Key result
KDM-Net outperforms standard models, classifying 12-lead atrial arrhythmias with ~96% accuracy.
Why the study?
Distinguishing atrial fibrillation from atrial flutter is challenging due to similar ECG manifestations and high risk of misclassification, motivating development of an effective atrial arrhythmia classification model.
Does KDM-Net improve the classification accuracy and F1-score of atrial arrhythmias from 12-lead ECGs compared to representative models?
Does KDM-Net improve the classification accuracy and F1-score of atrial arrhythmias from 12-lead ECGs compared to representative models?
KDM-Net provides a highly accurate and effective deep learning solution for the automated detection and classification of atrial arrhythmias using 12-lead ECG signals.
May support automated atrial arrhythmia detection on 12-lead ECGs; extends technical benchmarks but leaves open prospective clinical validation.
OBJECTIVE: Automatic recognition of atrial arrhythmias is important for early clinical screening and computer-aided diagnosis. Distinguishing atrial fibrillation from atrial flutter remains challenging because of their similar electrocardiographic manifestations and high risk of misclassification. This study aimed to develop an effective model for atrial arrhythmia classification with improved multi-lead feature utilization, long-range temporal modeling, and cross-patient generalization. APPROACH: We propose KDM-Net, which takes 12-lead electrocardiogram signals as input. The network employs a large-kernel K module to enhance the perception of waveform morphology and rhythm patterns, a D module to recalibrate and fuse multi-lead features, and a bidirectional Mamba-based M module to model long-range temporal dependencies. KDM-Net was evaluated on the combined CUSPH and PTB-XL dataset under an inter-patient protocol. MAIN RESULTS: In five-fold cross-validation, KDM-Net achieved an average accuracy and F1-score of 96.04% and 89.21%, respectively. On the independent patient-level test set, the accuracy and F1-score were 96.41% and 88.31%, respectively. On the CinC 2020 external test set, the model achieved an accuracy and F1-score of 91.14% and 80.41%, respectively. KDM-Net outperformed several representative models in comparative experiments. SIGNIFICANCE: KDM-Net effectively integrates multi-lead spatial information and long-range temporal dependencies, demonstrating strong recognition performance and promising cross-patient generalization. It provides an effective solution for the intelligent diagnosis of atrial arrhythmias.
No takes yet. Share an insight, caveat, or question.
Sun et al. (2026) studied Atrial arrhythmias. KDM-Net vs. representative models was evaluated on Classification accuracy and F1-score. KDM-Net for 12-lead atrial arrhythmia classification achieved an accuracy of 96.41% and an F1-score of 88.31% on an independent patient-level test set, outperforming representative models.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: