ECG-RAMBA: Zero-Shot ECG Generalization by Morphology-Rhythm Disentanglement and Long-Range Modeling

TL;DR

ECG-RAMBA introduces a novel framework that disentangles morphology and rhythm in ECG signals, enhancing zero-shot generalization across datasets through context-aware fusion and long-range modeling.

Contribution

The paper presents ECG-RAMBA, a new approach that separates and combines ECG morphology and rhythm features, improving cross-dataset robustness without test-time adaptation.

Findings

Achieves macro ROC-AUC of approximately 0.85 on Chapman--Shaoxing dataset.

Attains PR-AUC of 0.708 for atrial fibrillation detection on CPSC-2021 in zero-shot transfer.

Demonstrates consistent cross-dataset performance and robustness to distribution shifts.

Abstract

Deep learning has achieved strong performance for electrocardiogram (ECG) classification within individual datasets, yet dependable generalization across heterogeneous acquisition settings remains a major obstacle to clinical deployment and longitudinal monitoring. A key limitation of many model architectures is the implicit entanglement of morphological waveform patterns and rhythm dynamics, which can promote shortcut learning and amplify sensitivity to distribution shifts. We propose ECG-RAMBA, a framework that separates morphology and rhythm and then re-integrates them through context-aware fusion. ECG-RAMBA combines: (i) deterministic morphological features extracted by MiniRocket, (ii) global rhythm descriptors computed from heart-rate variability (HRV), and (iii) long-range contextual modeling via a bi-directional Mamba backbone. To improve sensitivity to transient abnormalities under windowed inference, we introduce a numerically stable Power Mean pooling operator ($Q=3$) that emphasizes high-evidence segments while avoiding the brittleness of max pooling and the dilution of averaging. We evaluate under a protocol-faithful setting with subject-level cross-validation, a fixed decision threshold, and no test-time adaptation. On the Chapman--Shaoxing dataset, ECG-RAMBA achieves a macro ROC-AUC $\approx 0.85$. In zero-shot transfer, it attains PR-AUC $=0.708$ for atrial fibrillation detection on the external CPSC-2021 dataset, substantially outperforming a comparable raw-signal Mamba baseline, and shows consistent cross-dataset performance on PTB-XL. Ablation studies indicate that deterministic morphology provides a strong foundation, while explicit rhythm modeling and long-range context are critical drivers of cross-domain robustness.