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

Acharya, Rajendra U and Fujita, Hamido and Raghavendra, U and Tan, Jen Hong and Muhammad, Adam and Arkadiusz, Gertych and Yaki, Hagiwara (2017) Automated identification of shockable and non-shockable life-threatening ventricular arrhythmias using convolutional neuralnetwork. Future Generation Computer Systems.

[img] PDF
3474.pdf - Published Version
Restricted to Registered users only

Download (2MB) | Request a copy

Abstract

Ventricular tachycardia (VT) and ventricular fibrillation (VFib) are the life-threatening shockable arrhythmias which require immediate attention. Cardiopulmonary resuscitation (CPR) and defibrillation arehighly recommended means of immediate treatment of these shockable arrhythmias and to resume spontaneouscirculation. 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 beprovided 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. Ourproposed 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-basedsupport is performed. Our tool can also be seamlessly integrated with an ECG acquisition systems in theintensive care units (ICUs).

Item Type: Article
Uncontrolled Keywords: Automated external defibrillator (AED)ECG signals Non-shockableShockableVentricular arrhythmias
Subjects: Engineering > MIT Manipal > Instrumentation and Control
Depositing User: MIT Library
Date Deposited: 24 Nov 2017 06:07
Last Modified: 24 Nov 2017 06:07
URI: http://eprints.manipal.edu/id/eprint/150059

Actions (login required)

View Item View Item