Blood predictive biomarkers for cognitive impairment among community-dwelling older adults: a cross-sectional study in China

Abstract Cognitive impairment is a common health problem. However, it is often ignored in primary healthcare due to complex examination. To develop biomarkers through easily accessible blood tests, we conducted a cross-sectional analysis including 2806 healthy Chinese adults aged over 60 years old w...

Full description

Saved in:
Bibliographic Details
Main Authors: Bosi Dong, Mengqiao He, Shuming Ji, Wenjie Yang, Qiulei Hong, Yusha Tang, Anjiao Peng, Lei Chen
Format: Article
Language:English
Published: Nature Portfolio 2025-03-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-92764-5
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850030007583244288
author Bosi Dong
Mengqiao He
Shuming Ji
Wenjie Yang
Qiulei Hong
Yusha Tang
Anjiao Peng
Lei Chen
author_facet Bosi Dong
Mengqiao He
Shuming Ji
Wenjie Yang
Qiulei Hong
Yusha Tang
Anjiao Peng
Lei Chen
author_sort Bosi Dong
collection DOAJ
description Abstract Cognitive impairment is a common health problem. However, it is often ignored in primary healthcare due to complex examination. To develop biomarkers through easily accessible blood tests, we conducted a cross-sectional analysis including 2806 healthy Chinese adults aged over 60 years old who finished the cognition assessment though Mini-Mental State Examination as well as blood routine and biochemical examination from four communities in China between July 2020 and September 2021. The blood biomarkers commonly selected by RFE and LASSO with cross-validation in the training dataset were levels of hemoglobin, high density lipoprotein, alkaline phosphatase, direct bilirubin, globulin, creatinine, magnesium, and calcium. We developed XGBoost, logistic regression and SVM models with cross-validation in the training dataset and then evaluated their performance by the receiver operating characteristic curves, F1 score and decision curve analysis in the test dataset. The accuracies of the eight biomarkers in XGBoost, logistic regression and SVM models were 0.880 (0.846–0.915), 0.851 (0.812–0.889), and 0.852 (0.814–0.890) with confirmed clinical utility to predict cognitive impairment separately. Cognitive impairment can be predicted based on blood routine and biochemical examination with good discrimination, which could be helpful in detection and intervention at primary care.
format Article
id doaj-art-5df03cedb3184fa9acfce354ae4637dd
institution DOAJ
issn 2045-2322
language English
publishDate 2025-03-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-5df03cedb3184fa9acfce354ae4637dd2025-08-20T02:59:20ZengNature PortfolioScientific Reports2045-23222025-03-0115111010.1038/s41598-025-92764-5Blood predictive biomarkers for cognitive impairment among community-dwelling older adults: a cross-sectional study in ChinaBosi Dong0Mengqiao He1Shuming Ji2Wenjie Yang3Qiulei Hong4Yusha Tang5Anjiao Peng6Lei Chen7Department of Neurology, West China Hospital, Sichuan UniversityDepartment of Clinical Research Management, West China Hospital, Sichuan UniversityDepartment of Clinical Research Management, West China Hospital, Sichuan UniversityDepartment of Clinical Research Management, West China Hospital, Sichuan UniversityDepartment of Neurology, West China Hospital, Sichuan UniversityDepartment of Neurology, West China Hospital, Sichuan UniversityDepartment of Neurology, West China Hospital, Sichuan UniversityDepartment of Neurology, West China Hospital, Sichuan UniversityAbstract Cognitive impairment is a common health problem. However, it is often ignored in primary healthcare due to complex examination. To develop biomarkers through easily accessible blood tests, we conducted a cross-sectional analysis including 2806 healthy Chinese adults aged over 60 years old who finished the cognition assessment though Mini-Mental State Examination as well as blood routine and biochemical examination from four communities in China between July 2020 and September 2021. The blood biomarkers commonly selected by RFE and LASSO with cross-validation in the training dataset were levels of hemoglobin, high density lipoprotein, alkaline phosphatase, direct bilirubin, globulin, creatinine, magnesium, and calcium. We developed XGBoost, logistic regression and SVM models with cross-validation in the training dataset and then evaluated their performance by the receiver operating characteristic curves, F1 score and decision curve analysis in the test dataset. The accuracies of the eight biomarkers in XGBoost, logistic regression and SVM models were 0.880 (0.846–0.915), 0.851 (0.812–0.889), and 0.852 (0.814–0.890) with confirmed clinical utility to predict cognitive impairment separately. Cognitive impairment can be predicted based on blood routine and biochemical examination with good discrimination, which could be helpful in detection and intervention at primary care.https://doi.org/10.1038/s41598-025-92764-5Cognitive impairmentBiomarkerMachine learning
spellingShingle Bosi Dong
Mengqiao He
Shuming Ji
Wenjie Yang
Qiulei Hong
Yusha Tang
Anjiao Peng
Lei Chen
Blood predictive biomarkers for cognitive impairment among community-dwelling older adults: a cross-sectional study in China
Scientific Reports
Cognitive impairment
Biomarker
Machine learning
title Blood predictive biomarkers for cognitive impairment among community-dwelling older adults: a cross-sectional study in China
title_full Blood predictive biomarkers for cognitive impairment among community-dwelling older adults: a cross-sectional study in China
title_fullStr Blood predictive biomarkers for cognitive impairment among community-dwelling older adults: a cross-sectional study in China
title_full_unstemmed Blood predictive biomarkers for cognitive impairment among community-dwelling older adults: a cross-sectional study in China
title_short Blood predictive biomarkers for cognitive impairment among community-dwelling older adults: a cross-sectional study in China
title_sort blood predictive biomarkers for cognitive impairment among community dwelling older adults a cross sectional study in china
topic Cognitive impairment
Biomarker
Machine learning
url https://doi.org/10.1038/s41598-025-92764-5
work_keys_str_mv AT bosidong bloodpredictivebiomarkersforcognitiveimpairmentamongcommunitydwellingolderadultsacrosssectionalstudyinchina
AT mengqiaohe bloodpredictivebiomarkersforcognitiveimpairmentamongcommunitydwellingolderadultsacrosssectionalstudyinchina
AT shumingji bloodpredictivebiomarkersforcognitiveimpairmentamongcommunitydwellingolderadultsacrosssectionalstudyinchina
AT wenjieyang bloodpredictivebiomarkersforcognitiveimpairmentamongcommunitydwellingolderadultsacrosssectionalstudyinchina
AT qiuleihong bloodpredictivebiomarkersforcognitiveimpairmentamongcommunitydwellingolderadultsacrosssectionalstudyinchina
AT yushatang bloodpredictivebiomarkersforcognitiveimpairmentamongcommunitydwellingolderadultsacrosssectionalstudyinchina
AT anjiaopeng bloodpredictivebiomarkersforcognitiveimpairmentamongcommunitydwellingolderadultsacrosssectionalstudyinchina
AT leichen bloodpredictivebiomarkersforcognitiveimpairmentamongcommunitydwellingolderadultsacrosssectionalstudyinchina