Cargando…

Age Differences in Estimating Physical Activity by Wrist Accelerometry Using Machine Learning

Accelerometer-based fitness trackers and smartwatches are proliferating with incessant attention towards health tracking. Despite their growing popularity, accurately measuring hallmark measures of physical activities has yet to be accomplished in adults of all ages. In this work, we evaluated the p...

Descripción completa

Detalles Bibliográficos
Autores principales: Mardini, Mamoun T., Bai, Chen, Wanigatunga, Amal A., Saldana, Santiago, Casanova, Ramon, Manini, Todd M.
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8150764/
https://www.ncbi.nlm.nih.gov/pubmed/34065906
http://dx.doi.org/10.3390/s21103352
_version_ 1783698225147936768
author Mardini, Mamoun T.
Bai, Chen
Wanigatunga, Amal A.
Saldana, Santiago
Casanova, Ramon
Manini, Todd M.
author_facet Mardini, Mamoun T.
Bai, Chen
Wanigatunga, Amal A.
Saldana, Santiago
Casanova, Ramon
Manini, Todd M.
author_sort Mardini, Mamoun T.
collection PubMed
description Accelerometer-based fitness trackers and smartwatches are proliferating with incessant attention towards health tracking. Despite their growing popularity, accurately measuring hallmark measures of physical activities has yet to be accomplished in adults of all ages. In this work, we evaluated the performance of four machine learning models: decision tree, random forest, extreme gradient boosting (XGBoost) and least absolute shrinkage and selection operator (LASSO), to estimate the hallmark measures of physical activities in young (20–50 years), middle-aged (50–70 years], and older adults (70–89 years]. Our models were built to recognize physical activity types, recognize physical activity intensities, estimate energy expenditure (EE) and recognize individual physical activities using wrist-worn tri-axial accelerometer data (33 activities per participant) from a large sample of participants (n = 253, 62% women, aged 20–89 years old). Results showed that the machine learning models were quite accurate at recognizing physical activity type and intensity and estimating energy expenditure. However, models performed less optimally when recognizing individual physical activities. F1-Scores derived from XGBoost’s models were high for sedentary (0.955–0.973), locomotion (0.942–0.964) and lifestyle (0.913–0.949) activity types with no apparent difference across age groups. Low (0.919–0.947), light (0.813–0.828) and moderate (0.846–0.875) physical activity intensities were also recognized accurately. The root mean square error range for EE was approximately 1 equivalent of resting EE [0.835–1.009 METs]. Generally, random forest and XGBoost models outperformed other models. In conclusion, machine learning models to label physical activity types, activity intensity and energy expenditure are accurate and there are minimal differences in their performance across young, middle-aged and older adults.
format Online
Article
Text
id pubmed-8150764
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-81507642021-05-27 Age Differences in Estimating Physical Activity by Wrist Accelerometry Using Machine Learning Mardini, Mamoun T. Bai, Chen Wanigatunga, Amal A. Saldana, Santiago Casanova, Ramon Manini, Todd M. Sensors (Basel) Article Accelerometer-based fitness trackers and smartwatches are proliferating with incessant attention towards health tracking. Despite their growing popularity, accurately measuring hallmark measures of physical activities has yet to be accomplished in adults of all ages. In this work, we evaluated the performance of four machine learning models: decision tree, random forest, extreme gradient boosting (XGBoost) and least absolute shrinkage and selection operator (LASSO), to estimate the hallmark measures of physical activities in young (20–50 years), middle-aged (50–70 years], and older adults (70–89 years]. Our models were built to recognize physical activity types, recognize physical activity intensities, estimate energy expenditure (EE) and recognize individual physical activities using wrist-worn tri-axial accelerometer data (33 activities per participant) from a large sample of participants (n = 253, 62% women, aged 20–89 years old). Results showed that the machine learning models were quite accurate at recognizing physical activity type and intensity and estimating energy expenditure. However, models performed less optimally when recognizing individual physical activities. F1-Scores derived from XGBoost’s models were high for sedentary (0.955–0.973), locomotion (0.942–0.964) and lifestyle (0.913–0.949) activity types with no apparent difference across age groups. Low (0.919–0.947), light (0.813–0.828) and moderate (0.846–0.875) physical activity intensities were also recognized accurately. The root mean square error range for EE was approximately 1 equivalent of resting EE [0.835–1.009 METs]. Generally, random forest and XGBoost models outperformed other models. In conclusion, machine learning models to label physical activity types, activity intensity and energy expenditure are accurate and there are minimal differences in their performance across young, middle-aged and older adults. MDPI 2021-05-12 /pmc/articles/PMC8150764/ /pubmed/34065906 http://dx.doi.org/10.3390/s21103352 Text en © 2021 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Mardini, Mamoun T.
Bai, Chen
Wanigatunga, Amal A.
Saldana, Santiago
Casanova, Ramon
Manini, Todd M.
Age Differences in Estimating Physical Activity by Wrist Accelerometry Using Machine Learning
title Age Differences in Estimating Physical Activity by Wrist Accelerometry Using Machine Learning
title_full Age Differences in Estimating Physical Activity by Wrist Accelerometry Using Machine Learning
title_fullStr Age Differences in Estimating Physical Activity by Wrist Accelerometry Using Machine Learning
title_full_unstemmed Age Differences in Estimating Physical Activity by Wrist Accelerometry Using Machine Learning
title_short Age Differences in Estimating Physical Activity by Wrist Accelerometry Using Machine Learning
title_sort age differences in estimating physical activity by wrist accelerometry using machine learning
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8150764/
https://www.ncbi.nlm.nih.gov/pubmed/34065906
http://dx.doi.org/10.3390/s21103352
work_keys_str_mv AT mardinimamount agedifferencesinestimatingphysicalactivitybywristaccelerometryusingmachinelearning
AT baichen agedifferencesinestimatingphysicalactivitybywristaccelerometryusingmachinelearning
AT wanigatungaamala agedifferencesinestimatingphysicalactivitybywristaccelerometryusingmachinelearning
AT saldanasantiago agedifferencesinestimatingphysicalactivitybywristaccelerometryusingmachinelearning
AT casanovaramon agedifferencesinestimatingphysicalactivitybywristaccelerometryusingmachinelearning
AT maninitoddm agedifferencesinestimatingphysicalactivitybywristaccelerometryusingmachinelearning