A deep transfer learning approach for wearable sleep stage classification with photoplethysmography

Abstract Unobtrusive home sleep monitoring using wrist-worn wearable photoplethysmography (PPG) could open the way for better sleep disorder screening and health monitoring. However, PPG is rarely included in large sleep studies with gold-standard sleep annotation from polysomnography. Therefore, tr...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Mustafa Radha, Pedro Fonseca, Arnaud Moreau, Marco Ross, Andreas Cerny, Peter Anderer, Xi Long, Ronald M. Aarts
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Computer applications to medicine. Medical informatics R858-859.7
Acceso en línea:	https://doaj.org/article/fec60914d8ef48c2a357f505610bfa45
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:fec60914d8ef48c2a357f505610bfa45
record_format	dspace
spelling	oai:doaj.org-article:fec60914d8ef48c2a357f505610bfa452021-12-02T18:33:53ZA deep transfer learning approach for wearable sleep stage classification with photoplethysmography10.1038/s41746-021-00510-82398-6352https://doaj.org/article/fec60914d8ef48c2a357f505610bfa452021-09-01T00:00:00Zhttps://doi.org/10.1038/s41746-021-00510-8https://doaj.org/toc/2398-6352Abstract Unobtrusive home sleep monitoring using wrist-worn wearable photoplethysmography (PPG) could open the way for better sleep disorder screening and health monitoring. However, PPG is rarely included in large sleep studies with gold-standard sleep annotation from polysomnography. Therefore, training data-intensive state-of-the-art deep neural networks is challenging. In this work a deep recurrent neural network is first trained using a large sleep data set with electrocardiogram (ECG) data (292 participants, 584 recordings) to perform 4-class sleep stage classification (wake, rapid-eye-movement, N1/N2, and N3). A small part of its weights is adapted to a smaller, newer PPG data set (60 healthy participants, 101 recordings) through three variations of transfer learning. Best results (Cohen’s kappa of 0.65 ± 0.11, accuracy of 76.36 ± 7.57%) were achieved with the domain and decision combined transfer learning strategy, significantly outperforming the PPG-trained and ECG-trained baselines. This performance for PPG-based 4-class sleep stage classification is unprecedented in literature, bringing home sleep stage monitoring closer to clinical use. The work demonstrates the merit of transfer learning in developing reliable methods for new sensor technologies by reusing similar, older non-wearable data sets. Further study should evaluate our approach in patients with sleep disorders such as insomnia and sleep apnoea.Mustafa RadhaPedro FonsecaArnaud MoreauMarco RossAndreas CernyPeter AndererXi LongRonald M. AartsNature PortfolioarticleComputer applications to medicine. Medical informaticsR858-859.7ENnpj Digital Medicine, Vol 4, Iss 1, Pp 1-11 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Computer applications to medicine. Medical informatics R858-859.7
spellingShingle	Computer applications to medicine. Medical informatics R858-859.7 Mustafa Radha Pedro Fonseca Arnaud Moreau Marco Ross Andreas Cerny Peter Anderer Xi Long Ronald M. Aarts A deep transfer learning approach for wearable sleep stage classification with photoplethysmography
description	Abstract Unobtrusive home sleep monitoring using wrist-worn wearable photoplethysmography (PPG) could open the way for better sleep disorder screening and health monitoring. However, PPG is rarely included in large sleep studies with gold-standard sleep annotation from polysomnography. Therefore, training data-intensive state-of-the-art deep neural networks is challenging. In this work a deep recurrent neural network is first trained using a large sleep data set with electrocardiogram (ECG) data (292 participants, 584 recordings) to perform 4-class sleep stage classification (wake, rapid-eye-movement, N1/N2, and N3). A small part of its weights is adapted to a smaller, newer PPG data set (60 healthy participants, 101 recordings) through three variations of transfer learning. Best results (Cohen’s kappa of 0.65 ± 0.11, accuracy of 76.36 ± 7.57%) were achieved with the domain and decision combined transfer learning strategy, significantly outperforming the PPG-trained and ECG-trained baselines. This performance for PPG-based 4-class sleep stage classification is unprecedented in literature, bringing home sleep stage monitoring closer to clinical use. The work demonstrates the merit of transfer learning in developing reliable methods for new sensor technologies by reusing similar, older non-wearable data sets. Further study should evaluate our approach in patients with sleep disorders such as insomnia and sleep apnoea.
format	article
author	Mustafa Radha Pedro Fonseca Arnaud Moreau Marco Ross Andreas Cerny Peter Anderer Xi Long Ronald M. Aarts
author_facet	Mustafa Radha Pedro Fonseca Arnaud Moreau Marco Ross Andreas Cerny Peter Anderer Xi Long Ronald M. Aarts
author_sort	Mustafa Radha
title	A deep transfer learning approach for wearable sleep stage classification with photoplethysmography
title_short	A deep transfer learning approach for wearable sleep stage classification with photoplethysmography
title_full	A deep transfer learning approach for wearable sleep stage classification with photoplethysmography
title_fullStr	A deep transfer learning approach for wearable sleep stage classification with photoplethysmography
title_full_unstemmed	A deep transfer learning approach for wearable sleep stage classification with photoplethysmography
title_sort	deep transfer learning approach for wearable sleep stage classification with photoplethysmography
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/fec60914d8ef48c2a357f505610bfa45
work_keys_str_mv	AT mustafaradha adeeptransferlearningapproachforwearablesleepstageclassificationwithphotoplethysmography AT pedrofonseca adeeptransferlearningapproachforwearablesleepstageclassificationwithphotoplethysmography AT arnaudmoreau adeeptransferlearningapproachforwearablesleepstageclassificationwithphotoplethysmography AT marcoross adeeptransferlearningapproachforwearablesleepstageclassificationwithphotoplethysmography AT andreascerny adeeptransferlearningapproachforwearablesleepstageclassificationwithphotoplethysmography AT peteranderer adeeptransferlearningapproachforwearablesleepstageclassificationwithphotoplethysmography AT xilong adeeptransferlearningapproachforwearablesleepstageclassificationwithphotoplethysmography AT ronaldmaarts adeeptransferlearningapproachforwearablesleepstageclassificationwithphotoplethysmography AT mustafaradha deeptransferlearningapproachforwearablesleepstageclassificationwithphotoplethysmography AT pedrofonseca deeptransferlearningapproachforwearablesleepstageclassificationwithphotoplethysmography AT arnaudmoreau deeptransferlearningapproachforwearablesleepstageclassificationwithphotoplethysmography AT marcoross deeptransferlearningapproachforwearablesleepstageclassificationwithphotoplethysmography AT andreascerny deeptransferlearningapproachforwearablesleepstageclassificationwithphotoplethysmography AT peteranderer deeptransferlearningapproachforwearablesleepstageclassificationwithphotoplethysmography AT xilong deeptransferlearningapproachforwearablesleepstageclassificationwithphotoplethysmography AT ronaldmaarts deeptransferlearningapproachforwearablesleepstageclassificationwithphotoplethysmography
_version_	1718377958283935744

A deep transfer learning approach for wearable sleep stage classification with photoplethysmography

Ejemplares similares