An Ensemble of Deep Recurrent Neural Networks for P-wave Detection in Electrocardiogram

Abdolrahman Peimankar; Sadasivan Puthusserypady

doi:10.1109/ICASSP.2019.8682307

An Ensemble of Deep Recurrent Neural Networks for P-wave Detection in Electrocardiogram

Abdolrahman Peimankar
, Sadasivan Puthusserypady

Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

522 Downloads (Orbit)

Abstract

Detection of P-waves in electrocardiogram (ECG) signals is of great importance to cardiologists in order to help them diagnosing arrhythmias such as atrial fibrillation. This paper proposes an end-to-end deep learning approach for detection of P-waves in ECG signals. Four different deep Recurrent Neural Networks (RNNs), namely, the Long-Short Term Memory (LSTM) are used in an ensemble framework. Each of these networks are trained to extract the useful features from raw ECG signals and determine the absence/presence of P-waves. Outputs of these classifiers are then combined for final detection of the P-waves. The proposed algorithm was trained and validated on a database which consists of more than 111000 annotated heart beats and the results show consistently high classification accuracy and sensitivity of around 98.48% and 97.22%, respectively.

Original language	English
Title of host publication	2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Publisher	IEEE
Publication date	2019
Pages	1284-1288
ISBN (Electronic)	978-1-4799-8131-1
DOIs	https://doi.org/10.1109/ICASSP.2019.8682307
Publication status	Published - 2019
Event	2019 IEEE International Conference on Acoustics, Speech, and Signal Processing - Brighton Conference Centre, Brighton, United Kingdom Duration: 12 May 2019 → 17 May 2019 Conference number: 44 https://2019.ieeeicassp.org/ https://www.2019.ieeeicassp.org/2019.ieeeicassp.org/index.html

Conference

Conference	2019 IEEE International Conference on Acoustics, Speech, and Signal Processing
Number	44
Location	Brighton Conference Centre
Country/Territory	United Kingdom
City	Brighton
Period	12/05/2019 → 17/05/2019
Sponsor	IEEE
Internet address	https://2019.ieeeicassp.org/ https://www.2019.ieeeicassp.org/2019.ieeeicassp.org/index.html

Series	I E E E International Conference on Acoustics, Speech and Signal Processing. Proceedings
ISSN	1520-6149

Access to Document

10.1109/ICASSP.2019.8682307

fulltextAccepted author manuscript, 1.29 MB

OpenUrl availability

Full text

Cite this

@inproceedings{d1c135ab2ec348439bcd53b02789010d,

title = "An Ensemble of Deep Recurrent Neural Networks for P-wave Detection in Electrocardiogram",

abstract = "Detection of P-waves in electrocardiogram (ECG) signals is of great importance to cardiologists in order to help them diagnosing arrhythmias such as atrial fibrillation. This paper proposes an end-to-end deep learning approach for detection of P-waves in ECG signals. Four different deep Recurrent Neural Networks (RNNs), namely, the Long-Short Term Memory (LSTM) are used in an ensemble framework. Each of these networks are trained to extract the useful features from raw ECG signals and determine the absence/presence of P-waves. Outputs of these classifiers are then combined for final detection of the P-waves. The proposed algorithm was trained and validated on a database which consists of more than 111000 annotated heart beats and the results show consistently high classification accuracy and sensitivity of around 98.48\% and 97.22\%, respectively.",

author = "Abdolrahman Peimankar and Sadasivan Puthusserypady",

year = "2019",

doi = "10.1109/ICASSP.2019.8682307",

language = "English",

series = "I E E E International Conference on Acoustics, Speech and Signal Processing. Proceedings",

publisher = "IEEE",

pages = "1284--1288",

booktitle = "2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)",

address = "United States",

note = "2019 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 ; Conference date: 12-05-2019 Through 17-05-2019",

url = "https://2019.ieeeicassp.org/, https://www.2019.ieeeicassp.org/2019.ieeeicassp.org/index.html",

}

Peimankar, A & Puthusserypady, S 2019, An Ensemble of Deep Recurrent Neural Networks for P-wave Detection in Electrocardiogram. in 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, I E E E International Conference on Acoustics, Speech and Signal Processing. Proceedings, pp. 1284-1288, 2019 IEEE International Conference on Acoustics, Speech, and Signal Processing, Brighton, United Kingdom, 12/05/2019. https://doi.org/10.1109/ICASSP.2019.8682307

An Ensemble of Deep Recurrent Neural Networks for P-wave Detection in Electrocardiogram. / Peimankar, Abdolrahman; Puthusserypady, Sadasivan.
2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 2019. p. 1284-1288 (I E E E International Conference on Acoustics, Speech and Signal Processing. Proceedings).

Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

TY - GEN

T1 - An Ensemble of Deep Recurrent Neural Networks for P-wave Detection in Electrocardiogram

AU - Peimankar, Abdolrahman

AU - Puthusserypady, Sadasivan

N1 - Conference code: 44

PY - 2019

Y1 - 2019

N2 - Detection of P-waves in electrocardiogram (ECG) signals is of great importance to cardiologists in order to help them diagnosing arrhythmias such as atrial fibrillation. This paper proposes an end-to-end deep learning approach for detection of P-waves in ECG signals. Four different deep Recurrent Neural Networks (RNNs), namely, the Long-Short Term Memory (LSTM) are used in an ensemble framework. Each of these networks are trained to extract the useful features from raw ECG signals and determine the absence/presence of P-waves. Outputs of these classifiers are then combined for final detection of the P-waves. The proposed algorithm was trained and validated on a database which consists of more than 111000 annotated heart beats and the results show consistently high classification accuracy and sensitivity of around 98.48% and 97.22%, respectively.

AB - Detection of P-waves in electrocardiogram (ECG) signals is of great importance to cardiologists in order to help them diagnosing arrhythmias such as atrial fibrillation. This paper proposes an end-to-end deep learning approach for detection of P-waves in ECG signals. Four different deep Recurrent Neural Networks (RNNs), namely, the Long-Short Term Memory (LSTM) are used in an ensemble framework. Each of these networks are trained to extract the useful features from raw ECG signals and determine the absence/presence of P-waves. Outputs of these classifiers are then combined for final detection of the P-waves. The proposed algorithm was trained and validated on a database which consists of more than 111000 annotated heart beats and the results show consistently high classification accuracy and sensitivity of around 98.48% and 97.22%, respectively.

U2 - 10.1109/ICASSP.2019.8682307

DO - 10.1109/ICASSP.2019.8682307

M3 - Article in proceedings

T3 - I E E E International Conference on Acoustics, Speech and Signal Processing. Proceedings

SP - 1284

EP - 1288

BT - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

PB - IEEE

T2 - 2019 IEEE International Conference on Acoustics, Speech, and Signal Processing

Y2 - 12 May 2019 through 17 May 2019

ER -

An Ensemble of Deep Recurrent Neural Networks for P-wave Detection in Electrocardiogram

Abstract

Conference

Access to Document

OpenUrl availability

Fingerprint

Cite this