Versatile and Risk-Sensitive Cardiac Diagnosis via Graph-Based ECG Signal Representation

2025-11-11

AI Summary

Existing ECG analysis methods face two key challenges: limited generalizability across signals with heterogeneous lead counts, sampling rates, and durations; and poor detection of rare risk patterns due to severe class imbalance. To address these, we propose VARS—a novel framework that (1) unifies multi-source ECG signals into structured graphs, enabling cross-configuration adaptive representation learning; (2) integrates denoising autoencoding with contrastive learning to preserve temporal fidelity while enhancing discriminability of pathological features; and (3) incorporates an interpretable graph attention mechanism for precise abnormal waveform localization and clinical attribution. Evaluated on three heterogeneous, multicenter ECG datasets, VARS achieves substantial improvements in risk signal detection—averaging an 8.2% absolute gain in F1-score—and enables end-to-end visualizable anomaly localization. The framework demonstrates strong generalizability across diverse acquisition protocols and provides clinically meaningful interpretability.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Computer Vision: Multi-modal Vision
• Reasoning under Uncertainty: Graphical Models

Application Category

• Graph Algorithms and Modeling for the Web: Algorithms and analysis for heterogeneous, signed, attributed, multi-relational, temporal, higher-order, and annotated Web-related graphs
• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics

Abstract

Despite the rapid advancements of electrocardiogram (ECG) signal diagnosis and analysis methods through deep learning, two major hurdles still limit their clinical adoption: the lack of versatility in processing ECG signals with diverse configurations, and the inadequate detection of risk signals due to sample imbalances. Addressing these challenges, we introduce VersAtile and Risk-Sensitive cardiac diagnosis (VARS), an innovative approach that employs a graph-based representation to uniformly model heterogeneous ECG signals. VARS stands out by transforming ECG signals into versatile graph structures that capture critical diagnostic features, irrespective of signal diversity in the lead count, sampling frequency, and duration. This graph-centric formulation also enhances diagnostic sensitivity, enabling precise localization and identification of abnormal ECG patterns that often elude standard analysis methods. To facilitate representation transformation, our approach integrates denoising reconstruction with contrastive learning to preserve raw ECG information while highlighting pathognomonic patterns. We rigorously evaluate the efficacy of VARS on three distinct ECG datasets, encompassing a range of structural variations. The results demonstrate that VARS not only consistently surpasses existing state-of-the-art models across all these datasets but also exhibits substantial improvement in identifying risk signals. Additionally, VARS offers interpretability by pinpointing the exact waveforms that lead to specific model outputs, thereby assisting clinicians in making informed decisions. These findings suggest that our VARS will likely emerge as an invaluable tool for comprehensive cardiac health assessment.

Problem

• Lack of versatility in processing diverse ECG signal configurations
• Inadequate detection of risk signals due to sample imbalances
• Difficulty in localizing abnormal ECG patterns with standard methods

Innovation

• Graph-based representation models heterogeneous ECG signals
• Denoising reconstruction with contrastive learning preserves raw information
• Transforms ECG signals into versatile graph structures capturing diagnostic features