Atrial Fibrillation Classification with Smart Wearables Using Short-Term Heart Rate Variability and Deep Convolutional Neural Networks

Atrial fibrillation (AF) is a type of cardiac arrhythmia affecting millions of people every year. This disease increases the likelihood of strokes, heart failure, and even death. While dedicated medical-grade electrocardiogram (ECG) devices can enable gold-standard analysis, these devices are expens...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Jayroop Ramesh, Zahra Solatidehkordi, Raafat Aburukba, Assim Sagahyroon
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	biomedical informatics cardiovascular disease deep learning ECG heart rate variability machine learning Chemical technology TP1-1185
Acceso en línea:	https://doaj.org/article/9e1fbb2eb0884ead84f1122170641e29
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:9e1fbb2eb0884ead84f1122170641e29
record_format	dspace
spelling	oai:doaj.org-article:9e1fbb2eb0884ead84f1122170641e292021-11-11T19:12:31ZAtrial Fibrillation Classification with Smart Wearables Using Short-Term Heart Rate Variability and Deep Convolutional Neural Networks10.3390/s212172331424-8220https://doaj.org/article/9e1fbb2eb0884ead84f1122170641e292021-10-01T00:00:00Zhttps://www.mdpi.com/1424-8220/21/21/7233https://doaj.org/toc/1424-8220Atrial fibrillation (AF) is a type of cardiac arrhythmia affecting millions of people every year. This disease increases the likelihood of strokes, heart failure, and even death. While dedicated medical-grade electrocardiogram (ECG) devices can enable gold-standard analysis, these devices are expensive and require clinical settings. Recent advances in the capabilities of general-purpose smartphones and wearable technology equipped with photoplethysmography (PPG) sensors increase diagnostic accessibility for most populations. This work aims to develop a single model that can generalize AF classification across the modalities of ECG and PPG with a unified knowledge representation. This is enabled by approximating the transformation of signals obtained from low-cost wearable PPG sensors in terms of Pulse Rate Variability (PRV) to temporal Heart Rate Variability (HRV) features extracted from medical-grade ECG. This paper proposes a one-dimensional deep convolutional neural network that uses HRV-derived features for classifying 30-s heart rhythms as normal sinus rhythm or atrial fibrillation from both ECG and PPG-based sensors. The model is trained with three MIT-BIH ECG databases and is assessed on a dataset of unseen PPG signals acquired from wrist-worn wearable devices through transfer learning. The model achieved the aggregate binary classification performance measures of accuracy: 95.50%, sensitivity: 94.50%, and specificity: 96.00% across a five-fold cross-validation strategy on the ECG datasets. It also achieved 95.10% accuracy, 94.60% sensitivity, 95.20% specificity on an unseen PPG dataset. The results show considerable promise towards seamless adaptation of gold-standard ECG trained models for non-ambulatory AF detection with consumer wearable devices through HRV-based knowledge transfer.Jayroop RameshZahra SolatidehkordiRaafat AburukbaAssim SagahyroonMDPI AGarticlebiomedical informaticscardiovascular diseasedeep learningECGheart rate variabilitymachine learningChemical technologyTP1-1185ENSensors, Vol 21, Iss 7233, p 7233 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	biomedical informatics cardiovascular disease deep learning ECG heart rate variability machine learning Chemical technology TP1-1185
spellingShingle	biomedical informatics cardiovascular disease deep learning ECG heart rate variability machine learning Chemical technology TP1-1185 Jayroop Ramesh Zahra Solatidehkordi Raafat Aburukba Assim Sagahyroon Atrial Fibrillation Classification with Smart Wearables Using Short-Term Heart Rate Variability and Deep Convolutional Neural Networks
description	Atrial fibrillation (AF) is a type of cardiac arrhythmia affecting millions of people every year. This disease increases the likelihood of strokes, heart failure, and even death. While dedicated medical-grade electrocardiogram (ECG) devices can enable gold-standard analysis, these devices are expensive and require clinical settings. Recent advances in the capabilities of general-purpose smartphones and wearable technology equipped with photoplethysmography (PPG) sensors increase diagnostic accessibility for most populations. This work aims to develop a single model that can generalize AF classification across the modalities of ECG and PPG with a unified knowledge representation. This is enabled by approximating the transformation of signals obtained from low-cost wearable PPG sensors in terms of Pulse Rate Variability (PRV) to temporal Heart Rate Variability (HRV) features extracted from medical-grade ECG. This paper proposes a one-dimensional deep convolutional neural network that uses HRV-derived features for classifying 30-s heart rhythms as normal sinus rhythm or atrial fibrillation from both ECG and PPG-based sensors. The model is trained with three MIT-BIH ECG databases and is assessed on a dataset of unseen PPG signals acquired from wrist-worn wearable devices through transfer learning. The model achieved the aggregate binary classification performance measures of accuracy: 95.50%, sensitivity: 94.50%, and specificity: 96.00% across a five-fold cross-validation strategy on the ECG datasets. It also achieved 95.10% accuracy, 94.60% sensitivity, 95.20% specificity on an unseen PPG dataset. The results show considerable promise towards seamless adaptation of gold-standard ECG trained models for non-ambulatory AF detection with consumer wearable devices through HRV-based knowledge transfer.
format	article
author	Jayroop Ramesh Zahra Solatidehkordi Raafat Aburukba Assim Sagahyroon
author_facet	Jayroop Ramesh Zahra Solatidehkordi Raafat Aburukba Assim Sagahyroon
author_sort	Jayroop Ramesh
title	Atrial Fibrillation Classification with Smart Wearables Using Short-Term Heart Rate Variability and Deep Convolutional Neural Networks
title_short	Atrial Fibrillation Classification with Smart Wearables Using Short-Term Heart Rate Variability and Deep Convolutional Neural Networks
title_full	Atrial Fibrillation Classification with Smart Wearables Using Short-Term Heart Rate Variability and Deep Convolutional Neural Networks
title_fullStr	Atrial Fibrillation Classification with Smart Wearables Using Short-Term Heart Rate Variability and Deep Convolutional Neural Networks
title_full_unstemmed	Atrial Fibrillation Classification with Smart Wearables Using Short-Term Heart Rate Variability and Deep Convolutional Neural Networks
title_sort	atrial fibrillation classification with smart wearables using short-term heart rate variability and deep convolutional neural networks
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/9e1fbb2eb0884ead84f1122170641e29
work_keys_str_mv	AT jayroopramesh atrialfibrillationclassificationwithsmartwearablesusingshorttermheartratevariabilityanddeepconvolutionalneuralnetworks AT zahrasolatidehkordi atrialfibrillationclassificationwithsmartwearablesusingshorttermheartratevariabilityanddeepconvolutionalneuralnetworks AT raafataburukba atrialfibrillationclassificationwithsmartwearablesusingshorttermheartratevariabilityanddeepconvolutionalneuralnetworks AT assimsagahyroon atrialfibrillationclassificationwithsmartwearablesusingshorttermheartratevariabilityanddeepconvolutionalneuralnetworks
_version_	1718431600708943872

Atrial Fibrillation Classification with Smart Wearables Using Short-Term Heart Rate Variability and Deep Convolutional Neural Networks

Ejemplares similares