A Multi-View Learning Approach to Enhance Automatic 12-Lead ECG Diagnosis Performance

TL;DR

This paper introduces a multi-view ensemble learning approach combined with ECG data augmentation, significantly improving automatic 12-lead ECG diagnosis accuracy over existing methods.

Contribution

It presents a novel ensemble-based multi-view learning framework with ECG augmentation, demonstrating superior performance in ECG diagnosis tasks.

Findings

Achieved an F1 score of 0.840, surpassing state-of-the-art methods.

Showed that multi-view learning enhances diagnostic accuracy.

Data augmentation contributes to performance improvements.

Abstract

The performances of commonly used electrocardiogram (ECG) diagnosis models have recently improved with the introduction of deep learning (DL). However, the impact of various combinations of multiple DL components and/or the role of data augmentation techniques on the diagnosis have not been sufficiently investigated. This study proposes an ensemble-based multi-view learning approach with an ECG augmentation technique to achieve a higher performance than traditional automatic 12-lead ECG diagnosis methods. The data analysis results show that the proposed model reports an F1 score of 0.840, which outperforms existing state-ofthe-art methods in the literature.