Prediction of Decline in Global Cognitive Function Using Machine Learning with Feature Ranking of Gait and Physical Fitness Outcomes in Older Adults

Gait and physical fitness are related to cognitive function. A decrease in motor function and physical fitness can serve as an indicator of declining global cognitive function in older adults. This study aims to use machine learning (ML) to identify important features of gait and physical fitness to...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Byungjoo Noh, Hyemin Yoon, Changhong Youm, Sangjin Kim, Myeounggon Lee, Hwayoung Park, Bohyun Kim, Hyejin Choi, Yoonjae Noh
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	aging gait analysis physical fitness dementia machine learning inertial measurement unit Medicine R
Acceso en línea:	https://doaj.org/article/8d69453aeec14f33b43ab99b67f29faa
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:8d69453aeec14f33b43ab99b67f29faa
record_format	dspace
spelling	oai:doaj.org-article:8d69453aeec14f33b43ab99b67f29faa2021-11-11T16:28:50ZPrediction of Decline in Global Cognitive Function Using Machine Learning with Feature Ranking of Gait and Physical Fitness Outcomes in Older Adults10.3390/ijerph1821113471660-46011661-7827https://doaj.org/article/8d69453aeec14f33b43ab99b67f29faa2021-10-01T00:00:00Zhttps://www.mdpi.com/1660-4601/18/21/11347https://doaj.org/toc/1661-7827https://doaj.org/toc/1660-4601Gait and physical fitness are related to cognitive function. A decrease in motor function and physical fitness can serve as an indicator of declining global cognitive function in older adults. This study aims to use machine learning (ML) to identify important features of gait and physical fitness to predict a decline in global cognitive function in older adults. A total of three hundred and six participants aged seventy-five years or older were included in the study, and their gait performance at various speeds and physical fitness were evaluated. Eight ML models were applied to data ranked by the <i>p</i>-value (LP) of linear regression and the importance gain (XI) of XGboost. Five optimal features were selected using elastic net on the LP data for men, and twenty optimal features were selected using support vector machine on the XI data for women. Thus, the important features for predicting a potential decline in global cognitive function in older adults were successfully identified herein. The proposed ML approach could inspire future studies on the early detection and prevention of cognitive function decline in older adults.Byungjoo NohHyemin YoonChanghong YoumSangjin KimMyeounggon LeeHwayoung ParkBohyun KimHyejin ChoiYoonjae NohMDPI AGarticleaginggait analysisphysical fitnessdementiamachine learninginertial measurement unitMedicineRENInternational Journal of Environmental Research and Public Health, Vol 18, Iss 11347, p 11347 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	aging gait analysis physical fitness dementia machine learning inertial measurement unit Medicine R
spellingShingle	aging gait analysis physical fitness dementia machine learning inertial measurement unit Medicine R Byungjoo Noh Hyemin Yoon Changhong Youm Sangjin Kim Myeounggon Lee Hwayoung Park Bohyun Kim Hyejin Choi Yoonjae Noh Prediction of Decline in Global Cognitive Function Using Machine Learning with Feature Ranking of Gait and Physical Fitness Outcomes in Older Adults
description	Gait and physical fitness are related to cognitive function. A decrease in motor function and physical fitness can serve as an indicator of declining global cognitive function in older adults. This study aims to use machine learning (ML) to identify important features of gait and physical fitness to predict a decline in global cognitive function in older adults. A total of three hundred and six participants aged seventy-five years or older were included in the study, and their gait performance at various speeds and physical fitness were evaluated. Eight ML models were applied to data ranked by the <i>p</i>-value (LP) of linear regression and the importance gain (XI) of XGboost. Five optimal features were selected using elastic net on the LP data for men, and twenty optimal features were selected using support vector machine on the XI data for women. Thus, the important features for predicting a potential decline in global cognitive function in older adults were successfully identified herein. The proposed ML approach could inspire future studies on the early detection and prevention of cognitive function decline in older adults.
format	article
author	Byungjoo Noh Hyemin Yoon Changhong Youm Sangjin Kim Myeounggon Lee Hwayoung Park Bohyun Kim Hyejin Choi Yoonjae Noh
author_facet	Byungjoo Noh Hyemin Yoon Changhong Youm Sangjin Kim Myeounggon Lee Hwayoung Park Bohyun Kim Hyejin Choi Yoonjae Noh
author_sort	Byungjoo Noh
title	Prediction of Decline in Global Cognitive Function Using Machine Learning with Feature Ranking of Gait and Physical Fitness Outcomes in Older Adults
title_short	Prediction of Decline in Global Cognitive Function Using Machine Learning with Feature Ranking of Gait and Physical Fitness Outcomes in Older Adults
title_full	Prediction of Decline in Global Cognitive Function Using Machine Learning with Feature Ranking of Gait and Physical Fitness Outcomes in Older Adults
title_fullStr	Prediction of Decline in Global Cognitive Function Using Machine Learning with Feature Ranking of Gait and Physical Fitness Outcomes in Older Adults
title_full_unstemmed	Prediction of Decline in Global Cognitive Function Using Machine Learning with Feature Ranking of Gait and Physical Fitness Outcomes in Older Adults
title_sort	prediction of decline in global cognitive function using machine learning with feature ranking of gait and physical fitness outcomes in older adults
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/8d69453aeec14f33b43ab99b67f29faa
work_keys_str_mv	AT byungjoonoh predictionofdeclineinglobalcognitivefunctionusingmachinelearningwithfeaturerankingofgaitandphysicalfitnessoutcomesinolderadults AT hyeminyoon predictionofdeclineinglobalcognitivefunctionusingmachinelearningwithfeaturerankingofgaitandphysicalfitnessoutcomesinolderadults AT changhongyoum predictionofdeclineinglobalcognitivefunctionusingmachinelearningwithfeaturerankingofgaitandphysicalfitnessoutcomesinolderadults AT sangjinkim predictionofdeclineinglobalcognitivefunctionusingmachinelearningwithfeaturerankingofgaitandphysicalfitnessoutcomesinolderadults AT myeounggonlee predictionofdeclineinglobalcognitivefunctionusingmachinelearningwithfeaturerankingofgaitandphysicalfitnessoutcomesinolderadults AT hwayoungpark predictionofdeclineinglobalcognitivefunctionusingmachinelearningwithfeaturerankingofgaitandphysicalfitnessoutcomesinolderadults AT bohyunkim predictionofdeclineinglobalcognitivefunctionusingmachinelearningwithfeaturerankingofgaitandphysicalfitnessoutcomesinolderadults AT hyejinchoi predictionofdeclineinglobalcognitivefunctionusingmachinelearningwithfeaturerankingofgaitandphysicalfitnessoutcomesinolderadults AT yoonjaenoh predictionofdeclineinglobalcognitivefunctionusingmachinelearningwithfeaturerankingofgaitandphysicalfitnessoutcomesinolderadults
_version_	1718432309402664960

Prediction of Decline in Global Cognitive Function Using Machine Learning with Feature Ranking of Gait and Physical Fitness Outcomes in Older Adults

Ejemplares similares