HexagonalWarriorMamba: Superior Threshold-Dependent Multi-label Classification of 12-Lead ECG Cardiac Abnormalities

2026-05-18

AI Summary

Existing deep learning approaches struggle to effectively model the long-range dependencies and spatial relationships inherent in 12-lead electrocardiograms (ECGs), limiting their performance in multi-label cardiac abnormality diagnosis. This work proposes the first application of the Mamba architecture to two-dimensional modeling of 12-lead ECGs, introducing a hierarchical structure combined with a two-dimensional selective scanning mechanism to efficiently capture global contextual information and complex inter-lead correlations. Evaluated on the PhysioNet/CinC 2021 dataset, the proposed method consistently outperforms current state-of-the-art approaches across five threshold-dependent metrics—including Challenge Score and Subset Accuracy—while achieving Macro AUROC performance comparable to the best existing methods.

Abstract

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.

Problem

• multi-label classification
• 12-lead ECG
• cardiac abnormalities
• long-range dependencies
• automated diagnosis

Innovation

• Mamba architecture
• 2D Selective Scan
• multi-label ECG classification
• threshold-dependent metrics
• long-range dependencies