An attention-augmented bidirectional LSTM-based encoder-decoder architecture for electrocardiogram heartbeat classification

Electrocardiogram (ECG) records a series of heart depolarization and repolarization of the atria and ventricles that manifest in waves. They are systematically deployed as a standard non-invasive tool to monitor the cardiac activity and reliably detect eventual heart diseases or any abnormal heart activity. To relief the medical staff of the burden of diagnosing long ECG records, classification algorithms have been tested and explored to give a new way for heartbeat failure detection. This paper proposes a method based on a convolutional neural network (CNN) to extract time-invariant features and a bidirectional long short-term memory (BiLSTM) network-based sequence-to-sequence (seq2seq) architecture augmented with an attention mechanism (AM) to classify the heartbeats into five classes according to the ANSI/AAMI/ISO EC57, 1998-(R)2008 standard. We also use the adaptive synthetic sampling (ADASYN) which is a data augmentation technique to reduce the bias caused by imbalanced data. Finally, to avoid skewing the classification results, we use the inter-patient paradigm diagnosis. For verification, we used the MIT-BIH arrhythmia database, the experiment achieved an accuracy rate of 99.87%. The evaluation results demonstrate that the proposed method obtains excellent performances for heartbeat classification task. The introduction of an AM improves the efficiency of the encoder-decoder architecture.