Predicting the risk of depression in older adults with disability using machine learning: an analysis based on CHARLS data

BackgroundThe advancement of artificial intelligence technologies has opened new avenues for depression prevention and management in older adults with disability (defined by basic or instrumental activities of daily living, BADL/IADL). This study systematically developed machine learning (ML) models...

Full description

Saved in:
Bibliographic Details
Main Authors: Tongtong Jin, Ayitijiang· Halili
Format: Article
Language:English
Published: Frontiers Media S.A. 2025-07-01
Series:Frontiers in Artificial Intelligence
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/frai.2025.1624171/full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849468406007332864
author Tongtong Jin
Ayitijiang· Halili
author_facet Tongtong Jin
Ayitijiang· Halili
author_sort Tongtong Jin
collection DOAJ
description BackgroundThe advancement of artificial intelligence technologies has opened new avenues for depression prevention and management in older adults with disability (defined by basic or instrumental activities of daily living, BADL/IADL). This study systematically developed machine learning (ML) models to predict depression risk in disabled elderly individuals using longitudinal data from the China Health and Retirement Longitudinal Study (CHARLS), providing a potentially generalizable tool for early screening.MethodsThis study utilized longitudinal data from the CHARLS 2011–2015 cohort. A three-stage serial consensus approach feature selection framework (LASSO, Elastic Net, and Boruta) was employed to identify 21 robust predictors from 74 candidate variables. Ten ML algorithms were evaluated: LR, HistGBM, MLP, XGBoost, bagging, DT, LightGBM, RF, SVM, and CatBoost. Temporal external validation was performed using an independent 2018–2020 cohort to assess model generalizability. Performance was comprehensively evaluated using accuracy, AUC, F1-score, precision, and recall metrics. The SHAP framework was employed to interpret feature contribution mechanisms.ResultsResults demonstrated that the HistGBM model achieved optimal overall performance on the testing sets (AUC = 0.779, F1-score = 0.735, accuracy = 0.713), with only an 8.5% AUC difference between training and testing sets and a 10% difference between external validation and testing sets, indicating temporal stability. SHAP interpretability analysis revealed that sleep time (mean SHAP value = 0.344) in the health behavior domain and life satisfaction (0.339) and episodic memory (0.220) in the subjective perception domain contributed more significantly to prediction than traditional biomedical indicators.ConclusionThis study developed an AI-based tool for depression risk assessment in older adults with disability through a multi-stage feature selection process and a temporal external validation framework. These findings provide a practical screening instrument and a methodological reference for implementing AI technologies in geriatric mental health applications, thereby facilitating clinical translation of predictive analytics in this field.
format Article
id doaj-art-df9386ccc6fb457da396fef4565cc03f
institution Kabale University
issn 2624-8212
language English
publishDate 2025-07-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Artificial Intelligence
spelling doaj-art-df9386ccc6fb457da396fef4565cc03f2025-08-20T03:25:53ZengFrontiers Media S.A.Frontiers in Artificial Intelligence2624-82122025-07-01810.3389/frai.2025.16241711624171Predicting the risk of depression in older adults with disability using machine learning: an analysis based on CHARLS dataTongtong Jin0Ayitijiang· Halili1School of Law, Shanxi University of Finance and Economics, Taiyuan, ChinaCollege of Public Management (Law), Xinjiang Agricultural University, Urumqi, ChinaBackgroundThe advancement of artificial intelligence technologies has opened new avenues for depression prevention and management in older adults with disability (defined by basic or instrumental activities of daily living, BADL/IADL). This study systematically developed machine learning (ML) models to predict depression risk in disabled elderly individuals using longitudinal data from the China Health and Retirement Longitudinal Study (CHARLS), providing a potentially generalizable tool for early screening.MethodsThis study utilized longitudinal data from the CHARLS 2011–2015 cohort. A three-stage serial consensus approach feature selection framework (LASSO, Elastic Net, and Boruta) was employed to identify 21 robust predictors from 74 candidate variables. Ten ML algorithms were evaluated: LR, HistGBM, MLP, XGBoost, bagging, DT, LightGBM, RF, SVM, and CatBoost. Temporal external validation was performed using an independent 2018–2020 cohort to assess model generalizability. Performance was comprehensively evaluated using accuracy, AUC, F1-score, precision, and recall metrics. The SHAP framework was employed to interpret feature contribution mechanisms.ResultsResults demonstrated that the HistGBM model achieved optimal overall performance on the testing sets (AUC = 0.779, F1-score = 0.735, accuracy = 0.713), with only an 8.5% AUC difference between training and testing sets and a 10% difference between external validation and testing sets, indicating temporal stability. SHAP interpretability analysis revealed that sleep time (mean SHAP value = 0.344) in the health behavior domain and life satisfaction (0.339) and episodic memory (0.220) in the subjective perception domain contributed more significantly to prediction than traditional biomedical indicators.ConclusionThis study developed an AI-based tool for depression risk assessment in older adults with disability through a multi-stage feature selection process and a temporal external validation framework. These findings provide a practical screening instrument and a methodological reference for implementing AI technologies in geriatric mental health applications, thereby facilitating clinical translation of predictive analytics in this field.https://www.frontiersin.org/articles/10.3389/frai.2025.1624171/fulldisabled older adultsdepressionrisk predictionmachine learningCHARLSmental health LR
spellingShingle Tongtong Jin
Ayitijiang· Halili
Predicting the risk of depression in older adults with disability using machine learning: an analysis based on CHARLS data
Frontiers in Artificial Intelligence
disabled older adults
depression
risk prediction
machine learning
CHARLS
mental health LR
title Predicting the risk of depression in older adults with disability using machine learning: an analysis based on CHARLS data
title_full Predicting the risk of depression in older adults with disability using machine learning: an analysis based on CHARLS data
title_fullStr Predicting the risk of depression in older adults with disability using machine learning: an analysis based on CHARLS data
title_full_unstemmed Predicting the risk of depression in older adults with disability using machine learning: an analysis based on CHARLS data
title_short Predicting the risk of depression in older adults with disability using machine learning: an analysis based on CHARLS data
title_sort predicting the risk of depression in older adults with disability using machine learning an analysis based on charls data
topic disabled older adults
depression
risk prediction
machine learning
CHARLS
mental health LR
url https://www.frontiersin.org/articles/10.3389/frai.2025.1624171/full
work_keys_str_mv AT tongtongjin predictingtheriskofdepressioninolderadultswithdisabilityusingmachinelearningananalysisbasedoncharlsdata
AT ayitijianghalili predictingtheriskofdepressioninolderadultswithdisabilityusingmachinelearningananalysisbasedoncharlsdata