EB-GAME: A Game-Changer in ECG Heartbeat Anomaly Detection

TL;DR

EB-GAME is a novel unsupervised deep learning model that effectively detects ECG heartbeat anomalies using GAN-based anomaly detection, addressing data imbalance issues with high accuracy on the MIT-BIH dataset.

Contribution

Introduces EB-GAME, a GAN-based unsupervised model inspired by vision transformers and masked auto-encoders for ECG anomaly detection with state-of-the-art results.

Findings

Achieved state-of-the-art performance on MIT-BIH dataset.

Effective in detecting anomalies with limited abnormal data.

Addresses data imbalance in ECG anomaly detection.

Abstract

Cardiologists use electrocardiograms (ECG) for the detection of arrhythmias. However, continuous monitoring of ECG signals to detect cardiac abnormal-ities requires significant time and human resources. As a result, several deep learning studies have been conducted in advance for the automatic detection of arrhythmia. These models show relatively high performance in supervised learning, but are not applicable in cases with few training examples. This is because abnormal ECG data is scarce compared to normal data in most real-world clinical settings. Therefore, in this study, GAN-based anomaly detec-tion, i.e., unsupervised learning, was employed to address the issue of data imbalance. This paper focuses on detecting abnormal signals in electrocardi-ograms (ECGs) using only labels from normal signals as training data. In-spired by self-supervised vision transformers, which learn by dividing images into patches, and masked auto-encoders, known for their effectiveness in patch reconstruction and solving information redundancy, we introduce the ECG Heartbeat Anomaly Detection model, EB-GAME. EB-GAME was trained and validated on the MIT-BIH Arrhythmia Dataset, where it achieved state-of-the-art performance on this benchmark.