An Efficient Method to Detect Sleep Hypopnea- Apnea Events Based on EEG Signals

Yao Wang,Xiaohong Wang,Tianshun Yang,Siyu Ji,Xiaoyun Zhao,Huiquan Wang

doi:10.1109/access.2020.3038486

Abstract

Hypopnea refers to the state in which insufficient alveolar ventilation during night sleep decreases the respiratory airflow by more than 50% of the airflow. However, sleep apnea is a more serious respiratory event, such as complete cessation of respiratory airflow for 10 seconds. The occurrence of hypopnea is a precursor to the occurrence of apnea events and the two are closely connected. In this paper, we propose a method based on the combination of discrete wavelet transform and approximate entropy of EEG signals to detect sleep apnea and hypopnea events. For this purpose, first, data preprocessing is performed on the EEG record data set obtained from Tianjin Chest Hospital, and then infinite impulse response (IIR) Butterworth bandpass filter is used to decompose the data into delta, theta, alpha, beta and gamma. Second, descriptive features are extracted based on sub-bands discrete wavelet transform such as the approximate entropy of high-frequency coefficients. Third, the features are filtered based on Support Vector Machine (SVM) recursive elimination. Finally, several machine learning algorithms including SVM, K-Nearest Neighbor (KNN) and Random forest (RF) are employed to identify the occurrence of sleep hypopnea-apnea events. The highest accuracy rate reached 94.33%, the sensitivity reached 93.10%, and the specificity reached 95.07%. The obtained results validate that the proposed method is an effective and practical diagnostic method to detect the occurrence of hypopnea-apnea events.

Highlights

Sleep disturbances can lead to insufficient sleep at night and mental fatigue during the day, which can have a significant negative impact on our lives
A method for obstructive sleep apnea severity prediction based on single channel ECG signal was proposed, the accuracy of 79.45% for Obstructive Sleep Apnea (OSA) severity classification with sensitivity, specificity, and F-score was achieved [14]
EEG signals contain a lot of important information, which reflects activities and abnormal breathing, in this paper, a feature extraction based on EEG signals is proposed to detect sleep apnea-hypopnea events and achieve more accurate results

Summary

INTRODUCTION

Sleep disturbances can lead to insufficient sleep at night and mental fatigue during the day, which can have a significant negative impact on our lives. Y. Wang et al.: Efficient Method to Detect Sleep Hypopnea- Apnea Events Based on EEG Signals. The EEG signal feature extraction and intelligent methods for the corresponding waveband can be used to treat sleep disordered breathing [6], [7]. When a hypopnea or apnea event occurs, the EEG signal will show different characteristics in different frequency bands without exception. The proposed method in this article finds the approximate entropy of the detail coefficient as characteristics of EEG signals during the apnea-hypopnea events. Our model achieves the best result with accuracy 94.33%, sensitivity 93.10%, and specificity 95.07% and provides a detection method that uses the EEG signals to automatically detect the hypopnea-apnea events that occur during nighttime sleep

RELATED WORK

MATERIALS AND METHODS

FEATURE EXTRACTION

FEATURE SELECTION

Find the feature with the lowest ranking score:

RESULTS AND DISCUSSION