FoundationalECGNet: A Lightweight Foundational Model for ECG-based Multitask Cardiac Analysis

2025-09-10

AI Summary

Robust and scalable ECG analysis methods are urgently needed for cardiovascular disease diagnosis, yet existing models suffer from sensitivity to noise, class imbalance, and dataset heterogeneity. To address these challenges, we propose a lightweight multi-task foundation model that uniquely integrates two-stage Morlet/Daubechies wavelet denoising, Convolutional Block Attention Module (CBAM), Graph Attention Network (GAT), and time-series Transformer to jointly capture spatiotemporal dependencies in ECG signals. The model supports both binary classification (normal vs. abnormal) and fine-grained five-class diagnosis—including arrhythmia, conduction disorders, and hypertrophy—while delivering interpretable risk assessments. Evaluated on a multicenter dataset, it achieves 99.0% F1-score for normal/abnormal classification and exceeds 98.9% F1 for three critical disease classes—outperforming state-of-the-art methods. The framework demonstrates superior accuracy, strong generalization across heterogeneous clinical sites, and clinically meaningful interpretability.

Technology Category

• Machine Learning: Multi-class/Multi-label Learning & Extreme Classification
• Computer Vision: Multi-modal Vision
• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning

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
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods

Abstract

Cardiovascular diseases (CVDs) remain a leading cause of mortality worldwide, underscoring the importance of accurate and scalable diagnostic systems. Electrocardiogram (ECG) analysis is central to detecting cardiac abnormalities, yet challenges such as noise, class imbalance, and dataset heterogeneity limit current methods. To address these issues, we propose FoundationalECGNet, a foundational framework for automated ECG classification. The model integrates a dual-stage denoising by Morlet and Daubechies wavelets transformation, Convolutional Block Attention Module (CBAM), Graph Attention Networks (GAT), and Time Series Transformers (TST) to jointly capture spatial and temporal dependencies in multi-channel ECG signals. FoundationalECGNet first distinguishes between Normal and Abnormal ECG signals, and then classifies the Abnormal signals into one of five cardiac conditions: Arrhythmias, Conduction Disorders, Myocardial Infarction, QT Abnormalities, or Hypertrophy. Across multiple datasets, the model achieves a 99% F1-score for Normal vs. Abnormal classification and shows state-of-the-art performance in multi-class disease detection, including a 99% F1-score for Conduction Disorders and Hypertrophy, as well as a 98.9% F1-score for Arrhythmias. Additionally, the model provides risk level estimations to facilitate clinical decision-making. In conclusion, FoundationalECGNet represents a scalable, interpretable, and generalizable solution for automated ECG analysis, with the potential to improve diagnostic precision and patient outcomes in healthcare settings. We'll share the code after acceptance.

Problem

• Developing accurate ECG classification system for cardiac abnormalities detection
• Addressing challenges like noise imbalance and dataset heterogeneity in ECG analysis
• Creating scalable foundational model for multitask cardiac diagnosis using ECG signals

Innovation

• Dual-stage wavelet denoising for signal preprocessing
• CBAM and GAT integration for spatial-temporal analysis
• Multi-task classification with risk level estimation