Key result
SwinMobileNet model detects AF with ~98% accuracy, outperforming other deep learning architectures.
Why the study?
Atrial fibrillation can lead to severe complications, underscoring the urgent need for effective detection methods.
Does the VMD+HT+SwinMobileNet pipeline improve the accuracy of atrial fibrillation detection in ECG records compared to other deep learning models?
Does the VMD+HT+SwinMobileNet pipeline improve the accuracy of atrial fibrillation detection in ECG records compared to other deep learning models?
A novel hybrid deep learning model combining time-frequency analysis and SwinMobileNet achieves high accuracy in detecting atrial fibrillation from ECG signals, offering potential for real-time clinical application.
Answers are grounded in this paper and cite their sources.
May support hybrid DL for ECG-based AF detection; leaves open prospective validation before clinical adoption.
Atrial fibrillation (AF), a common cardiac arrhythmia, can lead to severe complications, emphasizing the urgent need for effective detection methods. This study proposes an automated algorithm for AF detection that combines time-frequency analysis with deep learning techniques, achieving exceptional performance across multiple public ECG datasets. The proposed system applies variational mode decomposition (VMD) to decompose non-stationary ECG signals, followed by Hilbert transform (HT) to generate time-frequency representations. These 2D maps are then processed by a deep learning model for classification. We introduce a novel architecture, SwinMobileNet, which integrates the strengths of the Swin Transformer and MobileNetV2 to effectively model both spatial and temporal features in ECG signals. An adaptive attention mechanism ensures efficient and accurate classification. The implementation of this algorithm is available at: https://anonymous.4open.science/r/SwinMobileNet1-0C3C .
No takes yet. Share an insight, caveat, or question.
Zeng et al. (2025) studied Atrial Fibrillation (n=27,990). SwinMobileNet with time-frequency representations (VMD and HT) vs. Traditional CNN and Transformer models (e.g., ResNet34, MobileNetV2, InceptionV2) was evaluated on Accuracy of Atrial Fibrillation detection (Binary classification on Paroxysmal AF dataset). The proposed SwinMobileNet model combined with time-frequency representations achieved 98.43% accuracy for atrial fibrillation detection on the Paroxysmal AF dataset, outperforming other deep learning architectures.
Synapse has enriched 8 closely related papers on similar clinical questions. Consider them for comparative context: