ECG Arrhythmia Detection Using Disease-specific Attention-based Deep Learning Model

TL;DR

This paper introduces a disease-specific attention-based deep learning model (DANet) that enhances ECG arrhythmia detection accuracy and interpretability by incorporating waveform guidance, outperforming benchmarks and aiding clinical diagnosis.

Contribution

The study proposes a novel DANet model with waveform-enhanced modules and a combined training framework, improving ECG arrhythmia detection and interpretability over existing methods.

Findings

DANet outperforms benchmark models in atrial premature contraction detection.

The model provides interpretable waveform regions relevant to diagnosis.

Waveform guidance improves classification performance and clinical relevance.

Abstract

The electrocardiogram (ECG) is one of the most commonly-used tools to diagnose cardiovascular disease in clinical practice. Although deep learning models have achieved very impressive success in the field of automatic ECG analysis, they often lack model interpretability that is significantly important in the healthcare applications. To this end, many schemes such as general-purpose attention mechanism, Grad-CAM technique and ECG knowledge graph were proposed to be integrated with deep learning models. However, they either result in decreased classification performance or do not consist with the one in cardiologists' mind when interpreting ECG. In this study, we propose a novel disease-specific attention-based deep learning model (DANet) for arrhythmia detection from short ECG recordings. The novel idea is to introduce a soft-coding or hard-coding waveform enhanced module into existing deep neural networks, which amends original ECG signals with the guidance of the rule for diagnosis of a given disease type before being fed into the classification module. For the soft-coding DANet, we also develop a learning framework combining self-supervised pre-training with two-stage supervised training. To verify the effectiveness of our proposed DANet, we applied it to the problem of atrial premature contraction detection and the experimental results shows that it demonstrates superior performance compared to the benchmark model. Moreover, it also provides the waveform regions that deserve special attention in the model's decision-making process, allowing it to be a medical diagnostic assistant for physicians.