Real-time detection of atrial fibrillation from short time single lead ECG traces using recurrent neural networks

Abstract

Atrial fibrillation (AF) is the predominant type of cardiac arrhythmia affecting more than 45 Million individuals globally. It is one of the leading contributors of strokes and hence detecting them in real-time is of paramount importance for early intervention. Traditional methods require long ECG traces and tedious preprocessing for accurate diagnosis. In this paper, we explore and employ deep learning methods such as RNN, LSTM and GRU to detect the Atrial Fibrillation (AF) faster in the given electrocardiogram traces. For this study, we used one of the well-known publicly available MIT-BIH Physionet dataset. To the best of our knowledge this is the first time Deep learning has been employed to detect the Atrial Fibrillation in real-time. Based on our experiments RNN, LSTM and GRU offer the accuracy of 0.950, 1.000 and 1.000 respectively. Our methodology does not require any de-noising, other filtering and preprocessing methods. Results are encouraging enough to begin clinical trials for the real-time detection of AF that will be highly beneficial in the scenarios of ambulatory, intensive care units and for real-time detection of AF for life saving implantable defibrillators.