Key result
RM-PAFNet model achieves up to ~91% precision localizing PAF on clinical ECGs.
Why the study?
Coupling of rhythm and morphology attributes causes ambiguous boundaries and misleads deep learning models in localizing paroxysmal AF episodes on single-lead ECGs.
Does RM-PAFNet improve the localization and classification of paroxysmal atrial fibrillation in single-lead ECGs?
Does RM-PAFNet improve the localization and classification of paroxysmal atrial fibrillation in single-lead ECGs?
The RM-PAFNet deep learning model demonstrates high precision and reliability for localizing paroxysmal atrial fibrillation in single-lead ECGs by decoupling rhythm and morphological attributes.
May aid single-lead ECG monitoring for PAF; leaves open prospective validation before clinical use.
The transient and asymptomatic nature of paroxysmal atrial fibrillation (PAF) episodes makes their localization challenging. Although there has been an interest in assessing the atrial fibrillation (AF) burden of PAF patients through wearable electrocardiogram (ECG) monitoring, other arrhythmia symptoms and the artifact noise will cause ambiguous boundaries between AF and non-AF events. In fact, the coupling of the rhythmic attribute of R-peaks with the morphological attribute of P-waves or f-waves is what primarily causes these blurring representations. For previous end-to-end deep learning-based AF detection, abnormalities in a single attribute of morphology or rhythm are likely to mislead the model in the determination of AF. To address this issue, we established a rhythm-morphology-decoupled model, which was referred to as RM-PAFNet, for PAF localization. For RM-PAFNet, we utilized the squeeze-and-excitation residual (SE-Res) block as the fundamental unit to enhance interaction between feature channels. The two attributes were separated via mutual information (MI) constraints and knowledge distillation (KD) on the latent distributions. For experiments, we utilized The China Physiological Signal Challenge 2021-Train (CPSC 2021) database as training set and two clinical ECG databases from CPSC 2021-TEST as test set. The results indicated that RM-PAFNet consistently achieved the highest localization performance across various experiments. The PAF localization scores (C-Score) of RM-PAFNet on the two test sets are 88.66% and 70.33%, with intersection over unions (IoU) of 94.58% and 80.89% and F1s of 86.77% and 90.55%. Furthermore, RM-PAFNet also achieved the highest classification performance for AF, with F1s of 88.67% and 84.42% on the CPSC 2021-Test and CinC 2017 databases. The results demonstrated that RM-PAFNet exhibited high precision and reliability in the localization of PAF.
No takes yet. Share an insight, caveat, or question.
Li et al. (2024) studied Paroxysmal atrial fibrillation (PAF). RM-PAFNet was evaluated on PAF localization scores (C-Score). The RM-PAFNet model achieved high precision in localizing paroxysmal atrial fibrillation, with C-Scores of 88.66% and 70.33% and F1 scores of 86.77% and 90.55% on two clinical ECG test sets.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: