A Sub-frame Based Feature Extraction Approach from Split-Band EEG Signal for Sleep Apnea Event Detection Using Multi-Layer LSTM

Sleep apnea is a sleep disorder that millions of people all over the world are affected with. Untreated Sleep apnea can lead to various complex health issues including death. The detection of apnea events has been a pressing topic of research in the recent years. Several signals like polysomnography (PSG), electrocardiogram (ECG), electroencephalogram (EEG) are used to detect sleep apnea. In this paper, a novel approach has been proposed using EEG signal. The decomposed EEG signal is fed into a Long Short Term Memory (LSTM) model to explore the sequence of the signals. The output is then used for a Deep Neural Network (DNN) to correctly detect apnea frames. Lastly all the predictions are post-processed to get the final result. This scheme has the potential to be used in hospitals for continuous detection of sleep apnea event.

I. Introduction

Sleep apnea is a common yet dangerous respiratory disease all over the world. A patient while affected by this disease gets pause in breathing that can last for from a few seconds to even a few minutes. If kept untreated, people may become greatly vulnerable to other health problems, such as diabetes, high blood pressure, asthma and many other diseases. Death could occur from apnea due to lack of oxygen to the body if not treated at the right time. The percentage of the general adult population suffering from this disorder is in the region of 4 - 19% and for elderly patients this can rise to 49% [1].