Key result
The proposed MCNN-BLSTM network achieved an accuracy of 87.57% and an average F1 score of 84.56% for atrial fibrillation detection on the CinC 2017 database.
Why the study?
Reliable and accurate atrial fibrillation detection from wearable short single-lead ECG recordings remains challenging due to limited information.
Does the MCNN-BLSTM network improve the accuracy of atrial fibrillation detection in short single-lead ECG recordings compared to other methods?
Does the MCNN-BLSTM network improve the accuracy of atrial fibrillation detection in short single-lead ECG recordings compared to other methods?
The proposed MCNN-BLSTM network provides accurate and reliable atrial fibrillation detection from short single-lead ECG recordings, suitable for wearable devices.
Novel single-lead ECG algorithm may aid wearable AF detection; leaves open prospective validation before clinical use.
Atrial fibrillation (AF) is an arrhythmia that may cause blood clots and increase the risk of stroke and heart failure. Traditional 12-lead electrocardiogram (ECG) acquisition equipment is complex and difficult to carry. Short single-lead ECG recordings based on wearable devices can remedy these shortcomings. However, reliable and accurate atrial fibrillation detection is still an issue because of the limited information on the short single-lead ECG recordings. In this paper, we propose a novel multi-branch convolutional neural network and bidirectional long short-term memory network (MCNN-BLSTM) to deal with the reliability and accuracy of AF detection in short single-lead ECG recordings. Firstly, to fuller extract the feature information of short single-lead ECG recordings, the MCNN module is designed to dynamically set several corresponding branches according to the number of slices of short single-lead ECG recordings. Then, the BLSTM module is designed to further enhance the feature information learned from each branch. We validated the model on the PhysioNet/CinC Challenge 2017 (CinC2017) database and verified the generalization of the model on the China Physiological Signal Challenge 2018 (CPSC2018) database. The results show that the accuracy of the model on the CinC 2017 database reaches 87.57%, and the average F1 score reaches 84.56%. The accuracy of the model on the CPSC 2018 database reaches 87.50%, and the average F1 score reaches 82.01%. Compared with other advanced methods, our model shows better performance and can meet the daily needs of atrial fibrillation detection with short ECG wearable devices.
No takes yet. Share an insight, caveat, or question.
Zhang et al. (2022) studied Atrial fibrillation. MCNN-BLSTM network vs. Other advanced methods was evaluated on Accuracy and average F1 score for atrial fibrillation detection. The proposed MCNN-BLSTM network achieved an accuracy of 87.57% and an average F1 score of 84.56% for atrial fibrillation detection on the CinC 2017 database.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: