Recognition of Patient Groups with Sleep Related Disorders using Bio-signal Processing and Deep Learning.

Delaram Jarchi,Ales Prochazka,Oldrich Vysata,Jiri Kuchynka,Mehrin Kiani,Javier Andreu-Perez,Saeid Sanei

doi:10.3390/s20092594

Abstract

Accurately diagnosing sleep disorders is essential for clinical assessments and treatments. Polysomnography (PSG) has long been used for detection of various sleep disorders. In this research, electrocardiography (ECG) and electromayography (EMG) have been used for recognition of breathing and movement-related sleep disorders. Bio-signal processing has been performed by extracting EMG features exploiting entropy and statistical moments, in addition to developing an iterative pulse peak detection algorithm using synchrosqueezed wavelet transform (SSWT) for reliable extraction of heart rate and breathing-related features from ECG. A deep learning framework has been designed to incorporate EMG and ECG features. The framework has been used to classify four groups: healthy subjects, patients with obstructive sleep apnea (OSA), patients with restless leg syndrome (RLS) and patients with both OSA and RLS. The proposed deep learning framework produced a mean accuracy of 72% and weighted F1 score of 0.57 across subjects for our formulated four-class problem.

Highlights

Study of human sleep and the underlying physiological changes is crucial for detecting sleep disorders, improving the quality of sleep and avoiding daytime sleepiness
It includes a number of wearable sensors, such as an electrocardiogram (ECG) to record the cardiac activity from electrodes attached to chest; a pulse oximeter attached to a finger to record photoplethysmography (PPG) for blood oxygen saturation measurement; an electromyograph (EMG)
Our research has proposed a set of markers from highly-noisy electrophysiological data that can be useful for the recognition of disease symptoms

Summary

Introduction

Study of human sleep and the underlying physiological changes is crucial for detecting sleep disorders, improving the quality of sleep and avoiding daytime sleepiness. There are two main sleep disorders, including obstructive sleep apnea (OSA) [1,2] as a breathing-related sleep disorder, and restless leg syndrome (RLS) as a movement-related sleep disorder [3,4,5]. RLS is associated with uncontrollable sporadic or periodic leg movements during sleep. Polysomnography (PSG) as a type of sleep study has been developed for noninvasive analysis of sleep. It includes a number of wearable sensors, such as an electrocardiogram (ECG) to record the cardiac activity from electrodes attached to chest; a pulse oximeter attached to a finger to record photoplethysmography (PPG) for blood oxygen saturation measurement; an electromyograph (EMG)

Objectives

Methods

Results

Conclusion