Arrhythmia Classification Using Graph Neural Networks Based on Correlation Matrix

TL;DR

This paper proposes a graph neural network approach for arrhythmia classification using correlation matrices of ECG features, demonstrating promising precision and recall rates over 50%.

Contribution

It introduces a novel application of graph neural networks with correlation matrices for ECG-based arrhythmia classification.

Findings

Precision and recall for all arrhythmia classes exceeded 50%.

The proposed method outperforms some existing approaches.

Graph neural networks effectively model ECG feature correlations.

Abstract

With the advancements in graph neural network, there has been increasing interest in applying this network to ECG signal analysis. In this study, we generated an adjacency matrix using correlation matrix of extracted features and applied a graph neural network to classify arrhythmias. The proposed model was compared with existing approaches from the literature. The results demonstrated that precision and recall for all arrhythmia classes exceeded 50%, suggesting that this method can be considered an approach for arrhythmia classification.