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

TL;DR

HexagonalWarriorMamba (HWMamba) is a novel deep learning framework that models 12-lead ECGs as 2D images, outperforming state-of-the-art methods in multi-label cardiac abnormality detection across diverse datasets.

Contribution

The paper introduces HWMamba, a hierarchical 2D image-based model with a 2D Selective Scan mechanism, enhancing global context modeling for ECG multi-label classification.

Findings

HWMamba outperforms current SOTA methods on key metrics.

The model balances discriminative power with threshold selection.

It maintains near-SOTA Macro AUROC performance.

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.