Published on Fri Apr 10 2020

Fully Automatic Electrocardiogram Classification System based on Generative Adversarial Network with Auxiliary Classifier

Zhanhong Zhou, Xiaolong Zhai, Chung Tin

The ACE-GAN (Generative Adversarial Network with Auxiliary Classifier for Electrocardiogram) based automatic system can be a promising and reliable tool for high throughput clinical screening practice. The system showed superior overall classification performance for both supraventricular ectopic beats (SVEB or S beats) and Veb beats.

0
0
0
Abstract

A generative adversarial network (GAN) based fully automatic electrocardiogram (ECG) arrhythmia classification system with high performance is presented in this paper. The generator (G) in our GAN is designed to generate various coupling matrix inputs conditioned on different arrhythmia classes for data augmentation. Our designed discriminator (D) is trained on both real and generated ECG coupling matrix inputs, and is extracted as an arrhythmia classifier upon completion of training for our GAN. After fine-tuning the D by including patient-specific normal beats estimated using an unsupervised algorithm, and generated abnormal beats by G that are usually rare to obtain, our fully automatic system showed superior overall classification performance for both supraventricular ectopic beats (SVEB or S beats) and ventricular ectopic beats (VEB or V beats) on the MIT-BIH arrhythmia database. It surpassed several state-of-art automatic classifiers and can perform on similar levels as some expert-assisted methods. In particular, the F1 score of SVEB has been improved by up to 13% over the top-performing automatic systems. Moreover, high sensitivity for both SVEB (87%) and VEB (93%) detection has been achieved, which is of great value for practical diagnosis. We, therefore, suggest our ACE-GAN (Generative Adversarial Network with Auxiliary Classifier for Electrocardiogram) based automatic system can be a promising and reliable tool for high throughput clinical screening practice, without any need of manual intervene or expert assisted labeling.

Mon May 13 2019
Machine Learning
Adversarial Examples for Electrocardiograms
In recent years, the electrocardiogram (ECG) has seen a large diffusion in both medical and commercial applications, fueled by the rise of single-lead versions. Single-lead ECG can be embedded in medical devices and wearable products such as the injectable Medtronic Linq monitor.
0
0
0
Wed Jun 02 2021
Machine Learning
Synthesis of standard 12-lead electrocardiograms using two dimensional generative adversarial network
0
0
0
Sat Jun 09 2018
Machine Learning
Method to Annotate Arrhythmias by Deep Network
This study targets to automatically annotate on arrhythmia by deep network. The investigated types include sinus rhythm, asystole (Asys), supraventricular tachycardia (Tachy) and ventricular flutter or fibrillation.
0
0
0
Thu Apr 15 2021
Machine Learning
Estimation of atrial fibrillation from lead-I ECGs: Comparison with cardiologists and machine learning model (CurAlive), a clinical validation study
0
0
0
Tue Jan 19 2021
Machine Learning
Electrocardiogram Classification and Visual Diagnosis of Atrial Fibrillation with DenseECG
Atrial Fibrillation (AF) is a common cardiac arrhythmia affecting a large number of people around the world. A non-invasive, automatic, and effective detection method is needed to help early detection so that medical intervention can be implemented in time to prevent its progression.
0
0
0
Tue Oct 20 2020
Machine Learning
Interpretable Deep Learning for Automatic Diagnosis of 12-lead Electrocardiogram
Deep learning methods have demonstrated promising results in predictive healthcare tasks. Electrocardiogram (ECG) is a widely used reliable, non-invasive approach for cardiovascular disease diagnosis. The proposed model achieved an average area under the receiver operating characteristic curve (AUC) of 0.970.
0
0
0