MGNN: A multiscale grouped convolutional neural network for efficient atrial fibrillation detection. (September 2022)

• Record Type: Journal Article
• Authors: Liu, Sen; Wang, Aiguo; Deng, Xintao; Yang, Cuiwei
• Is Part Of: Computers in biology and medicine. Volume 148(2022)
• Publication Date: 2022-09
• Subjects: Atrial fibrillation -- Deep learning -- RR interval sequences -- Grouped convolutional neural network; Medicine -- Data processing -- Periodicals; Biology -- Data processing -- Periodicals; 610.285
• DOI: 10.1016/j.compbiomed.2022.105863
• Languages: English
• ISSNs: 0010-4825

Abstract

Abstract: The reliable detection of atrial fibrillation (AF) is of great significance for monitoring disease progression and developing tailored care paths. In this work, we proposed a novel and robust method based on deep learning for the accurate detection of AF. Using RR interval sequences, a multiscale grouped convolutional neural network (MGNN) combined with self-attention was designed for automatic feature extraction, and AF and non-AF classification. An average accuracy of 97.07% was obtained in the 5-fold cross-validation. The generalization ability of the proposed MGNN was further independently tested on four other unseen datasets, and the accuracy was 92.23%, 96.86%, 94.23% and 95.91%. Moreover, comparison of the network structures indicated that the MGNN had not only better detection performance but also lower computational complexity. In conclusion, the proposed model is shown to be an efficient AF detector that has great potential for use in clinical auxiliary diagnosis and long-term home monitoring based on wearable devices. Highlights: The acquisition of RR interval sequences is flexible in the assessment of atrial fibrillation. The analysis based on short RR interval sequences facilitates detection of paroxysmal episodes of atrial fibrillation. The end-to-end convolutional neural network enables automated analysis in the long-term monitoring. The proposed model shows low complexity, and achieves excellent generalization performance on five public databases.