Efficient Neural Architectures for Real-Time ECG Interpretation on Limited Hardware
2026-05-11 • Machine Learning
Machine Learning
AI summaryⓘ
The authors studied different computer models that read heart signals called ECGs to find a balance between accuracy and speed. They compared existing models and created three new, simpler models that process the heart data in different ways. These models were tested on ECG data from multiple countries and tasks, sometimes using extra information like age and sex to help. The authors also made a score to fairly compare each model's size, speed, memory use, and accuracy. Their work helps make useful and efficient AI tools for heart health diagnosis.
Electrocardiogram (ECG)Convolutional Neural Network (CNN)Deep LearningCardiac AbnormalitiesModel EfficiencyDiagnostic AccuracyMulticlass ClassificationMultilabel ClassificationPhysioNet ChallengeDemographic Metadata
Authors
Ashery Mbilinyi, Callum O'Riley, Julia Handra, Ashley Moller-Hansen, Jason Andrade, Marc Deyell, Cameron Hague, Nathaniel Hawkins, Kendall Ho, Jonathan Leipsic, Roger Tam
Abstract
Electrocardiogram (ECG) interpretation is essential for diagnosing a wide range of cardiac abnormalities. While deep learning has shown strong potential for automating ECG classification, many existing models rely on large, computationally intensive architectures that hinder practical deployment. In this paper, we present an empirical study of convolutional neural network (CNN) architectures, exploring tradeoffs between diagnostic accuracy and computational efficiency. We benchmark two established baselines: AttiaNet, a compact model composed of sequential temporal and spatial blocks, and DeepResidualCNN, the winning architecture of the 2021 PhysioNet/Computing in Cardiology Challenge. Building on these, we propose three lightweight models: (i) ParallelCNN, which employs dual temporal and spatial branches for parallel pattern extraction; (ii) ParallelCNNew, a variant with symmetric weight initialization for balanced feature learning; and (iii) SimpleNet, a streamlined architecture that jointly processes temporal and spatial dimensions. Our experiments span three publicly available 12-lead ECG datasets from Germany, China, and the United States, covering binary, multiclass, and multilabel classification tasks across diverse patient populations. We further evaluate the impact of integrating low-cost demographic metadata (age and sex) to improve performance with minimal overhead. To ensure fair comparison, we introduce a unified Efficiency Score that integrates model size, inference speed, memory usage, and AUC performance. By balancing diagnostic performance and efficiency, our models offer a scalable and viable foundation for next-generation AI systems in cardiovascular care.