Automatic Premature Ventricular Contractions Detection for Multi-Lead Electrocardiogram Signal

Mohamad Mahmoud Al Rahhal, Naif Al Ajlan, Yakoub Bazi, Haikel Al Hichri, Timon Rabczuk

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

In this paper, we propose an electrocardiogram (ECG) technique for the automatic detection of Premature Ventricular Contractions (PVC) based on multi-lead signals and on a deep learning architecture which is built using Stacked Denoising Autoencoders (SDAEs) networks. The proposed method consists of two main stages; feature learning and classification. In the first stage, we learn a new feature representation from data using SDAEs. Regarding the classification, we add a softmax regression layer on the top of the resulting hidden representation layer yielding a deep neural network (DNN). The proposed method fuses the results of several ECG leads (up to 12) in order to increase the detection accuracy. In the experiments, we use INCART database to test the proposed DNN multi-lead method. The obtained results are 98.6%, 91.4%, and 97.7% respectively for overall accuracy (OA), average sensitivity (Se), and average positive productivity (Pp).

Original languageEnglish
Title of host publication2018 IEEE International Conference on Electro/Information Technology, EIT 2018
PublisherIEEE Computer Society
Pages169-173
Number of pages5
Volume2018-May
ISBN (Electronic)9781538653982
DOIs
Publication statusPublished - 2018 Oct 18
Externally publishedYes
Event2018 IEEE International Conference on Electro/Information Technology, EIT 2018 - Rochester, United States
Duration: 2018 May 32018 May 5

Other

Other2018 IEEE International Conference on Electro/Information Technology, EIT 2018
CountryUnited States
CityRochester
Period18/5/318/5/5

Fingerprint

Electrocardiography
Lead
Electric fuses
Productivity
Experiments
Deep neural networks
Deep learning

ASJC Scopus subject areas

  • Computer Science Applications
  • Information Systems
  • Control and Systems Engineering
  • Electrical and Electronic Engineering

Cite this

Rahhal, M. M. A., Ajlan, N. A., Bazi, Y., Hichri, H. A., & Rabczuk, T. (2018). Automatic Premature Ventricular Contractions Detection for Multi-Lead Electrocardiogram Signal. In 2018 IEEE International Conference on Electro/Information Technology, EIT 2018 (Vol. 2018-May, pp. 169-173). [8500197] IEEE Computer Society. https://doi.org/10.1109/EIT.2018.8500197

Automatic Premature Ventricular Contractions Detection for Multi-Lead Electrocardiogram Signal. / Rahhal, Mohamad Mahmoud Al; Ajlan, Naif Al; Bazi, Yakoub; Hichri, Haikel Al; Rabczuk, Timon.

