Key result
An ensemble-based multi-view learning approach with ECG-specific data augmentation achieved an F1 score of 0.840 for classifying nine arrhythmia classes, outperforming existing state-of-the-art methods.
Why the study?
The impact of combining multiple deep learning components and the role of augmentation techniques on automatic ECG diagnosis had not been sufficiently investigated.
Does an ensemble-based multi-view learning approach with ECG augmentation improve automatic 12-lead ECG diagnosis performance compared to existing methods?
Does an ensemble-based multi-view learning approach with ECG augmentation improve automatic 12-lead ECG diagnosis performance compared to existing methods?
An ensemble-based multi-view deep learning approach with ECG-specific data augmentation achieves state-of-the-art performance in automatic 12-lead ECG arrhythmia classification.
The electrocardiogram (ECG) has important clinical value for the early diagnosis of cardiovascular diseases. Recently, the performance of existing diagnosis models based on ECG data has improved with the introduction of deep learning (DL). However, the impact of various combinations of multiple DL components and/or the role of augmentation techniques on the diagnosis have not been sufficiently investigated in this field. In this sense, this study aims to design an integrated model consisting of diverse DL-based modules. Here, an ensemble-based multi-view learning approach with an ECG augmentation technique is proposed to achieve higher performance than traditional automatic 12-lead ECG diagnosis methods. Accordingly, several experiments have been conducted with CPSC2018 dataset for evaluation. The proposed model reports F1 score of 0.840, which outperforms existing state-of-the-art methods in the literature. Thus, this study provides quantitative evidence demonstrating that the multi-view learning approach can be used as a unified algorithmic method in the field of bioinformatics.
No takes yet. Share an insight, caveat, or question.
Choi et al. (2023) studied Arrhythmia (n=9,831). Ensemble-based multi-view learning approach with ECG augmentation vs. Existing state-of-the-art methods was evaluated on F1 score. An ensemble-based multi-view learning approach with ECG-specific data augmentation achieved an F1 score of 0.840 for classifying nine arrhythmia classes, outperforming existing state-of-the-art methods.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: