Key result
Novel AS-CNN-GRU deep learning model achieves state-of-the-art multi-label ECG arrhythmia classification.
Why the study?
Standard ECG deep learning approaches do not fully account for dynamic temporal, spatial, and multi-labeling characteristics or disease correlations, resulting in information loss.
A novel multi-label fusion deep learning approach combining CNN and RNN networks improves the automatic detection and classification of arrhythmias from ECG signals.
May accelerate automated multi-label arrhythmia detection in ECG workflows; leaves open prospective clinical validation before adoption.
There are three primary challenges in the automatic diagnosis of arrhythmias by electrocardiogram (ECG): the significant variation among individual patients, the multiple pathologies in the ECG signal and the high cost in annotating clinical ECG with the corresponding labels. Traditional ECG processing approaches rely heavily on prior knowledge, such as those from feature extraction and waveform analysis. The preprocessing for prior knowledge incurs computational overhead. Furthermore, standard deep learning methods do not fully consider the dynamic temporal, spatial and multi-labeling characteristics of ECG data. In clinical ECG waveforms, it is common to see multi-labeling in which a patient is labeled with multiple classes of arrhythmias. However, multiclass approaches in current research mainly solve the multi-label machine learning problem, ignoring the correlation between diseases, resulting in information loss. In this paper, an arrhythmia detection and classification scheme called multi-label fusion deep learning is proposed. The objective is to build a unified system with automatic feature learning which supports effective multi-label classification. First, a multi-label ECG-based feature selection method is combined with a matrix decomposition and sparse learning theory. The optimal feature subset is selected as a preprocessing algorithm for ECG data. A multi-label classifier is then constructed by fusing CNN and RNN networks to fully exploit the interactions and features of the time and space dimensions. The experimental result demonstrates that the proposed method can achieve a state-of-the-art performance compared to other algorithms in multi-label database experiments.
No takes yet. Share an insight, caveat, or question.
Yang et al. (2022) studied Arrhythmia (n=5,078). AS-CNN-GRU fusion deep learning model vs. Other traditional and ensemble multi-label classifiers (e.g., BRSVM, MLKNN, MLHARAM, MLSVM) was evaluated on Multi-label classification performance (Accuracy, Jaccard similarity, Hamming Loss, F-value). The proposed AS-CNN-GRU fusion deep learning model achieved state-of-the-art performance in multi-label arrhythmia classification by effectively extracting spatio-temporal features from ECG signals.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: