The proposed ParNet-adv model using a minimal subset of ECG leads (II and V1) transformed into 2D recurrence plots achieved an F1 score of 0.9763 for atrial fibrillation prediction, significantly outperforming complete 12-lead ECG models.
Does a novel AF prediction method using a minimal subset of ECG leads (II and V1) and a shallow ParNet-adv network improve AF classification performance compared to single or 12-lead ECGs?
A novel shallow neural network using 2D recurrence plots of just two ECG leads (II and V1) accurately detects atrial fibrillation, offering a computationally efficient approach suitable for wearable devices.
Tasa de eventos absoluta: 0.9763% vs 0.9692%
valor p: p=<0.05
Atrial fibrillation (AF) is the most common cardiac arrhythmia, and its early detection is critical for preventing complications and optimizing treatment. In this study, a novel AF prediction method is proposed, which is based on investigating a subset of the 12-lead ECG data using a recurrent plot and ParNet-adv model. The minimal subset of ECG leads (II V1) is determined via a forward stepwise selection procedure, and the selected 1D ECG data is transformed into 2D recurrence plot (RP) images as an input to train a shallow ParNet-adv Network for AF prediction. In this study, the proposed method achieved F1 score of 0.9763, Precision of 0.9654, Recall of 0.9875, Specificity of 0.9646, and Accuracy of 0.9760, which significantly outperformed solutions based on single leads and complete 12 leads. When studying several ECG datasets, including the CPSC and Georgia ECG databases of the PhysioNet/Computing in Cardiology Challenge 2020, the new method achieved F1 score of 0.9693 and 0.8660, respectively. The results suggested a good generalization of the proposed method. Compared with several state-of-art frameworks, the proposed model with a shallow network of only 12 depths and asymmetric convolutions achieved the highest average F1 score. Extensive experimental studies proved that the proposed method has a high potential for AF prediction in clinical and particularly wearable applications.
Zhang et al. (Tue,) conducted a other in Atrial fibrillation (n=5,845). ParNet-adv model with 2D recurrence plot of minimal subset ECG leads (II & V1) vs. Complete 12-lead ECG and other state-of-the-art models was evaluated on F1 score for atrial fibrillation prediction (p=<0.05). The proposed ParNet-adv model using a minimal subset of ECG leads (II and V1) transformed into 2D recurrence plots achieved an F1 score of 0.9763 for atrial fibrillation prediction, significantly outperforming complete 12-lead ECG models.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: