Prediction of depression risk in middle-aged and elderly Cardiovascular-Kidney-Metabolic syndrome patients by social and environmental determinants of health: an interpretable machine learning approach using longitudinal data from China

Abstract Background Cardiovascular-Kidney-Metabolic (CKM) syndrome is a systemic disease characterized by pathophysiological interactions between the cardiovascular system, chronic kidney disease, and metabolic risk factors. In China, the prevalence of CKM in middle-aged and elderly patients is rela...

Full description

Saved in:
Bibliographic Details
Main Authors: Xinyi Xu, Xinru Li, Xiyan Li, Benli Xue, Xiao Zheng, Shujuan Xiao, Lingli Yang, Xinyi Zhang, Chengyu Chen, Ting Zheng, Yuyang Li, Yanan Wang, Jianan Han, Haoran Wu, Mengjie Zhang, Yanming Liao, Siyi Bai, Nan Zeng, Chichen Zhang
Format: Article
Language:English
Published: BMC 2025-06-01
Series:Journal of Health, Population and Nutrition
Subjects:
Online Access:https://doi.org/10.1186/s41043-025-00897-0
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849725362858098688
author Xinyi Xu
Xinru Li
Xiyan Li
Benli Xue
Xiao Zheng
Shujuan Xiao
Lingli Yang
Xinyi Zhang
Chengyu Chen
Ting Zheng
Yuyang Li
Yanan Wang
Jianan Han
Haoran Wu
Mengjie Zhang
Yanming Liao
Siyi Bai
Nan Zeng
Chichen Zhang
author_facet Xinyi Xu
Xinru Li
Xiyan Li
Benli Xue
Xiao Zheng
Shujuan Xiao
Lingli Yang
Xinyi Zhang
Chengyu Chen
Ting Zheng
Yuyang Li
Yanan Wang
Jianan Han
Haoran Wu
Mengjie Zhang
Yanming Liao
Siyi Bai
Nan Zeng
Chichen Zhang
author_sort Xinyi Xu
collection DOAJ
description Abstract Background Cardiovascular-Kidney-Metabolic (CKM) syndrome is a systemic disease characterized by pathophysiological interactions between the cardiovascular system, chronic kidney disease, and metabolic risk factors. In China, the prevalence of CKM in middle-aged and elderly patients is relatively high. The current research lacks an exploration into the impact of social and environmental determinants of health on depression in CKM patients. Objective This study aims to construct a depression risk prediction model for middle-aged and elderly CKM patients by social and environmental determinants of health. Methods In this study, 3220 participants were included and collected from three waves of the China Health and Retirement Longitudinal Study (CHARLS). A depression risk prediction model for middle-aged and elderly CKM patients was constructed by using 10 machine learning models. Additionally, the mediating effect of NO2 between arthritis and depression outcomes was analyzed in this population. Results An interpretable machine learning model framework was constructed to predict depression risk in middle-aged and elderly CKM patients using the longitudinal cohort data from CHARLS. The RF model demonstrated strong performance in predicting the training set, and the Xgboost model exhibited excellent generalization ability. The presence of arthritis showed a significant independent effect on depression outcomes, with an average direct effect of − 8.5559. The total effect of arthritis on depression outcomes was − 9.5162. The mediating effect of NO2 represented 10.09% of the total effect (average), indicating that NO2 serves as a mediator between arthritis and depression outcomes. Conclusions A depression risk prediction model for middle-aged and elderly CKM patients was developed based on the CHARLS longitudinal data from 2011 to 2015. The SHAP framework was used to provide machine learning model explanations. Intervention strategies that address social and environmental determinants of health are needed. Potential strategies include enhancing urban greening to reduce NO2 levels, integrating CKM as a special outpatient chronic disease to alleviate the financial burdens of patients, and focusing on the treatment of arthritis and digestive diseases in CKM patients.
