Using Machine Learning to Predict Cognitive Decline in Older Adults From the Chinese Longitudinal Healthy Longevity Survey: Model Development and Validation Study

Abstract BackgroundCognitive impairment, indicative of Alzheimer disease and other forms of dementia, significantly deteriorates the quality of life of older adult populations and imposes considerable burdens on families and health care systems worldwide. The early identificat...

Full description

Saved in:
Bibliographic Details
Main Authors: Hao Ren, Yiying Zheng, Changjin Li, Fengshi Jing, Qiting Wang, Zeyu Luo, Dongxiao Li, Deyi Liang, Weiming Tang, Li Liu, Weibin Cheng
Format: Article
Language:English
Published: JMIR Publications 2025-04-01
Series:JMIR Aging
Online Access:https://aging.jmir.org/2025/1/e67437
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850036306424365056
author Hao Ren
Yiying Zheng
Changjin Li
Fengshi Jing
Qiting Wang
Zeyu Luo
Dongxiao Li
Deyi Liang
Weiming Tang
Li Liu
Weibin Cheng
author_facet Hao Ren
Yiying Zheng
Changjin Li
Fengshi Jing
Qiting Wang
Zeyu Luo
Dongxiao Li
Deyi Liang
Weiming Tang
Li Liu
Weibin Cheng
author_sort Hao Ren
collection DOAJ
description Abstract BackgroundCognitive impairment, indicative of Alzheimer disease and other forms of dementia, significantly deteriorates the quality of life of older adult populations and imposes considerable burdens on families and health care systems worldwide. The early identification of individuals at risk for cognitive impairment through a convenient and rapid method is crucial for the timely implementation of interventions. ObjectiveThe objective of this study was to explore the application of machine learning (ML) to integrate blood biomarkers, life behaviors, and disease history to predict the decline in cognitive function. MethodsThis approach uses data from the Chinese Longitudinal Healthy Longevity Survey. A total of 2688 participants aged 65 years or older from the 2008‐2009, 2011‐2012, and 2014 Chinese Longitudinal Healthy Longevity Survey waves were included, with cognitive impairment defined as a Mini-Mental State Examination (MMSE) score below 18. The dataset was divided into a training set (n=1331), an internal test set (n=333), and a prospective validation set (n=1024). Participants with a baseline MMSE score of less than 18 were excluded from the cohort to ensure a more accurate assessment of cognitive function. We developed ML models that integrate demographic information, health behaviors, disease history, and blood biomarkers to predict cognitive function at the 3-year follow-up point, specifically identifying individuals who are at risk of experiencing significant declines in cognitive function by that time. Specifically, the models aimed to identify individuals who would experience a significant decline in their MMSE scores (less than 18) by the end of the follow-up period. The performance of these models was evaluated using metrics including accuracy, sensitivity, and the area under the receiver operating characteristic curve. ResultsAll ML models outperformed the MMSE alone. The balanced random forest achieved the highest accuracy (88.5% in the internal test set and 88.7% in the prospective validation set), albeit with a lower sensitivity, while logistic regression recorded the highest sensitivity. SHAP (Shapley Additive Explanations) analysis identified instrumental activities of daily living, age, and baseline MMSE scores as the most influential predictors for cognitive impairment. ConclusionsThe incorporation of blood biomarkers, along with demographic, life behavior, and disease history into ML models offers a convenient, rapid, and accurate approach for the early identification of older adult individuals at risk of cognitive impairment. This method presents a valuable tool for health care professionals to facilitate timely interventions and underscores the importance of integrating diverse data types in predictive health models.
format Article
id doaj-art-5ec7f696cb9f4566a7884a97dbc2280f
institution DOAJ
issn 2561-7605
language English
publishDate 2025-04-01
publisher JMIR Publications
record_format Article
series JMIR Aging
spelling doaj-art-5ec7f696cb9f4566a7884a97dbc2280f2025-08-20T02:57:13ZengJMIR PublicationsJMIR Aging2561-76052025-04-018e67437e6743710.2196/67437Using Machine Learning to Predict Cognitive Decline in Older Adults From the Chinese Longitudinal Healthy Longevity Survey: Model Development and Validation StudyHao Renhttp://orcid.org/0000-0003-1127-4608Yiying Zhenghttp://orcid.org/0009-0000-5195-6473Changjin Lihttp://orcid.org/0009-0007-5536-816XFengshi Jinghttp://orcid.org/0000-0002-6747-6527Qiting Wanghttp://orcid.org/0009-0002-3323-8966Zeyu Luohttp://orcid.org/0009-0002-1405-474XDongxiao Lihttp://orcid.org/0009-0009-2831-657XDeyi Lianghttp://orcid.org/0009-0002-4318-1203Weiming Tanghttp://orcid.org/0000-0002-9026-707XLi Liuhttp://orcid.org/0000-0001-8888-7117Weibin Chenghttp://orcid.org/0000-0002-9845-6676 Abstract BackgroundCognitive impairment, indicative of Alzheimer disease and other forms of dementia, significantly deteriorates the quality of life of older adult populations and imposes considerable burdens on families and health care systems worldwide. The early identification of individuals at risk for cognitive impairment through a convenient and rapid method is crucial for the timely implementation of interventions. ObjectiveThe objective of this study was to explore the