Cargando…

A Multi-Level Classification Approach for Sleep Stage Prediction With Processed Data Derived From Consumer Wearable Activity Trackers

Consumer wearable activity trackers, such as Fitbit are widely used in ubiquitous and longitudinal sleep monitoring in free-living environments. However, these devices are known to be inaccurate for measuring sleep stages. In this study, we develop and validate a novel approach that leverages the pr...

Descripción completa

Detalles Bibliográficos
Autores principales: Liang, Zilu, Chapa-Martell, Mario Alberto
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8521802/
https://www.ncbi.nlm.nih.gov/pubmed/34713139
http://dx.doi.org/10.3389/fdgth.2021.665946
_version_ 1784584960967966720
author Liang, Zilu
Chapa-Martell, Mario Alberto
author_facet Liang, Zilu
Chapa-Martell, Mario Alberto
author_sort Liang, Zilu
collection PubMed
description Consumer wearable activity trackers, such as Fitbit are widely used in ubiquitous and longitudinal sleep monitoring in free-living environments. However, these devices are known to be inaccurate for measuring sleep stages. In this study, we develop and validate a novel approach that leverages the processed data readily available from consumer activity trackers (i.e., steps, heart rate, and sleep metrics) to predict sleep stages. The proposed approach adopts a selective correction strategy and consists of two levels of classifiers. The level-I classifier judges whether a Fitbit labeled sleep epoch is misclassified, and the level-II classifier re-classifies misclassified epochs into one of the four sleep stages (i.e., light sleep, deep sleep, REM sleep, and wakefulness). Best epoch-wise performance was achieved when support vector machine and gradient boosting decision tree (XGBoost) with up sampling were used, respectively at the level-I and level-II classification. The model achieved an overall per-epoch accuracy of 0.731 ± 0.119, Cohen's Kappa of 0.433 ± 0.212, and multi-class Matthew's correlation coefficient (MMCC) of 0.451 ± 0.214. Regarding the total duration of individual sleep stage, the mean normalized absolute bias (MAB) of this model was 0.469, which is a 23.9% reduction against the proprietary Fitbit algorithm. The model that combines support vector machine and XGBoost with down sampling achieved sub-optimal per-epoch accuracy of 0.704 ± 0.097, Cohen's Kappa of 0.427 ± 0.178, and MMCC of 0.439 ± 0.180. The sub-optimal model obtained a MAB of 0.179, a significantly reduction of 71.0% compared to the proprietary Fitbit algorithm. We highlight the challenges in machine learning based sleep stage prediction with consumer wearables, and suggest directions for future research.
format Online
Article
Text
id pubmed-8521802
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher Frontiers Media S.A.
record_format MEDLINE/PubMed
spelling pubmed-85218022021-10-27 A Multi-Level Classification Approach for Sleep Stage Prediction With Processed Data Derived From Consumer Wearable Activity Trackers Liang, Zilu Chapa-Martell, Mario Alberto Front Digit Health Digital Health Consumer wearable activity trackers, such as Fitbit are widely used in ubiquitous and longitudinal sleep monitoring in free-living environments. However, these devices are known to be inaccurate for measuring sleep stages. In this study, we develop and validate a novel approach that leverages the processed data readily available from consumer activity trackers (i.e., steps, heart rate, and sleep metrics) to predict sleep stages. The proposed approach adopts a selective correction strategy and consists of two levels of classifiers. The level-I classifier judges whether a Fitbit labeled sleep epoch is misclassified, and the level-II classifier re-classifies misclassified epochs into one of the four sleep stages (i.e., light sleep, deep sleep, REM sleep, and wakefulness). Best epoch-wise performance was achieved when support vector machine and gradient boosting decision tree (XGBoost) with up sampling were used, respectively at the level-I and level-II classification. The model achieved an overall per-epoch accuracy of 0.731 ± 0.119, Cohen's Kappa of 0.433 ± 0.212, and multi-class Matthew's correlation coefficient (MMCC) of 0.451 ± 0.214. Regarding the total duration of individual sleep stage, the mean normalized absolute bias (MAB) of this model was 0.469, which is a 23.9% reduction against the proprietary Fitbit algorithm. The model that combines support vector machine and XGBoost with down sampling achieved sub-optimal per-epoch accuracy of 0.704 ± 0.097, Cohen's Kappa of 0.427 ± 0.178, and MMCC of 0.439 ± 0.180. The sub-optimal model obtained a MAB of 0.179, a significantly reduction of 71.0% compared to the proprietary Fitbit algorithm. We highlight the challenges in machine learning based sleep stage prediction with consumer wearables, and suggest directions for future research. Frontiers Media S.A. 2021-05-28 /pmc/articles/PMC8521802/ /pubmed/34713139 http://dx.doi.org/10.3389/fdgth.2021.665946 Text en Copyright © 2021 Liang and Chapa-Martell. https://creativecommons.org/licenses/by/4.0/This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
spellingShingle Digital Health
Liang, Zilu
Chapa-Martell, Mario Alberto
A Multi-Level Classification Approach for Sleep Stage Prediction With Processed Data Derived From Consumer Wearable Activity Trackers
title A Multi-Level Classification Approach for Sleep Stage Prediction With Processed Data Derived From Consumer Wearable Activity Trackers
title_full A Multi-Level Classification Approach for Sleep Stage Prediction With Processed Data Derived From Consumer Wearable Activity Trackers
title_fullStr A Multi-Level Classification Approach for Sleep Stage Prediction With Processed Data Derived From Consumer Wearable Activity Trackers
title_full_unstemmed A Multi-Level Classification Approach for Sleep Stage Prediction With Processed Data Derived From Consumer Wearable Activity Trackers
title_short A Multi-Level Classification Approach for Sleep Stage Prediction With Processed Data Derived From Consumer Wearable Activity Trackers
title_sort multi-level classification approach for sleep stage prediction with processed data derived from consumer wearable activity trackers
topic Digital Health
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8521802/
https://www.ncbi.nlm.nih.gov/pubmed/34713139
http://dx.doi.org/10.3389/fdgth.2021.665946
work_keys_str_mv AT liangzilu amultilevelclassificationapproachforsleepstagepredictionwithprocesseddataderivedfromconsumerwearableactivitytrackers
AT chapamartellmarioalberto amultilevelclassificationapproachforsleepstagepredictionwithprocesseddataderivedfromconsumerwearableactivitytrackers
AT liangzilu multilevelclassificationapproachforsleepstagepredictionwithprocesseddataderivedfromconsumerwearableactivitytrackers
AT chapamartellmarioalberto multilevelclassificationapproachforsleepstagepredictionwithprocesseddataderivedfromconsumerwearableactivitytrackers