsong Du
Jinsong Du
Jinsong Du
Xinru Tao
Le Zhu
Wenhao Qi
Xiaoqiang Min
Xiaoqiang Min
Hongyan Deng
Shujie Wei
Xiaoyan Zhang
Xiao Chang
A risk prediction system for depression in middle-aged and older adults grounded in machine learning and visualization technology: a cohort study
Frontiers in Public Health
depression
machine learning
CHARLS
risk prediction
visualization
title A risk prediction system for depression in middle-aged and older adults grounded in machine learning and visualization technology: a cohort study
title_full A risk prediction system for depression in middle-aged and older adults grounded in machine learning and visualization technology: a cohort study
title_fullStr A risk prediction system for depression in middle-aged and older adults grounded in machine learning and visualization technology: a cohort study
title_full_unstemmed A risk prediction system for depression in middle-aged and older adults grounded in machine learning and visualization technology: a cohort study
title_short A risk prediction system for depression in middle-aged and older adults grounded in machine learning and visualization technology: a cohort study
title_sort risk prediction system for depression in middle aged and older adults grounded in machine learning and visualization technology a cohort study
topic depression
machine learning
CHARLS
risk prediction
visualization
url https://www.frontiersin.org/articles/10.3389/fpubh.2025.1606316/full
work_keys_str_mv AT jinsongdu ariskpredictionsystemfordepressioninmiddleagedandolderadultsgroundedinmachinelearningandvisualizationtechnologyacohortstudy
AT jinsongdu ariskpredictionsystemfordepressioninmiddleagedandolderadultsgroundedinmachinelearningandvisualizationtechnologyacohortstudy
AT jinsongdu ariskpredictionsystemfordepressioninmiddleagedandolderadultsgroundedinmachinelearningandvisualizationtechnologyacohortstudy
AT xinrutao ariskpredictionsystemfordepressioninmiddleagedandolderadultsgroundedinmachinelearningandvisualizationtechnologyacohortstudy
AT lezhu ariskpredictionsystemfordepressioninmiddleagedandolderadultsgroundedinmachinelearningandvisualizationtechnologyacohortstudy
AT wenhaoqi ariskpredictionsystemfordepressioninmiddleagedandolderadultsgroundedinmachinelearningandvisualizationtechnologyacohortstudy
AT xiaoqiangmin ariskpredictionsystemfordepressioninmiddleagedandolderadultsgroundedinmachinelearningandvisualizationtechnologyacohortstudy
AT xiaoqiangmin ariskpredictionsystemfordepressioninmiddleagedandolderadultsgroundedinmachinelearningandvisualizationtechnologyacohortstudy
AT hongyandeng ariskpredictionsystemfordepressioninmiddleagedandolderadultsgroundedinmachinelearningandvisualizationtechnologyacohortstudy
AT shujiewei ariskpredictionsystemfordepressioninmiddleagedandolderadultsgroundedinmachinelearningandvisualizationtechnologyacohortstudy
AT xiaoyanzhang ariskpredictionsystemfordepressioninmiddleagedandolderadultsgroundedinmachinelearningandvisualizationtechnologyacohortstudy
AT xiaochang ariskpredictionsystemfordepressioninmiddleagedandolderadultsgroundedinmachinelearningandvisualizationtechnologyacohortstudy
AT jinsongdu riskpredictionsystemfordepressioninmiddleagedandolderadultsgroundedinmachinelearningandvisualizationtechnologyacohortstudy
AT jinsongdu riskpredictionsystemfordepressioninmiddleagedandolderadultsgroundedinmachinelearningandvisualizationtechnologyacohortstudy
AT jinsongdu riskpredictionsystemfordepressioninmiddleagedandolderadultsgroundedinmachinelearningandvisualizationtechnologyacohortstudy
AT xinrutao riskpredictionsystemfordepressioninmiddleagedandolderadultsgroundedinmachinelearningandvisualizationtechnologyacohortstudy
AT lezhu riskpredictionsystemfordepressioninmiddleagedandolderadultsgroundedinmachinelearningandvisualizationtechnologyacohortstudy
AT wenhaoqi riskpredictionsystemfordepressioninmiddleagedandolderadultsgroundedinmachinelearningandvisualizationtechnologyacohortstudy
AT xiaoqiangmin riskpredictionsystemfordepressioninmiddleagedandolderadultsgroundedinmachinelearningandvisualizationtechnologyacohortstudy
AT xiaoqiangmin riskpredictionsystemfordepressioninmiddleagedandolderadultsgroundedinmachinelearningandvisualizationtechnologyacohortstudy
AT hongyandeng riskpredictionsystemfordepressioninmiddleagedandolderadultsgroundedinmachinelearningandvisualizationtechnologyacohortstudy
AT shujiewei riskpredictionsystemfordepressioninmiddleagedandolderadultsgroundedinmachinelearningandvisualizationtechnologyacohortstudy
AT xiaoyanzhang riskpredictionsystemfordepressioninmiddleagedandolderadultsgroundedinmachinelearningandvisualizationtechnologyacohortstudy
AT xiaochang riskpredictionsystemfordepressioninmiddleagedandolderadultsgroundedinmachinelearningandvisualizationtechnologyacohortstudy