Machine learning for the prediction of cognitive impairment in older adults - Original Research

Aug 5, 2026

Upload by Logic

This original research develops and validates machine learning models to predict cognitive impairment in older adults. Data from 2,226 participants aged 60–80 are extracted from the 2011–2014 NHANES database and evaluated using composite cognitive functioning scores based on multiple neuropsychological tests. Thirteen demographic and risk-factor variables are screened with the Boruta algorithm, while GLM, random forest, SVM, ANN, and stochastic gradient boosting are trained via ten-fold cross-validation. Results identify 10 key variables and show GLM provides the strongest predictive discrimination and clinical utility.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages11

Reading Time28 min

AccessFree to download

Objective

Methods

Participants and data source

Cognitive assessment

Variables and feature selection

Model building and evaluation

Results

Conclusions

Introduction

TYPE Original Research PUBLISHED 27 April 2023 DOI 10. 3389/fnins.2023.1158141 OPEN ACCESS EDITED BY Fengpei Hu, Zhejiang University of Technology, China REVIEWED BY Kuldeep Kumar, Bond University, Australia Zhenggang Bai, Nanjing University of Science and Technology, China *CORRESPONDENCE Jun Lyu [lyujun2020@jnu.edu.cn](lyujun2020@jnu.edu.cn)[ ](lyujun2020@jnu.edu.cn)Zhuoming Chen [zm120tchzm@qq.com](zm120tchzm@qq.com) †These authors have contributed equally to this work RECEIVED 03 February 2023 ACCEPTED 10 April 2023 PUBLISHED 27 April 2023 CITATION Li W, Zeng L, Yuan S, Shang Y, Zhuang W, Chen Z and Lyu J (2023) Machine learning for the prediction of cognitive impairment in older adults. Front. Neurosci. 17:1158141 . doi: 10.3389/fnins.2023.1158141 COPYRIGHT © 2023 Li, Zeng, Yuan, Shang, Zhuang, Chen and Lyu. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY) . The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms. Machine learning for the prediction of cognitive impairment in older adults Wanyue Li1†, Li Zeng2†, Shiqi Yuan3†, Yaru Shang1 , Weisheng Zhuang4 , Zhuoming Chen1* and Jun Lyu5,6* 1 Department of Rehabilitation, The First A􀀈liated Hospital of Jinan University, Guangzhou, Guangdong, China, 2The Second Clinical Medical College of Guizhou University of Traditional Chinese Medicine, Guiyang, Guizhou, China, 3 Department of Neurology, The First A􀀈liated Hospital of Jinan University, Guangzhou, Guangdong, China, 4 Department of Rehabilitation, Henan Provincial People’s Hospital, People’s Hospital of Zhengzhou University, Zhengzhou, Henan, China, 5 Department of Clinical Research, The First A􀀈liated Hospital of Jinan University, Guangzhou, Guangdong, China, 6 Guangdong Provincial Key Laboratory of Traditional Chinese Medicine Informatization, Guangzhou, Guangdong, China Objective: The purpose of this study was to develop and validate a predictive model of cognitive impairment in older adults based on a novel machine learning (ML) algorithm. Methods: The complete data of 2,226 participants aged 60–80 years were extracted from the 2011–2014 National Health and Nutrition Examination Survey database. Cognitive abilities were assessed using a composite cognitive functioning score (Z-score) calculated using a correlation test among the Consortium to Establish a Registry for Alzheimer’s Disease Word Learning and Delayed Recall tests, Animal Fluency Test, and the Digit Symbol Substitution Test. Thirteen demographic characteristics and risk factors associated with cognitive impairment were considered: age, sex, race, body mass index (BMI), drink, smoke, direct HDL-cholesterol level, stroke history, dietary inﬂammatory index (DII), glycated hemoglobin (HbA1c), Patient Health Questionnaire-9 (PHQ-9) score, sleep duration, and albumin level. Feature selection is performed using the Boruta algorithm. Model building is performed using ten-fold cross-validation, machine learning (ML) algorithms such as generalized linear model (GLM), random forest (RF), support vector machine (SVM), artiﬁcial neural network (ANN), and stochastic gradient boosting (SGB) . The performance of these models was evaluated in terms of discriminatory power and clinical application. Results: The study ultimately included 2,226 older adults for analysis, of whom 384 (17 . 25%) had cognitive impairment. After random assignment, 1,559 and 667 older adults were included in the training and test sets, respectively. A total of 10 variables such as age, race, BMI, direct HDL-cholesterol level, stroke history, DII, HbA1c, PHQ-9 score, sleep duration, and albumin level were se

FAQs

What is the study objective regarding cognitive impairment?

To develop and validate a predictive model for cognitive impairment in older adults using a novel machine learning approach.

How were participants and cognitive abilities assessed?

Complete data from 2,226 participants aged 60–80 were taken from NHANES, and cognitive abilities were quantified using a composite cognitive functioning Z-score derived from multiple cognitive tests.

Which model showed the best predictive performance and why does it matter?

The GLM model achieved the best performance in discriminatory power and clinical application, suggesting practical reliability for predicting cognitive impairment risk.

Aug 5, 2026

Upload by Logic