Automated identification of shockable and non-shockable life-threatening ventricular arrhythmias using convolutional neural network

U. Rajendra Acharya, Hamido Fujita, Shu Lih Oh, U. Raghavendra, Jen Hong Tan, Muhammad Adam, Arkadiusz Gertych, Yuki Hagiwara

Research output: Contribution to journalArticle

61 Citations (Scopus)

Abstract

Ventricular tachycardia (VT) and ventricular fibrillation (VFib) are the life-threatening shockable arrhythmias which require immediate attention. Cardiopulmonary resuscitation (CPR) and defibrillation are highly recommended means of immediate treatment of these shockable arrhythmias and to resume spontaneous circulation. However, to increase efficacy of defibrillation by an automated external defibrillator (AED), an accurate distinction of shockable ventricular arrhythmias from non-shockable ones needs to be provided upfront. Therefore, in this work, we have proposed a novel tool for an automated differentiation of shockable and non-shockable ventricular arrhythmias from 2 s electrocardiogram (ECG) segments. Segmented ECGs are processed by an eleven-layer convolutional neural network (CNN) model. Our proposed system was 10-fold cross validated and achieved maximum accuracy, sensitivity and specificity of 93.18%, 95.32% and 91.04% respectively. Its high performance indicates that shockable life-threatening arrhythmia can be immediately detected and thus increase the chance of survival while CPR or AED-based support is performed. Our tool can also be seamlessly integrated with an ECG acquisition systems in the intensive care units (ICUs).

Original languageEnglish
JournalFuture Generation Computer Systems
DOIs
Publication statusPublished - 01-02-2018

Fingerprint

Electrocardiography
Defibrillators
Resuscitation
Neural networks
Intensive care units

All Science Journal Classification (ASJC) codes

  • Software
  • Hardware and Architecture
  • Computer Networks and Communications

Cite this

Acharya, U. Rajendra ; Fujita, Hamido ; Oh, Shu Lih ; Raghavendra, U. ; Tan, Jen Hong ; Adam, Muhammad ; Gertych, Arkadiusz ; Hagiwara, Yuki. / Automated identification of shockable and non-shockable life-threatening ventricular arrhythmias using convolutional neural network. In: Future Generation Computer Systems. 2018.
@article{e566ae6042ef45768c9ed5cf1294367e,
title = "Automated identification of shockable and non-shockable life-threatening ventricular arrhythmias using convolutional neural network",
abstract = "Ventricular tachycardia (VT) and ventricular fibrillation (VFib) are the life-threatening shockable arrhythmias which require immediate attention. Cardiopulmonary resuscitation (CPR) and defibrillation are highly recommended means of immediate treatment of these shockable arrhythmias and to resume spontaneous circulation. However, to increase efficacy of defibrillation by an automated external defibrillator (AED), an accurate distinction of shockable ventricular arrhythmias from non-shockable ones needs to be provided upfront. Therefore, in this work, we have proposed a novel tool for an automated differentiation of shockable and non-shockable ventricular arrhythmias from 2 s electrocardiogram (ECG) segments. Segmented ECGs are processed by an eleven-layer convolutional neural network (CNN) model. Our proposed system was 10-fold cross validated and achieved maximum accuracy, sensitivity and specificity of 93.18{\%}, 95.32{\%} and 91.04{\%} respectively. Its high performance indicates that shockable life-threatening arrhythmia can be immediately detected and thus increase the chance of survival while CPR or AED-based support is performed. Our tool can also be seamlessly integrated with an ECG acquisition systems in the intensive care units (ICUs).",
author = "Acharya, {U. Rajendra} and Hamido Fujita and Oh, {Shu Lih} and U. Raghavendra and Tan, {Jen Hong} and Muhammad Adam and Arkadiusz Gertych and Yuki Hagiwara",
year = "2018",
month = "2",
day = "1",
doi = "10.1016/j.future.2017.08.039",
language = "English",
journal = "Future Generation Computer Systems",
issn = "0167-739X",
publisher = "Elsevier",

}

Automated identification of shockable and non-shockable life-threatening ventricular arrhythmias using convolutional neural network. / Acharya, U. Rajendra; Fujita, Hamido; Oh, Shu Lih; Raghavendra, U.; Tan, Jen Hong; Adam, Muhammad; Gertych, Arkadiusz; Hagiwara, Yuki.

In: Future Generation Computer Systems, 01.02.2018.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Automated identification of shockable and non-shockable life-threatening ventricular arrhythmias using convolutional neural network

AU - Acharya, U. Rajendra

AU - Fujita, Hamido

AU - Oh, Shu Lih

AU - Raghavendra, U.

AU - Tan, Jen Hong

AU - Adam, Muhammad

AU - Gertych, Arkadiusz

AU - Hagiwara, Yuki

PY - 2018/2/1

Y1 - 2018/2/1

N2 - Ventricular tachycardia (VT) and ventricular fibrillation (VFib) are the life-threatening shockable arrhythmias which require immediate attention. Cardiopulmonary resuscitation (CPR) and defibrillation are highly recommended means of immediate treatment of these shockable arrhythmias and to resume spontaneous circulation. However, to increase efficacy of defibrillation by an automated external defibrillator (AED), an accurate distinction of shockable ventricular arrhythmias from non-shockable ones needs to be provided upfront. Therefore, in this work, we have proposed a novel tool for an automated differentiation of shockable and non-shockable ventricular arrhythmias from 2 s electrocardiogram (ECG) segments. Segmented ECGs are processed by an eleven-layer convolutional neural network (CNN) model. Our proposed system was 10-fold cross validated and achieved maximum accuracy, sensitivity and specificity of 93.18%, 95.32% and 91.04% respectively. Its high performance indicates that shockable life-threatening arrhythmia can be immediately detected and thus increase the chance of survival while CPR or AED-based support is performed. Our tool can also be seamlessly integrated with an ECG acquisition systems in the intensive care units (ICUs).

AB - Ventricular tachycardia (VT) and ventricular fibrillation (VFib) are the life-threatening shockable arrhythmias which require immediate attention. Cardiopulmonary resuscitation (CPR) and defibrillation are highly recommended means of immediate treatment of these shockable arrhythmias and to resume spontaneous circulation. However, to increase efficacy of defibrillation by an automated external defibrillator (AED), an accurate distinction of shockable ventricular arrhythmias from non-shockable ones needs to be provided upfront. Therefore, in this work, we have proposed a novel tool for an automated differentiation of shockable and non-shockable ventricular arrhythmias from 2 s electrocardiogram (ECG) segments. Segmented ECGs are processed by an eleven-layer convolutional neural network (CNN) model. Our proposed system was 10-fold cross validated and achieved maximum accuracy, sensitivity and specificity of 93.18%, 95.32% and 91.04% respectively. Its high performance indicates that shockable life-threatening arrhythmia can be immediately detected and thus increase the chance of survival while CPR or AED-based support is performed. Our tool can also be seamlessly integrated with an ECG acquisition systems in the intensive care units (ICUs).

UR - http://www.scopus.com/inward/record.url?scp=85028712399&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85028712399&partnerID=8YFLogxK

U2 - 10.1016/j.future.2017.08.039

DO - 10.1016/j.future.2017.08.039

M3 - Article

AN - SCOPUS:85028712399

JO - Future Generation Computer Systems

JF - Future Generation Computer Systems

SN - 0167-739X

ER -