KGD-GNN: A Knowledge-Guided Graph Neural Network for Myocardial Infarction Localization via 12-lead ECG

Abstract

Myocardial infarction (MI) is one of the most dangerous cardiovascular diseases, typically diagnosed using electrocardiogram (ECG). While many deep learning methods exist for MI detection, they often overlook the correlations and medical knowledge between leads of ECG, resulting in limited interpretability. To address the challenges, we propose a knowledge-guided multi branch dense graph neural network (KGD-GNN) for MI localization. The proposed method incorporates clinical diagnostic knowledge to represent ECG as a graph, capturing inter-lead relationships. A multi-branch graph convolutional module is then used to extract disease-specific features through dense graph convolution. Evaluations on the public PTB-XL dataset demonstrate the superior performance of KGD-GNN across multiple metrics.