A deep learning approach for real-time detection of atrial fibrillation

作者：

Highlights：

• Proposed a deep learning model for automatic detection of atrial fibrillation.

• An end-to-end model using CNN and RNN was developed to extract high level features.

• The model was trained and validated on three different publicly available databases.

• A post-processing scheme was also used to reduce the number of false positives.

摘要

•Proposed a deep learning model for automatic detection of atrial fibrillation.•An end-to-end model using CNN and RNN was developed to extract high level features.•The model was trained and validated on three different publicly available databases.•A post-processing scheme was also used to reduce the number of false positives.

论文关键词：Electrocardiogram (ECG),Atrial fibrillation,Deep learning,Convolutional neural networks (CNNs),Recurrent neural networks (RNNs),Long short-term memory (LSTM)

论文评审过程：Received 15 May 2018, Revised 20 July 2018, Accepted 9 August 2018, Available online 14 August 2018, Version of Record 23 August 2018.

论文官网地址：https://doi.org/10.1016/j.eswa.2018.08.011