BEAT-Net: Injecting Biomimetic Spatio-Temporal Priors for Interpretable ECG Classification

TL;DR

BEAT-Net introduces a biomimetic, tokenization-based approach for ECG classification that enhances interpretability, robustness, and data efficiency by explicitly modeling physiological structures and rhythms.

Contribution

The paper presents BEAT-Net, a novel framework that reformulates ECG analysis as a language modeling task using QRS tokenization, improving interpretability and data efficiency over traditional CNN methods.

Findings

Achieves comparable accuracy to CNNs on large-scale benchmarks.

Significantly improves robustness and data efficiency, using only 30-35% of annotated data.

Provides inherent interpretability through attention mechanisms that align with clinical heuristics.

Abstract

Although deep learning has advanced automated electrocardiogram (ECG) diagnosis, prevalent supervised methods typically treat recordings as undifferentiated one-dimensional (1D) signals or two-dimensional (2D) images. This formulation compels models to learn physiological structures implicitly, resulting in data inefficiency and opacity that diverge from medical reasoning. To address these limitations, we propose BEAT-Net, a Biomimetic ECG Analysis with Tokenization framework that reformulates the problem as a language modeling task. Utilizing a QRS tokenization strategy to transform continuous signals into biologically aligned heartbeat sequences, the architecture explicitly decomposes cardiac physiology through specialized encoders that extract local beat morphology while normalizing spatial lead perspectives and modeling temporal rhythm dependencies. Evaluations across three large-scale benchmarks demonstrate that BEAT-Net matches the diagnostic accuracy of dominant convolutional neural network (CNN) architectures while substantially improving robustness. The framework exhibits exceptional data efficiency, recovering fully supervised performance using only 30 to 35 percent of annotated data. Moreover, learned attention mechanisms provide inherent interpretability by spontaneously reproducing clinical heuristics, such as Lead II prioritization for rhythm analysis, without explicit supervision. These findings indicate that integrating biological priors offers a computationally efficient and interpretable alternative to data-intensive large-scale pre-training.