application of machine learning (ML) to integrate blood biomarkers, life behaviors, and disease history to predict the decline in cognitive function. MethodsThis approach uses data from the Chinese Longitudinal Healthy Longevity Survey. A total of 2688 participants aged 65 years or older from the 2008‐2009, 2011‐2012, and 2014 Chinese Longitudinal Healthy Longevity Survey waves were included, with cognitive impairment defined as a Mini-Mental State Examination (MMSE) score below 18. The dataset was divided into a training set (n=1331), an internal test set (n=333), and a prospective validation set (n=1024). Participants with a baseline MMSE score of less than 18 were excluded from the cohort to ensure a more accurate assessment of cognitive function. We developed ML models that integrate demographic information, health behaviors, disease history, and blood biomarkers to predict cognitive function at the 3-year follow-up point, specifically identifying individuals who are at risk of experiencing significant declines in cognitive function by that time. Specifically, the models aimed to identify individuals who would experience a significant decline in their MMSE scores (less than 18) by the end of the follow-up period. The performance of these models was evaluated using metrics including accuracy, sensitivity, and the area under the receiver operating characteristic curve. ResultsAll ML models outperformed the MMSE alone. The balanced random forest achieved the highest accuracy (88.5% in the internal test set and 88.7% in the prospective validation set), albeit with a lower sensitivity, while logistic regression recorded the highest sensitivity. SHAP (Shapley Additive Explanations) analysis identified instrumental activities of daily living, age, and baseline MMSE scores as the most influential predictors for cognitive impairment. ConclusionsThe incorporation of blood biomarkers, along with demographic, life behavior, and disease history into ML models offers a convenient, rapid, and accurate approach for the early identification of older adult individuals at risk of cognitive impairment. This method presents a valuable tool for health care professionals to facilitate timely interventions and underscores the importance of integrating diverse data types in predictive health models.https://aging.jmir.org/2025/1/e67437
spellingShingle Hao Ren
Yiying Zheng
Changjin Li
Fengshi Jing
Qiting Wang
Zeyu Luo
Dongxiao Li
Deyi Liang
Weiming Tang
Li Liu
Weibin Cheng
Using Machine Learning to Predict Cognitive Decline in Older Adults From the Chinese Longitudinal Healthy Longevity Survey: Model Development and Validation Study
JMIR Aging
title Using Machine Learning to Predict Cognitive Decline in Older Adults From the Chinese Longitudinal Healthy Longevity Survey: Model Development and Validation Study
title_full Using Machine Learning to Predict Cognitive Decline in Older Adults From the Chinese Longitudinal Healthy Longevity Survey: Model Development and Validation Study
title_fullStr Using Machine Learning to Predict Cognitive Decline in Older Adults From the Chinese Longitudinal Healthy Longevity Survey: Model Development and Validation Study
title_full_unstemmed Using Machine Learning to Predict Cognitive Decline in Older Adults From the Chinese Longitudinal Healthy Longevity Survey: Model Development and Validation Study
title_short Using Machine Learning to Predict Cognitive Decline in Older Adults From the Chinese Longitudinal Healthy Longevity Survey: Model Development and Validation Study
title_sort using machine learning to predict cognitive decline in older adults from the chinese longitudinal healthy longevity survey model development and validation study
url https://aging.jmir.org/2025/1/e67437
work_keys_str_mv AT haoren usingmachinelearningtopredictcognitivedeclineinolderadultsfromthechineselongitudinalhealthylongevitysurveymodeldevelopmentandvalidationstudy
AT yiyingzheng usingmachinelearningtopredictcognitivedeclineinolderadultsfromthechineselongitudinalhealthylongevitysurveymodeldevelopmentandvalidationstudy
AT changjinli usingmachinelearningtopredictcognitivedeclineinolderadultsfromthechineselongitudinalhealthylongevitysurveymodeldevelopmentandvalidationstudy
AT fengshijing usingmachinelearningtopredictcognitivedeclineinolderadultsfromthechineselongitudinalhealthylongevitysurveymodeldevelopmentandvalidationstudy
AT qitingwang usingmachinelearningtopredictcognitivedeclineinolderadultsfromthechineselongitudinalhealthylongevitysurveymodeldevelopmentandvalidationstudy
AT zeyuluo usingmachinelearningtopredictcognitivedeclineinolderadultsfromthechineselongitudinalhealthylongevitysurveymodeldevelopmentandvalidationstudy
AT dongxiaoli usingmachinelearningtopredictcognitivedeclineinolderadultsfromthechineselongitudinalhealthylongevitysurveymodeldevelopmentandvalidationstudy
AT deyiliang usingmachinelearningtopredictcognitivedeclineinolderadultsfromthechineselongitudinalhealthylongevitysurveymodeldevelopmentandvalidationstudy
AT weimingtang usingmachinelearningtopredictcognitivedeclineinolderadultsfromthechineselongitudinalhealthylongevitysurveymodeldevelopmentandvalidationstudy
AT liliu usingmachinelearningtopredictcognitivedeclineinolderadultsfromthechineselongitudinalhealthylongevitysurveymodeldevelopmentandvalidationstudy
AT weibincheng usingmachinelearningtopredictcognitivedeclineinolderadultsfromthechineselongitudinalhealthylongevitysurveymodeldevelopmentandvalidationstudy