Convolutional Recurrent Neural Networks for Electrocardiogram Classification

TL;DR

This paper introduces two deep neural network architectures, including CNN and CNN-LSTM, for classifying ECG recordings, demonstrating improved performance with a novel data augmentation method on atrial fibrillation detection.

Contribution

It presents a novel combination of CNN and LSTM architectures for ECG classification and introduces an effective data augmentation scheme for improved training.

Findings

CNN-LSTM outperforms CNN with an 82.1% F1 score.

Data augmentation significantly improves classification accuracy.

Proposed models effectively classify atrial fibrillation from ECG data.

Abstract

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.