Convolutional Recurrent Neural Networks for Electrocardiogram Classification
This work addresses the problem of automated ECG classification for medical diagnosis, but it is incremental as it builds on existing deep learning methods.
The authors tackled the classification of atrial fibrillation in ECG recordings by proposing two deep neural network architectures, with the convolutional-LSTM hybrid achieving an F1 score of 82.1% on a hidden test set.
We propose two deep neural network architectures for classification of arbitrary-length electrocardiogram (ECG) recordings and evaluate them on the atrial fibrillation (AF) classification data set provided by the PhysioNet/CinC Challenge 2017. The first architecture is a deep convolutional neural network (CNN) with averaging-based feature aggregation across time. The second architecture combines convolutional layers for feature extraction with long-short term memory (LSTM) layers for temporal aggregation of features. As a key ingredient of our training procedure we introduce a simple data augmentation scheme for ECG data and demonstrate its effectiveness in the AF classification task at hand. The second architecture was found to outperform the first one, obtaining an $F_1$ score of $82.1$% on the hidden challenge testing set.