Cargando…
Are Machine Learning Models Used to Represent Accelerometry Data Robust to Age Differences?
Regular and sufficient amounts of physical activity (PA) are significant in increasing health benefits and mitigating health risks. Given the growing popularity of wrist-worn devices across all age groups, a rigorous evaluation for recognizing hallmark measures of physical activities and estimating...
Autores principales: | , , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Oxford University Press
2021
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8681343/ http://dx.doi.org/10.1093/geroni/igab046.2880 |
_version_ | 1784616954530627584 |
---|---|
author | Manini, Todd Bai, Chen Wanigatunga, Amal Saldana, Santiago Casanova, Ramon Mardini, Mamoun |
author_facet | Manini, Todd Bai, Chen Wanigatunga, Amal Saldana, Santiago Casanova, Ramon Mardini, Mamoun |
author_sort | Manini, Todd |
collection | PubMed |
description | Regular and sufficient amounts of physical activity (PA) are significant in increasing health benefits and mitigating health risks. Given the growing popularity of wrist-worn devices across all age groups, a rigorous evaluation for recognizing hallmark measures of physical activities and estimating energy expenditure is needed to compare their accuracy across the lifespan. The goal of the study was to build machine learning models to recognizing the hallmark measures of PA and estimating energy expenditure (EE), and to test the hypothesis that model performance varies across age-group: young [20-50 years], middle (50-70 years], and old (70-89 years]. Participants (n = 253, 62% women, aged 20-89 years old) performed a battery of 33 daily activities in a standardized laboratory setting while wearing a portable metabolic unit to measure EE that was used to gauge metabolic intensity. Participants also wore a Tri-axial accelerometer on the right wrist. Results from random forests algorithm were quite accurate at recognizing PA type; the F1-Score range across age groups was: sedentary [0.955 – 0.973], locomotion [0.942 – 0.964], and lifestyle [0.913 – 0.949]. Recognizing PA intensity resulted in lower performance; the F1-Score range across age groups was: sedentary [0.919 – 0.947], light [0.813 – 0.828], and moderate [0.846–0.875]. The root mean square error range was [0.835–1.009] for the estimation of EE. The F1-Score range for recognizing individual PAs was [0.263–0.784]. In conclusion, machine learning models used to represent accelerometry data are robust to age differences and a generalizable approach might be sufficient to utilize in accelerometer-based wearables. |
format | Online Article Text |
id | pubmed-8681343 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2021 |
publisher | Oxford University Press |
record_format | MEDLINE/PubMed |
spelling | pubmed-86813432021-12-17 Are Machine Learning Models Used to Represent Accelerometry Data Robust to Age Differences? Manini, Todd Bai, Chen Wanigatunga, Amal Saldana, Santiago Casanova, Ramon Mardini, Mamoun Innov Aging Abstracts Regular and sufficient amounts of physical activity (PA) are significant in increasing health benefits and mitigating health risks. Given the growing popularity of wrist-worn devices across all age groups, a rigorous evaluation for recognizing hallmark measures of physical activities and estimating energy expenditure is needed to compare their accuracy across the lifespan. The goal of the study was to build machine learning models to recognizing the hallmark measures of PA and estimating energy expenditure (EE), and to test the hypothesis that model performance varies across age-group: young [20-50 years], middle (50-70 years], and old (70-89 years]. Participants (n = 253, 62% women, aged 20-89 years old) performed a battery of 33 daily activities in a standardized laboratory setting while wearing a portable metabolic unit to measure EE that was used to gauge metabolic intensity. Participants also wore a Tri-axial accelerometer on the right wrist. Results from random forests algorithm were quite accurate at recognizing PA type; the F1-Score range across age groups was: sedentary [0.955 – 0.973], locomotion [0.942 – 0.964], and lifestyle [0.913 – 0.949]. Recognizing PA intensity resulted in lower performance; the F1-Score range across age groups was: sedentary [0.919 – 0.947], light [0.813 – 0.828], and moderate [0.846–0.875]. The root mean square error range was [0.835–1.009] for the estimation of EE. The F1-Score range for recognizing individual PAs was [0.263–0.784]. In conclusion, machine learning models used to represent accelerometry data are robust to age differences and a generalizable approach might be sufficient to utilize in accelerometer-based wearables. Oxford University Press 2021-12-17 /pmc/articles/PMC8681343/ http://dx.doi.org/10.1093/geroni/igab046.2880 Text en © The Author(s) 2021. Published by Oxford University Press on behalf of The Gerontological Society of America. https://creativecommons.org/licenses/by/4.0/This is an Open Access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0/ (https://creativecommons.org/licenses/by/4.0/) ), which permits unrestricted reuse, distribution, and reproduction in any medium, provided the original work is properly cited. |
spellingShingle | Abstracts Manini, Todd Bai, Chen Wanigatunga, Amal Saldana, Santiago Casanova, Ramon Mardini, Mamoun Are Machine Learning Models Used to Represent Accelerometry Data Robust to Age Differences? |
title | Are Machine Learning Models Used to Represent Accelerometry Data Robust to Age Differences? |
title_full | Are Machine Learning Models Used to Represent Accelerometry Data Robust to Age Differences? |
title_fullStr | Are Machine Learning Models Used to Represent Accelerometry Data Robust to Age Differences? |
title_full_unstemmed | Are Machine Learning Models Used to Represent Accelerometry Data Robust to Age Differences? |
title_short | Are Machine Learning Models Used to Represent Accelerometry Data Robust to Age Differences? |
title_sort | are machine learning models used to represent accelerometry data robust to age differences? |
topic | Abstracts |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8681343/ http://dx.doi.org/10.1093/geroni/igab046.2880 |
work_keys_str_mv | AT maninitodd aremachinelearningmodelsusedtorepresentaccelerometrydatarobusttoagedifferences AT baichen aremachinelearningmodelsusedtorepresentaccelerometrydatarobusttoagedifferences AT wanigatungaamal aremachinelearningmodelsusedtorepresentaccelerometrydatarobusttoagedifferences AT saldanasantiago aremachinelearningmodelsusedtorepresentaccelerometrydatarobusttoagedifferences AT casanovaramon aremachinelearningmodelsusedtorepresentaccelerometrydatarobusttoagedifferences AT mardinimamoun aremachinelearningmodelsusedtorepresentaccelerometrydatarobusttoagedifferences |