2018 IEEE International Conference on Electro/Information Technology, EIT 2018. Vol. 2018-May IEEE Computer Society, 2018. p. 169-173 8500197.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Rahhal, MMA, Ajlan, NA, Bazi, Y, Hichri, HA & Rabczuk, T 2018, Automatic Premature Ventricular Contractions Detection for Multi-Lead Electrocardiogram Signal. in 2018 IEEE International Conference on Electro/Information Technology, EIT 2018. vol. 2018-May, 8500197, IEEE Computer Society, pp. 169-173, 2018 IEEE International Conference on Electro/Information Technology, EIT 2018, Rochester, United States, 18/5/3. https://doi.org/10.1109/EIT.2018.8500197
Rahhal MMA, Ajlan NA, Bazi Y, Hichri HA, Rabczuk T. Automatic Premature Ventricular Contractions Detection for Multi-Lead Electrocardiogram Signal. In 2018 IEEE International Conference on Electro/Information Technology, EIT 2018. Vol. 2018-May. IEEE Computer Society. 2018. p. 169-173. 8500197 https://doi.org/10.1109/EIT.2018.8500197
Rahhal, Mohamad Mahmoud Al ; Ajlan, Naif Al ; Bazi, Yakoub ; Hichri, Haikel Al ; Rabczuk, Timon. / Automatic Premature Ventricular Contractions Detection for Multi-Lead Electrocardiogram Signal. 2018 IEEE International Conference on Electro/Information Technology, EIT 2018. Vol. 2018-May IEEE Computer Society, 2018. pp. 169-173
@inproceedings{433c85b4679a4452b522a182001995e4,
title = "Automatic Premature Ventricular Contractions Detection for Multi-Lead Electrocardiogram Signal",
abstract = "In this paper, we propose an electrocardiogram (ECG) technique for the automatic detection of Premature Ventricular Contractions (PVC) based on multi-lead signals and on a deep learning architecture which is built using Stacked Denoising Autoencoders (SDAEs) networks. The proposed method consists of two main stages; feature learning and classification. In the first stage, we learn a new feature representation from data using SDAEs. Regarding the classification, we add a softmax regression layer on the top of the resulting hidden representation layer yielding a deep neural network (DNN). The proposed method fuses the results of several ECG leads (up to 12) in order to increase the detection accuracy. In the experiments, we use INCART database to test the proposed DNN multi-lead method. The obtained results are 98.6{\%}, 91.4{\%}, and 97.7{\%} respectively for overall accuracy (OA), average sensitivity (Se), and average positive productivity (Pp).",
author = "Rahhal, {Mohamad Mahmoud Al} and Ajlan, {Naif Al} and Yakoub Bazi and Hichri, {Haikel Al} and Timon Rabczuk",
year = "2018",
month = "10",
day = "18",
doi = "10.1109/EIT.2018.8500197",
language = "English",
volume = "2018-May",
pages = "169--173",
booktitle = "2018 IEEE International Conference on Electro/Information Technology, EIT 2018",
publisher = "IEEE Computer Society",

}

TY - GEN

T1 - Automatic Premature Ventricular Contractions Detection for Multi-Lead Electrocardiogram Signal

AU - Rahhal, Mohamad Mahmoud Al

AU - Ajlan, Naif Al

AU - Bazi, Yakoub

AU - Hichri, Haikel Al

AU - Rabczuk, Timon

PY - 2018/10/18

Y1 - 2018/10/18

N2 - In this paper, we propose an electrocardiogram (ECG) technique for the automatic detection of Premature Ventricular Contractions (PVC) based on multi-lead signals and on a deep learning architecture which is built using Stacked Denoising Autoencoders (SDAEs) networks. The proposed method consists of two main stages; feature learning and classification. In the first stage, we learn a new feature representation from data using SDAEs. Regarding the classification, we add a softmax regression layer on the top of the resulting hidden representation layer yielding a deep neural network (DNN). The proposed method fuses the results of several ECG leads (up to 12) in order to increase the detection accuracy. In the experiments, we use INCART database to test the proposed DNN multi-lead method. The obtained results are 98.6%, 91.4%, and 97.7% respectively for overall accuracy (OA), average sensitivity (Se), and average positive productivity (Pp).

AB - In this paper, we propose an electrocardiogram (ECG) technique for the automatic detection of Premature Ventricular Contractions (PVC) based on multi-lead signals and on a deep learning architecture which is built using Stacked Denoising Autoencoders (SDAEs) networks. The proposed method consists of two main stages; feature learning and classification. In the first stage, we learn a new feature representation from data using SDAEs. Regarding the classification, we add a softmax regression layer on the top of the resulting hidden representation layer yielding a deep neural network (DNN). The proposed method fuses the results of several ECG leads (up to 12) in order to increase the detection accuracy. In the experiments, we use INCART database to test the proposed DNN multi-lead method. The obtained results are 98.6%, 91.4%, and 97.7% respectively for overall accuracy (OA), average sensitivity (Se), and average positive productivity (Pp).

UR - http://www.scopus.com/inward/record.url?scp=85057131453&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85057131453&partnerID=8YFLogxK

U2 - 10.1109/EIT.2018.8500197

DO - 10.1109/EIT.2018.8500197

M3 - Conference contribution

VL - 2018-May

SP - 169

EP - 173

BT - 2018 IEEE International Conference on Electro/Information Technology, EIT 2018

PB - IEEE Computer Society

ER -