Machine learning based prediction of cognitive metrics using major biomarkers in SuperAgers

Abstract As populations age, understanding cognitive decline and age-related diseases like dementia has become increasingly important. “SuperAgers,” individuals over 65 with cognitive abilities similar to those in their 40s, provide a unique perspective on cognitive reserve. This study analyzed 55 b...

Full description

Saved in:
Bibliographic Details
Main Authors: Hyo-Bin Lee, So-Yeon Kwon, Ji-Hae Park, Bori Kim, Geon-Ha Kim, Jang-Hwan Choi, Young Mi Park
Format: Article
Language:English
Published: Nature Portfolio 2025-05-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-01477-2
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849235412413841408
author Hyo-Bin Lee
So-Yeon Kwon
Ji-Hae Park
Bori Kim
Geon-Ha Kim
Jang-Hwan Choi
Young Mi Park
author_facet Hyo-Bin Lee
So-Yeon Kwon
Ji-Hae Park
Bori Kim
Geon-Ha Kim
Jang-Hwan Choi
Young Mi Park
author_sort Hyo-Bin Lee
collection DOAJ
description Abstract As populations age, understanding cognitive decline and age-related diseases like dementia has become increasingly important. “SuperAgers,” individuals over 65 with cognitive abilities similar to those in their 40s, provide a unique perspective on cognitive reserve. This study analyzed 55 blood biomarkers, including cellular components and metabolism/inflammation-related factors, in 39 SuperAgers and 42 typical agers. While conventional statistical analyses identified significant differences in only four biomarkers, advanced feature selection and machine learning techniques revealed a broader set of 15 key biomarkers associated with SuperAger status. A predictive model built using these biomarkers achieved an accuracy of 76% in cognitive domain prediction. To address the limitation of small sample sizes, data augmentation leveraging large language models improved the model’s robustness. Shapley Additive exPlanations (SHAP) provided interpretability, revealing the impact of specific blood factors on cognitive function. These findings suggest that certain blood biomarkers are not only associated with cognitive performance but may also serve as indicators of cognitive reserve. By utilizing simple blood tests, this research presents a clinically significant method for predicting cognitive function and identifying SuperAger status in healthy elderly individuals, offering a foundation for future studies on the biological mechanisms underpinning cognitive resilience.
format Article
id doaj-art-dc4c32cff3f8478da7a8d91df52f9457
institution Kabale University
issn 2045-2322
language English
publishDate 2025-05-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-dc4c32cff3f8478da7a8d91df52f94572025-08-20T04:02:46ZengNature PortfolioScientific Reports2045-23222025-05-0115112010.1038/s41598-025-01477-2Machine learning based prediction of cognitive metrics using major biomarkers in SuperAgersHyo-Bin Lee0So-Yeon Kwon1Ji-Hae Park2Bori Kim3Geon-Ha Kim4Jang-Hwan Choi5Young Mi Park6Department of Computational Medicine, Graduate Program in System Health Science and Engineering, Ewha Womans UniversityDepartment of Molecular Medicine, Ewha Womans UniversityDepartment of Molecular Medicine, Ewha Womans UniversityDepartment of Neurology, Ewha Womans University Mokdong Hospital, Ewha Womans UniversityDepartment of Neurology, Ewha Womans University Mokdong Hospital, Ewha Womans UniversityDepartment of Computational Medicine, Graduate Program in System Health Science and Engineering, Ewha Womans UniversityDepartment of Molecular Medicine, Ewha Womans UniversityAbstract As populations age, understanding cognitive decline and age-related diseases like dementia has become increasingly important. “SuperAgers,” individuals over 65 with cognitive abilities similar to those in their 40s, provide a unique perspective on cognitive reserve. This study analyzed 55 blood biomarkers, including cellular components and metabolism/inflammation-related factors, in 39 SuperAgers and 42 typical agers. While conventional statistical analyses identified significant differences in only four biomarkers, advanced feature selection and machine learning techniques revealed a broader set of 15 key biomarkers associated with SuperAger status. A predictive model built using these biomarkers achieved an accuracy of 76% in cognitive domain prediction. To address the limitation of small sample sizes, data augmentation leveraging large language models improved the model’s robustness. Shapley Additive exPlanations (SHAP) provided interpretability, revealing the impact of specific blood factors on cognitive function. These findings suggest that certain blood biomarkers are not only associated with cognitive performance but may also serve as indicators of cognitive reserve. By utilizing simple blood tests, this research presents a clinically significant method for predicting cognitive function and identifying SuperAger status in healthy elderly individuals, offering a foundation for future studies on the biological mechanisms underpinning cognitive resilience.https://doi.org/10.1038/s41598-025-01477-2Super-AgersCognitive functionBlood biomarkersMachine learningCognitive metric predictionRecursive feature elimination (RFE)
spellingShingle Hyo-Bin Lee
So-Yeon Kwon
Ji-Hae Park
Bori Kim
Geon-Ha Kim
Jang-Hwan Choi
Young Mi Park
Machine learning based prediction of cognitive metrics using major biomarkers in SuperAgers
Scientific Reports
Super-Agers
Cognitive function
Blood biomarkers
Machine learning
Cognitive metric prediction
Recursive feature elimination (RFE)
title Machine learning based prediction of cognitive metrics using major biomarkers in SuperAgers
title_full Machine learning based prediction of cognitive metrics using major biomarkers in SuperAgers
title_fullStr Machine learning based prediction of cognitive metrics using major biomarkers in SuperAgers
title_full_unstemmed Machine learning based prediction of cognitive metrics using major biomarkers in SuperAgers
title_short Machine learning based prediction of cognitive metrics using major biomarkers in SuperAgers
title_sort machine learning based prediction of cognitive metrics using major biomarkers in superagers
topic Super-Agers
Cognitive function
Blood biomarkers
Machine learning
Cognitive metric prediction
Recursive feature elimination (RFE)
url https://doi.org/10.1038/s41598-025-01477-2
work_keys_str_mv AT hyobinlee machinelearningbasedpredictionofcognitivemetricsusingmajorbiomarkersinsuperagers
AT soyeonkwon machinelearningbasedpredictionofcognitivemetricsusingmajorbiomarkersinsuperagers
AT jihaepark machinelearningbasedpredictionofcognitivemetricsusingmajorbiomarkersinsuperagers
AT borikim machinelearningbasedpredictionofcognitivemetricsusingmajorbiomarkersinsuperagers
AT geonhakim machinelearningbasedpredictionofcognitivemetricsusingmajorbiomarkersinsuperagers
AT janghwanchoi machinelearningbasedpredictionofcognitivemetricsusingmajorbiomarkersinsuperagers
AT youngmipark machinelearningbasedpredictionofcognitivemetricsusingmajorbiomarkersinsuperagers