Automatic detection of sleep-disordered breathing events using recurrent neural networks from an electrocardiogram signal

Abstract

In this study, we propose a novel method for automatically detecting sleep-disordered breathing (SDB) events using a recurrent neural network (RNN) to analyze nocturnal electrocardiogram (ECG) recordings. We design a deep RNN model comprising six stacked recurrent layers for the automatic detection of SDB events. The proposed deep RNN model utilizes long short-term memory (LSTM) and a gated-recurrent unit (GRU). To evaluate the performance of the proposed RNN method, 92 SDB patients were enrolled. Single-lead ECG recordings were measured for an average 7.2-h duration and segmented into 10-s events. The dataset comprised a training dataset (68,545 events) from 74 patients and test dataset (17,157 events) from 18 patients. The proposed method achieved high performance with an F1-score of 98.0% for LSTM and 99.0% for GRU. The results demonstrate superior performance over conventional methods. The proposed method can be used as a precise screening and diagnosing tool for patients with SDB disorders.