A Deep Learning Approach for Real-Time Detection of Atrial Fibrillation

Rasmus Sten Andersen, Abdolrahman Peimankar, Sadasivan Puthusserypady*

*Corresponding author for this work

Research output: Contribution to journalJournal articleResearchpeer-review

Abstract

Goal: To develop a robust and real-time approach for automatic detection of Atrial Fibrillation (AF) in long-term electrocardiogram (ECG) recordings using deep learning (DL). Method: An end-to-end model combining the Convolutional- and Recurrent-Neural Networks (CNN and RNN) was proposed to extract high level features from segments of RR intervals (RRIs) in order to classify them as AF or normal sinus rhythm (NSR). Results: The model was trained and validated on three different databases including a total of 89 subjects. It achieved a sensitivity and specificity of 98.98% and 96.95% respectively, validated through a 5-fold cross-validation. Additionally, the proposed model was found to be computationally efficient and it was capable of analyzing 24 hours of ECG recordings in less than one second. The proposed algorithm was also tested on the unseen datasets to examine its robustness in detecting AF for new recordings which resulted in 98.96% and 86.04% for specificity and sensitivity, respectively. Conclusion: Compared to the state-of-the-art models evaluated on standard benchmark ECG datasets, the proposed model produced better performance in detecting AF. Additionally, since the model learns features directly from the data, it avoids the need for clever/cumbersome feature engineering.

Original languageEnglish
JournalExpert Systems with Applications
Volume115
Pages (from-to)465-473
Number of pages9
ISSN0957-4174
DOIs
Publication statusPublished - 2019

Keywords

  • Electrocardiogram (ECG)
  • Atrial Fibrillation
  • Deep Learning
  • Convolutional Neural Networks (CNNs)
  • Recurrent Neural Networks (RNNs)
  • Long Short-Term Memory (LSTM)

Cite this

@article{8eb505ddad9846e9b0ddfe377860ceae,
title = "A Deep Learning Approach for Real-Time Detection of Atrial Fibrillation",
abstract = "Goal: To develop a robust and real-time approach for automatic detection of Atrial Fibrillation (AF) in long-term electrocardiogram (ECG) recordings using deep learning (DL). Method: An end-to-end model combining the Convolutional- and Recurrent-Neural Networks (CNN and RNN) was proposed to extract high level features from segments of RR intervals (RRIs) in order to classify them as AF or normal sinus rhythm (NSR). Results: The model was trained and validated on three different databases including a total of 89 subjects. It achieved a sensitivity and specificity of 98.98{\%} and 96.95{\%} respectively, validated through a 5-fold cross-validation. Additionally, the proposed model was found to be computationally efficient and it was capable of analyzing 24 hours of ECG recordings in less than one second. The proposed algorithm was also tested on the unseen datasets to examine its robustness in detecting AF for new recordings which resulted in 98.96{\%} and 86.04{\%} for specificity and sensitivity, respectively. Conclusion: Compared to the state-of-the-art models evaluated on standard benchmark ECG datasets, the proposed model produced better performance in detecting AF. Additionally, since the model learns features directly from the data, it avoids the need for clever/cumbersome feature engineering.",
keywords = "Electrocardiogram (ECG), Atrial Fibrillation, Deep Learning, Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), Long Short-Term Memory (LSTM)",
author = "Andersen, {Rasmus Sten} and Abdolrahman Peimankar and Sadasivan Puthusserypady",
year = "2019",
doi = "10.1016/j.eswa.2018.08.011",
language = "English",
volume = "115",
pages = "465--473",
journal = "Expert Systems with Applications",
issn = "0957-4174",
publisher = "Pergamon Press",

}

A Deep Learning Approach for Real-Time Detection of Atrial Fibrillation. / Andersen, Rasmus Sten; Peimankar, Abdolrahman; Puthusserypady, Sadasivan.

In: Expert Systems with Applications, Vol. 115, 2019, p. 465-473.

Research output: Contribution to journalJournal articleResearchpeer-review

TY - JOUR

T1 - A Deep Learning Approach for Real-Time Detection of Atrial Fibrillation

AU - Andersen, Rasmus Sten

AU - Peimankar, Abdolrahman

AU - Puthusserypady, Sadasivan

PY - 2019

Y1 - 2019

N2 - Goal: To develop a robust and real-time approach for automatic detection of Atrial Fibrillation (AF) in long-term electrocardiogram (ECG) recordings using deep learning (DL). Method: An end-to-end model combining the Convolutional- and Recurrent-Neural Networks (CNN and RNN) was proposed to extract high level features from segments of RR intervals (RRIs) in order to classify them as AF or normal sinus rhythm (NSR). Results: The model was trained and validated on three different databases including a total of 89 subjects. It achieved a sensitivity and specificity of 98.98% and 96.95% respectively, validated through a 5-fold cross-validation. Additionally, the proposed model was found to be computationally efficient and it was capable of analyzing 24 hours of ECG recordings in less than one second. The proposed algorithm was also tested on the unseen datasets to examine its robustness in detecting AF for new recordings which resulted in 98.96% and 86.04% for specificity and sensitivity, respectively. Conclusion: Compared to the state-of-the-art models evaluated on standard benchmark ECG datasets, the proposed model produced better performance in detecting AF. Additionally, since the model learns features directly from the data, it avoids the need for clever/cumbersome feature engineering.

AB - Goal: To develop a robust and real-time approach for automatic detection of Atrial Fibrillation (AF) in long-term electrocardiogram (ECG) recordings using deep learning (DL). Method: An end-to-end model combining the Convolutional- and Recurrent-Neural Networks (CNN and RNN) was proposed to extract high level features from segments of RR intervals (RRIs) in order to classify them as AF or normal sinus rhythm (NSR). Results: The model was trained and validated on three different databases including a total of 89 subjects. It achieved a sensitivity and specificity of 98.98% and 96.95% respectively, validated through a 5-fold cross-validation. Additionally, the proposed model was found to be computationally efficient and it was capable of analyzing 24 hours of ECG recordings in less than one second. The proposed algorithm was also tested on the unseen datasets to examine its robustness in detecting AF for new recordings which resulted in 98.96% and 86.04% for specificity and sensitivity, respectively. Conclusion: Compared to the state-of-the-art models evaluated on standard benchmark ECG datasets, the proposed model produced better performance in detecting AF. Additionally, since the model learns features directly from the data, it avoids the need for clever/cumbersome feature engineering.

KW - Electrocardiogram (ECG)

KW - Atrial Fibrillation

KW - Deep Learning

KW - Convolutional Neural Networks (CNNs)

KW - Recurrent Neural Networks (RNNs)

KW - Long Short-Term Memory (LSTM)

U2 - 10.1016/j.eswa.2018.08.011

DO - 10.1016/j.eswa.2018.08.011

M3 - Journal article

VL - 115

SP - 465

EP - 473

JO - Expert Systems with Applications

JF - Expert Systems with Applications

SN - 0957-4174

ER -