Sleep classification from wrist-worn accelerometer data using random forests

Abstract Accurate and low-cost sleep measurement tools are needed in both clinical and epidemiological research. To this end, wearable accelerometers are widely used as they are both low in price and provide reasonably accurate estimates of movement. Techniques to classify sleep from the high-resolu...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Kalaivani Sundararajan, Sonja Georgievska, Bart H. W. te Lindert, Philip R. Gehrman, Jennifer Ramautar, Diego R. Mazzotti, Séverine Sabia, Michael N. Weedon, Eus J. W. van Someren, Lars Ridder, Jian Wang, Vincent T. van Hees
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/97baecca4ff44f33ac66c0224412daae
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:97baecca4ff44f33ac66c0224412daae
record_format	dspace
spelling	oai:doaj.org-article:97baecca4ff44f33ac66c0224412daae2021-12-02T11:45:55ZSleep classification from wrist-worn accelerometer data using random forests10.1038/s41598-020-79217-x2045-2322https://doaj.org/article/97baecca4ff44f33ac66c0224412daae2021-01-01T00:00:00Zhttps://doi.org/10.1038/s41598-020-79217-xhttps://doaj.org/toc/2045-2322Abstract Accurate and low-cost sleep measurement tools are needed in both clinical and epidemiological research. To this end, wearable accelerometers are widely used as they are both low in price and provide reasonably accurate estimates of movement. Techniques to classify sleep from the high-resolution accelerometer data primarily rely on heuristic algorithms. In this paper, we explore the potential of detecting sleep using Random forests. Models were trained using data from three different studies where 134 adult participants (70 with sleep disorder and 64 good healthy sleepers) wore an accelerometer on their wrist during a one-night polysomnography recording in the clinic. The Random forests were able to distinguish sleep-wake states with an F1 score of 73.93% on a previously unseen test set of 24 participants. Detecting when the accelerometer is not worn was also successful using machine learning ( $$\hbox {F1-score} > 93.31\%$$ F1-score > 93.31 % ), and when combined with our sleep detection models on day-time data provide a sleep estimate that is correlated with self-reported habitual nap behaviour ( $$\hbox {r}=.60$$ r = . 60 ). These Random forest models have been made open-source to aid further research. In line with literature, sleep stage classification turned out to be difficult using only accelerometer data.Kalaivani SundararajanSonja GeorgievskaBart H. W. te LindertPhilip R. GehrmanJennifer RamautarDiego R. MazzottiSéverine SabiaMichael N. WeedonEus J. W. van SomerenLars RidderJian WangVincent T. van HeesNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-10 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Kalaivani Sundararajan Sonja Georgievska Bart H. W. te Lindert Philip R. Gehrman Jennifer Ramautar Diego R. Mazzotti Séverine Sabia Michael N. Weedon Eus J. W. van Someren Lars Ridder Jian Wang Vincent T. van Hees Sleep classification from wrist-worn accelerometer data using random forests
description	Abstract Accurate and low-cost sleep measurement tools are needed in both clinical and epidemiological research. To this end, wearable accelerometers are widely used as they are both low in price and provide reasonably accurate estimates of movement. Techniques to classify sleep from the high-resolution accelerometer data primarily rely on heuristic algorithms. In this paper, we explore the potential of detecting sleep using Random forests. Models were trained using data from three different studies where 134 adult participants (70 with sleep disorder and 64 good healthy sleepers) wore an accelerometer on their wrist during a one-night polysomnography recording in the clinic. The Random forests were able to distinguish sleep-wake states with an F1 score of 73.93% on a previously unseen test set of 24 participants. Detecting when the accelerometer is not worn was also successful using machine learning ( $$\hbox {F1-score} > 93.31\%$$ F1-score > 93.31 % ), and when combined with our sleep detection models on day-time data provide a sleep estimate that is correlated with self-reported habitual nap behaviour ( $$\hbox {r}=.60$$ r = . 60 ). These Random forest models have been made open-source to aid further research. In line with literature, sleep stage classification turned out to be difficult using only accelerometer data.
format	article
author	Kalaivani Sundararajan Sonja Georgievska Bart H. W. te Lindert Philip R. Gehrman Jennifer Ramautar Diego R. Mazzotti Séverine Sabia Michael N. Weedon Eus J. W. van Someren Lars Ridder Jian Wang Vincent T. van Hees
author_facet	Kalaivani Sundararajan Sonja Georgievska Bart H. W. te Lindert Philip R. Gehrman Jennifer Ramautar Diego R. Mazzotti Séverine Sabia Michael N. Weedon Eus J. W. van Someren Lars Ridder Jian Wang Vincent T. van Hees
author_sort	Kalaivani Sundararajan
title	Sleep classification from wrist-worn accelerometer data using random forests
title_short	Sleep classification from wrist-worn accelerometer data using random forests
title_full	Sleep classification from wrist-worn accelerometer data using random forests
title_fullStr	Sleep classification from wrist-worn accelerometer data using random forests
title_full_unstemmed	Sleep classification from wrist-worn accelerometer data using random forests
title_sort	sleep classification from wrist-worn accelerometer data using random forests
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/97baecca4ff44f33ac66c0224412daae
work_keys_str_mv	AT kalaivanisundararajan sleepclassificationfromwristwornaccelerometerdatausingrandomforests AT sonjageorgievska sleepclassificationfromwristwornaccelerometerdatausingrandomforests AT barthwtelindert sleepclassificationfromwristwornaccelerometerdatausingrandomforests AT philiprgehrman sleepclassificationfromwristwornaccelerometerdatausingrandomforests AT jenniferramautar sleepclassificationfromwristwornaccelerometerdatausingrandomforests AT diegormazzotti sleepclassificationfromwristwornaccelerometerdatausingrandomforests AT severinesabia sleepclassificationfromwristwornaccelerometerdatausingrandomforests AT michaelnweedon sleepclassificationfromwristwornaccelerometerdatausingrandomforests AT eusjwvansomeren sleepclassificationfromwristwornaccelerometerdatausingrandomforests AT larsridder sleepclassificationfromwristwornaccelerometerdatausingrandomforests AT jianwang sleepclassificationfromwristwornaccelerometerdatausingrandomforests AT vincenttvanhees sleepclassificationfromwristwornaccelerometerdatausingrandomforests
_version_	1718395241704194048

Sleep classification from wrist-worn accelerometer data using random forests

Ejemplares similares