HexagonalWarriorMamba: Superior Threshold-Dependent Multi-label Classification of 12-Lead ECG Cardiac Abnormalities
For researchers and clinicians needing accurate multi-label ECG classification, this work provides a new approach that improves threshold-dependent metrics, but the gains are incremental over existing SOTA.
The paper proposes HexagonalWarriorMamba, a framework that processes 12-lead ECGs as 2D images using a Mamba-based architecture with a 2D Selective Scan mechanism. It outperforms state-of-the-art methods on the PhysioNet Challenge 2021 dataset across five threshold-dependent metrics, including Challenge Score and Subset Accuracy, while maintaining near-SOTA Macro AUROC.
The accurate automated diagnosis of cardiac abnormalities from 12-lead electrocardiograms (ECGs) is critical for managing cardiovascular disease. However, detecting concurrent conditions remains a challenge for traditional deep learning models, which often have limited ability to model the long-range dependencies inherent in ECG signals. This manuscript proposes HexagonalWarriorMamba (HWMamba), a framework built on the Mamba architecture that processes 12-lead ECGs as single-channel 2D images rather than conventional 1D time series. By integrating a hierarchical architecture with a 2D Selective Scan mechanism, HWMamba is designed to model global context and complex spatial relationships within the data. The model is evaluated on the PhysioNet/Computing in Cardiology Challenge 2021 dataset, which includes 26 diagnostic labels and comprises recordings collected from seven institutions across four countries and three continents. Results demonstrate that HWMamba outperforms current state-of-the-art (SOTA) methods across five key threshold-dependent metrics, including Challenge Score and Subset Accuracy. These improvements provide a balance between strong discriminative capability and effective threshold selection derived from the training data, while maintaining near-SOTA performance in Macro AUROC. This Hexagonal Warrior performance, reflecting consistent performance across multiple evaluation dimensions, positions HWMamba as a robust and versatile approach for multi-label ECG classification.