Domain Knowledge Based Temporal-Spatial Graph Convolution Network for ECG Recognition

2026-07-01

AI Summary

This study addresses the limited interpretability and poor performance on rare classes in end-to-end deep learning for electrocardiogram (ECG) classification by proposing a spatiotemporal dual-stream directed graph convolutional network that integrates medical prior knowledge. The method uniquely embeds clinically significant ECG fiducial points—P, R, Q, S, and T—into a graph structure, explicitly modeling both the spatial relationships among these landmarks within a single cardiac cycle and their temporal dependencies across multiple cycles. Evaluated on the nine-class task of the First China ECG Intelligence Challenge, the model achieves an overall average F1 score of 88.1% and a rare-class average F1 of 76.3%, significantly outperforming current state-of-the-art approaches while offering enhanced interpretability alongside high accuracy.

Abstract

In light of strides in Arti cial Intelligence (AI) and its wide spread application, challenges persist in the interpretability of AI models, particularly within specialized domains like healthcare, such as electro cardiograph (ECG) recognition. Rather than relying solely on end-to-end convolutional neural networks, this paper introduces a novel approach using a domain knowledge-based graph convolution network for ECG recognition. Key landmarks points of PRQST, vital to ECG interpreta tion, are incorporated as domain knowledge. The double-stream directed graph is employed to model both intra and inter ECG cycles. Speci cally, spatial directed graphs capture the positional relationships among key points, while temporal directed graphs delineate temporal dependencies between adjacent cycles in extended ECG sequences. Experimental re sults on the First Chinese ECG Intelligent Competition dataset, which speci cally classify ECG into nine categories, prove the e cacy of the proposed model. The overall average F1 score is 88.1%, the average F1 score of rare categories is 76.3%, both outperform the state-of-the-art models. The introduction of domain knowledge did enhance the detec tion performance, especially for rare categories.

Problem

• ECG recognition
• interpretability
• domain knowledge
• rare categories
• AI in healthcare

Innovation

• domain knowledge
• temporal-spatial graph convolution
• ECG recognition
• directed graph
• PRQST landmarks