format Article
id doaj-art-d8d86fc8149e42359ef44733dba6624e
institution DOAJ
issn 2072-1315
language English
publishDate 2025-06-01
publisher BMC
record_format Article
series Journal of Health, Population and Nutrition
spelling doaj-art-d8d86fc8149e42359ef44733dba6624e2025-08-20T03:10:28ZengBMCJournal of Health, Population and Nutrition2072-13152025-06-0144111510.1186/s41043-025-00897-0Prediction of depression risk in middle-aged and elderly Cardiovascular-Kidney-Metabolic syndrome patients by social and environmental determinants of health: an interpretable machine learning approach using longitudinal data from ChinaXinyi Xu0Xinru Li1Xiyan Li2Benli Xue3Xiao Zheng4Shujuan Xiao5Lingli Yang6Xinyi Zhang7Chengyu Chen8Ting Zheng9Yuyang Li10Yanan Wang11Jianan Han12Haoran Wu13Mengjie Zhang14Yanming Liao15Siyi Bai16Nan Zeng17Chichen Zhang18School of Public Health, Southern Medical UniversitySchool of Public Health, Southern Medical UniversityKey Laboratory of Philosophy and Social Sciences of Colleges and Universities in Guangdong Province for Collaborative Innovation of Health Management Policy and Precision Health ServiceSchool of Public Health, Southern Medical UniversitySchool of Public Health, Southern Medical UniversitySchool of Public Health, Southern Medical UniversityKey Laboratory of Philosophy and Social Sciences of Colleges and Universities in Guangdong Province for Collaborative Innovation of Health Management Policy and Precision Health ServiceSchool of Public Health, Southern Medical UniversityKey Laboratory of Philosophy and Social Sciences of Colleges and Universities in Guangdong Province for Collaborative Innovation of Health Management Policy and Precision Health ServiceSchool of Health Management, Southern Medical UniversitySchool of Health Management, Southern Medical UniversitySchool of Health Management, Southern Medical UniversitySchool of Health Management, Southern Medical UniversityKey Laboratory of Philosophy and Social Sciences of Colleges and Universities in Guangdong Province for Collaborative Innovation of Health Management Policy and Precision Health ServiceSchool of Health Management, Southern Medical UniversitySchool of Health Management, Southern Medical UniversitySchool of Health Management, Southern Medical UniversitySchool of Public Health, Southern Medical UniversitySchool of Public Health, Southern Medical UniversityAbstract Background Cardiovascular-Kidney-Metabolic (CKM) syndrome is a systemic disease characterized by pathophysiological interactions between the cardiovascular system, chronic kidney disease, and metabolic risk factors. In China, the prevalence of CKM in middle-aged and elderly patients is relatively high. The current research lacks an exploration into the impact of social and environmental determinants of health on depression in CKM patients. Objective This study aims to construct a depression risk prediction model for middle-aged and elderly CKM patients by social and environmental determinants of health. Methods In this study, 3220 participants were included and collected from three waves of the China Health and Retirement Longitudinal Study (CHARLS). A depression risk prediction model for middle-aged and elderly CKM patients was constructed by using 10 machine learning models. Additionally, the mediating effect of NO2 between arthritis and depression outcomes was analyzed in this population. Results An interpretable machine learning model framework was constructed to predict depression risk in middle-aged and elderly CKM patients using the longitudinal cohort data from CHARLS. The RF model demonstrated strong performance in predicting the training set, and the Xgboost model exhibited excellent generalization ability. The presence of arthritis showed a significant independent effect on depression outcomes, with an average direct effect of − 8.5559. The total effect of arthritis on depression outcomes was − 9.5162. The mediating effect of NO2 represented 10.09% of the total effect (average), indicating that NO2 serves as a mediator between arthritis and depression outcomes. Conclusions A depression risk prediction model for middle-aged and elderly CKM patients was developed based on the CHARLS longitudinal data from 2011 to 2015. The SHAP framework was used to provide machine learning model explanations. Intervention strategies that address social and environmental determinants of health are needed. Potential strategies include enhancing urban greening to reduce NO2 levels, integrating CKM as a special outpatient chronic disease to alleviate the financial burdens of patients, and focusing on the treatment of arthritis and digestive diseases in CKM patients.https://doi.org/10.1186/s41043-025-00897-0Cardiovascular-Kidney-Metabolic syndromeRandom forestMediation analysisHealth management
spellingShingle Xinyi Xu
Xinru Li
Xiyan Li
Benli Xue
Xiao Zheng
Shujuan Xiao
Lingli Yang
Xinyi Zhang
Chengyu Chen
Ting Zheng
Yuyang Li
Yanan Wang
Jianan Han
Haoran Wu
Mengjie Zhang
Yanming Liao
Siyi Bai
Nan Zeng
Chichen Zhang
Prediction of depression risk in middle-aged and elderly Cardiovascular-Kidney-Metabolic syndrome patients by social and environmental determinants of health: an interpretable machine learning approach using longitudinal data from China
Journal of Health, Population and Nutrition
Cardiovascular-Kidney-Metabolic syndrome
Random forest
Mediation analysis
Health management
title Prediction of depression risk in middle-aged and elderly Cardiovascular-Kidney-Metabolic syndrome patients by social and environmental determinants of health: an interpretable machine learning approach using longitudinal data from China
