The RT-AFNet model achieved high accuracy for automated atrial fibrillation detection across three public databases, with F1 scores ranging from 96.20% to 99.76% and AUC values from 98.28% to 99.97%.
Does the RT-AFNet architecture accurately detect atrial fibrillation from ECG signals?
The RT-AFNet hybrid deep learning architecture demonstrates high accuracy and robustness for automated atrial fibrillation detection across multiple public ECG databases.
Atrial fibrillation (AF) is a prevalent cardiac arrhythmia associated with an elevated risk of severe complications, including stroke and heart failure. Due to its paroxysmal nature and the inherent complexity of electrocardiogram (ECG) signals, developing highly accurate and robust automated detection methods remains a critical challenge. To address the limitations of existing models in simultaneously capturing local morphological anomalies and long-range temporal dependencies, we proposed RT-AFNet, a novel hybrid ResNet-Transformer architecture. Specifically, RT-AFNet integrated the robust local feature extraction capabilities of a Residual Neural Network (ResNet) backbone with the global temporal modeling power of a lightweight self-attention mechanism. Furthermore, a multi-scale feature fusion strategy was introduced to optimize feature representation. The proposed RT-AFNet model was evaluated on three public AF databases: the China Physiological Signal Challenge 2018 (CPSC2018), the PhysioNet/Computing in Cardiology Challenge 2017 (CinC2017), and the MIT-BIH Atrial Fibrillation Database (MIT-BIH AF). The proposed model achieved F1 scores of 99.76%, 97.47%, and 96.20%, along with area under the curve (AUC) values of 99.97%, 98.98%, and 98.28% on the three datasets, respectively. These results demonstrate that the proposed architecture exhibits excellent generalization ability and stability across different databases, providing a robust and reliable deep learning solution for automated AF screening.
Hu et al. (2026) studied Atrial fibrillation. RT-AFNet was evaluated on F1 score and area under the curve (AUC) for atrial fibrillation detection. The RT-AFNet model achieved high accuracy for automated atrial fibrillation detection across three public databases, with F1 scores ranging from 96.20% to 99.76% and AUC values from 98.28% to 99.97%.