Classification of ECG Arrhythmia using Recurrent Neural Networks

TLDR

The study aims to automatically separate regular and irregular ECG beats. The authors used the MIT‑BIH Arrhythmia database, feeding ECG time‑series into an LSTM and splitting the data into training and test sets. RNNs, particularly LSTM, accurately classified normal and abnormal ECG beats, outperforming other RNN models in quantitative tests.

Abstract

In this paper, Recurrent Neural Networks (RNN) have been applied for classifying the normal and abnormal beats in an ECG. The primary aim of this paper was to enable automatic separation of regular and irregular beats. The MIT-BIH Arrhythmia database is being used to classify the beat classification performance. The methodology used is carried out using huge volume of standard data i.e. ECG time-series data as inputs to Long Short Term Memory Network. We divided the dataset as training and testing sub-data. The effectiveness, accuracy and capabilities of our methodology ECG arrhythmia detection is demonstrated and quantitative comparisons with different RNN models have also been carried out.