title_full Prediction of depression risk in middle-aged and elderly Cardiovascular-Kidney-Metabolic syndrome patients by social and environmental determinants of health: an interpretable machine learning approach using longitudinal data from China
title_fullStr Prediction of depression risk in middle-aged and elderly Cardiovascular-Kidney-Metabolic syndrome patients by social and environmental determinants of health: an interpretable machine learning approach using longitudinal data from China
title_full_unstemmed Prediction of depression risk in middle-aged and elderly Cardiovascular-Kidney-Metabolic syndrome patients by social and environmental determinants of health: an interpretable machine learning approach using longitudinal data from China
title_short Prediction of depression risk in middle-aged and elderly Cardiovascular-Kidney-Metabolic syndrome patients by social and environmental determinants of health: an interpretable machine learning approach using longitudinal data from China
title_sort prediction of depression risk in middle aged and elderly cardiovascular kidney metabolic syndrome patients by social and environmental determinants of health an interpretable machine learning approach using longitudinal data from china
topic Cardiovascular-Kidney-Metabolic syndrome
Random forest
Mediation analysis
Health management
url https://doi.org/10.1186/s41043-025-00897-0
work_keys_str_mv AT xinyixu predictionofdepressionriskinmiddleagedandelderlycardiovascularkidneymetabolicsyndromepatientsbysocialandenvironmentaldeterminantsofhealthaninterpretablemachinelearningapproachusinglongitudinaldatafromchina
AT xinruli predictionofdepressionriskinmiddleagedandelderlycardiovascularkidneymetabolicsyndromepatientsbysocialandenvironmentaldeterminantsofhealthaninterpretablemachinelearningapproachusinglongitudinaldatafromchina
AT xiyanli predictionofdepressionriskinmiddleagedandelderlycardiovascularkidneymetabolicsyndromepatientsbysocialandenvironmentaldeterminantsofhealthaninterpretablemachinelearningapproachusinglongitudinaldatafromchina
AT benlixue predictionofdepressionriskinmiddleagedandelderlycardiovascularkidneymetabolicsyndromepatientsbysocialandenvironmentaldeterminantsofhealthaninterpretablemachinelearningapproachusinglongitudinaldatafromchina
AT xiaozheng predictionofdepressionriskinmiddleagedandelderlycardiovascularkidneymetabolicsyndromepatientsbysocialandenvironmentaldeterminantsofhealthaninterpretablemachinelearningapproachusinglongitudinaldatafromchina
AT shujuanxiao predictionofdepressionriskinmiddleagedandelderlycardiovascularkidneymetabolicsyndromepatientsbysocialandenvironmentaldeterminantsofhealthaninterpretablemachinelearningapproachusinglongitudinaldatafromchina
AT lingliyang predictionofdepressionriskinmiddleagedandelderlycardiovascularkidneymetabolicsyndromepatientsbysocialandenvironmentaldeterminantsofhealthaninterpretablemachinelearningapproachusinglongitudinaldatafromchina
AT xinyizhang predictionofdepressionriskinmiddleagedandelderlycardiovascularkidneymetabolicsyndromepatientsbysocialandenvironmentaldeterminantsofhealthaninterpretablemachinelearningapproachusinglongitudinaldatafromchina
AT chengyuchen predictionofdepressionriskinmiddleagedandelderlycardiovascularkidneymetabolicsyndromepatientsbysocialandenvironmentaldeterminantsofhealthaninterpretablemachinelearningapproachusinglongitudinaldatafromchina
AT tingzheng predictionofdepressionriskinmiddleagedandelderlycardiovascularkidneymetabolicsyndromepatientsbysocialandenvironmentaldeterminantsofhealthaninterpretablemachinelearningapproachusinglongitudinaldatafromchina
AT yuyangli predictionofdepressionriskinmiddleagedandelderlycardiovascularkidneymetabolicsyndromepatientsbysocialandenvironmentaldeterminantsofhealthaninterpretablemachinelearningapproachusinglongitudinaldatafromchina
AT yananwang predictionofdepressionriskinmiddleagedandelderlycardiovascularkidneymetabolicsyndromepatientsbysocialandenvironmentaldeterminantsofhealthaninterpretablemachinelearningapproachusinglongitudinaldatafromchina
AT jiananhan predictionofdepressionriskinmiddleagedandelderlycardiovascularkidneymetabolicsyndromepatientsbysocialandenvironmentaldeterminantsofhealthaninterpretablemachinelearningapproachusinglongitudinaldatafromchina
AT haoranwu predictionofdepressionriskinmiddleagedandelderlycardiovascularkidneymetabolicsyndromepatientsbysocialandenvironmentaldeterminantsofhealthaninterpretablemachinelearningapproachusinglongitudinaldatafromchina
AT mengjiezhang predictionofdepressionriskinmiddleagedandelderlycardiovascularkidneymetabolicsyndromepatientsbysocialandenvironmentaldeterminantsofhealthaninterpretablemachinelearningapproachusinglongitudinaldatafromchina
AT yanmingliao predictionofdepressionriskinmiddleagedandelderlycardiovascularkidneymetabolicsyndromepatientsbysocialandenvironmentaldeterminantsofhealthaninterpretablemachinelearningapproachusinglongitudinaldatafromchina
AT siyibai predictionofdepressionriskinmiddleagedandelderlycardiovascularkidneymetabolicsyndromepatientsbysocialandenvironmentaldeterminantsofhealthaninterpretablemachinelearningapproachusinglongitudinaldatafromchina
AT nanzeng predictionofdepressionriskinmiddleagedandelderlycardiovascularkidneymetabolicsyndromepatientsbysocialandenvironmentaldeterminantsofhealthaninterpretablemachinelearningapproachusinglongitudinaldatafromchina
AT chichenzhang predictionofdepressionriskinmiddleagedandelderlycardiovascularkidneymetabolicsyndromepatientsbysocialandenvironmentaldeterminantsofhealthaninterpretablemachinelearningapproachusinglongitudinaldatafromchina