Using Machine Learning to Predict Cognitive Impairment Among Middle-Aged and Older Chinese - A Longitudinal Study

Aug 4, 2026

Upload by Himbo

Machine learning is explored as a means to predict cognitive impairment and to identify important factors underlying impairment in Chinese middle-aged and older adults. The study analyzes questionnaire data from 2,326 participants and incorporates baseline physical examination, biomarker, functional, demographic, and emotional measures across follow-ups at Years 2 and 4. Random forest models are compared with logistic regression for longitudinal prediction and validated using cross-sectional Year 4 data.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages11

Reading Time28 min

AccessFree to download

Objective

Methods

Results

Conclusion

Introduction

Background on dementia and aging

Cognitive impairment screening

Rationale for prediction models

International Journal of Public Health ORIGINAL ARTICLE published: 19 January 2023 doi: 10.3389/ijph.2023.1605322 | | | | | --- | --- | --- | | | | | | Using Machine Learning to Predict | | | | Cognitive Impairment Among | | | | Middle-Aged and Older Chinese: A | | | | Longitudinal Study | | | | Haihong Liu 1,2, Xiaolei Zhang 3,4, Haining Liu 2,5,6* and Sheau Tsuey Chong 1, 7* | | | | 1Centre for Research in Psychology and Human Well-being, Faculty of Social Sciences and Humanities, Universiti Kebangsaan | | | | Malaysia, Bangi, Malaysia, 2Department of Psychology, Chengde Medical University, Chengde, China, 3Department of | | | | Biomedical Engineering, Chengde Medical University, Chengde, China, 4Faculty of Engineering, Universiti Putra Malaysia, | | | | Serdang, Malaysia, 5Hebei Key Laboratory of Nerve Injury and Repair, Chengde Medical University, Chengde, China, 6Hebei | | | | International Research Center of Medical Engineering, Chengde Medical University, Chengde, China, 7Counselling Psychology | | | | Programme, Secretariat of Postgraduate Studies, Faculty of Social Sciences and Humanities, Universiti Kebangsaan Malaysia, | | | | Bangi, Malaysia | | | | Objective: To explore the predictive value of machine learning in cognitive impairment, | | | | and identify important factors for cognitive impairment. | | | | | Methods: A total of 2,326 middle-aged and elderly people completed questionnaire, and | | | Edited by:
Gabriel Gulis,
University of Southern Denmark,
Denmark | physical examination evaluation at baseline, Year 2, and Year 4 follow-ups. A random forest machine learning (ML) model was used to predict the cognitive impairment at Year 2 and Year 4 longitudinally. Based on Year 4 cross-sectional data, the same method was | | | Reviewed by: applied to establish a prediction model and verify its longitudinal prediction accuracy for | | | | Alessandra Costanza,
University of Geneva, Switzerland
*Correspondence:
Haining Liu | cognitive impairment. Meanwhile, the ability of random forest and traditional logistic regression model to longitudinally predict 2-year and 4-year cognitive impairment was compared. | | | [liuhn0401@sina.com](liuhn0401@sina.com)
Sheau Tsuey Chong | Results: Random forest models showed high accuracy for all outcomes at Year 2, Year 4, | | | [stchong@ukm.edu.my](stchong@ukm.edu.my) and cross-sectional Year 4 [AUC = 0 .81, 0 .79, 0 .80] compared with logistic regression | | | | This Original Article is part of the IJPH
Special Issue “Public Health and
Primary Care, is 1+1=1?” | [AUC = 0 .61, 0 .62, 0 .70] . Baseline physical examination (e.g. , BMI, Blood pressure), biomarkers (e.g. , cholesterol), functioning (e.g. , functional limitations), demography (e.g. , age), and emotional status (e.g., depression) characteristics were identiﬁed as the top ten | | | Received: 15 August 2022
Accepted: 09 January 2023
Published: 19 January 2023 | important predictors of cognitive impairment.
Conclusion: ML algorithms could enhance the prediction of cognitive impairment among | | | Citation: the middle-aged and older Chinese for 4 years and identify essential risk markers. Liu H, Zhang X, Liu H and Chong ST | | | | (2023) Using Machine Learning to Keywords: longitudinal study, machine learning, random forest, middle-aged and older Chinese, cognitive | | | | Predict Cognitive Impairment Among impairment, dementia | | | | Middle-Aged and Older Chinese: A | | | | Longitudinal Study.
Int J Public Health 68:1605322. Abbreviations: ADL, activities of daily living; CHARLS, China health and retirement longitudinal study; IADL, instrumental | | | | doi: 10.3389/ijph.2023.1605322 activities of daily living; ML, machine learning; TICS, telephone interview of cognitive status. | | | Int J Public Health | Owned by SSPH+ | Published by Frontiers 1 January 2023 | Volume 68 | Article 1605322 INTRODUCTION With the curre

FAQs

What is the main objective of this study?

The study explores the predictive value of machine learning for cognitive impairment and identifies important factors related to cognitive impairment.

What data and modeling approach are used to make predictions?

Questionnaire and physical examination evaluations are collected at baseline with follow-ups at Years 2 and 4, and a random forest machine learning model predicts cognitive impairment at both follow-up points.

How do random forest and logistic regression compare in performance?

Random forest shows high accuracy for outcomes at Year 2 and Year 4, and its longitudinal prediction performance is compared against logistic regression using AUC values.

Aug 4, 2026

Upload by Himbo