Identification of Obstructive Sleep Apnea Using Artificial Neural Networks and Wavelet Packet Decomposition of the HRV Signal

Abstract

The advancement of telecommunication technologies has provided us with new promising alternatives for remote diagnosis and possible treatment suggestions for patients of diverse health disorders, among which is the ability to identify Obstructive Sleep Apnea (OSA) syndrome by means of Electrocardiograph (ECG) signal analysis. In this paper, the standard spectral bands’ powers and statistical interval-based parameters of the Heart Rate Variability (HRV) signal were considered as a form of features for classifying the Sultan Qaboos University Hospital (SQUH) database for OSA syndrome into 4 different levels. Wavelet packet analysis was applied to obtain and estimate the standard frequency bands of the HRV signal. Further, the single perceptron neural network, the feedforward with back-propagation neural network and the probabilistic neural network have been implemented in the classification task. The classification between normal subjects versus severe OSA patients achieved 95% accuracy with the probabilistic neural network. While the classification between normal subjects versus mild OSA subjects reached accuracy of 95% also. When grouping mild, moderate and severe OSA subjects in one group compared to normal subjects as a second group, the classification with the feedforward network achieved an accuracy of 87.5%. Finally, when classifying subjects directly into one of the four classes (normal or mild or moderate or severe), a 77.5% accuracy was achieved with the feedforward network.

Detection of sleep apnea using Machine learning algorithms based on ECG Signals: A comprehensive systematic review

“…As a result of this event, the brain increases the respiration rate by using immediate pulses to the respiratory system, and subsequently, the heart rate will increase again. Thus, such respiratory arrests affect the ECG waves, and episodes of apnea are recorded during an ECG record (Ali & Hossen, 2020). HR changes are determined by the analysis of heart rate variability (HRV).…”

“…In two studies, the diagnosis was made based on expertsexperts' opinions. One of the most common methods in studies for ECG signal analysis was the Pan Tompkins algorithm (PTA 12 ) (Al-Angari & Sahakian, 2012;Ali & Hossen, 2020;Baek et al, 2014;Varon et al, 2015;Bali, Nandi, Hiremath, & Patil, 2018;K. Li, Pan, Li, Jiang, & Liu, 2018;Ali & Hossen, 2020Tripathy, 2018Varon et al, 2015).…”

“…The filters have been applied to ECG waves with the aim of clearing ECG from noise, ground drift and baseline drift, and detecting HRV and EDR. Moving average filter was applied with the aim of limiting and adjusting the lower and upper limits of waves and eliminating false and unexplained points (Ali & Hossen, 2020;Ali & Hossen, 2020). This filter was also used to detect EDR (Song et al, 2016), RR distance (Chen et al, 2015) and mean RR value (Mendez et al, 2007;Mendez et al, 2009;Mendez et al, 2007).…”

Frequency monitoring analysis of milling edge chatter in composites using WPD for frequency band selection

“…The experimental results showed that the model achieved 95 % accuracy in classifying negative normal subjects and mild OSA subjects, and 87.5 % accuracy in classifying mild, moderate and severe OSA subjects [12]. Fan X.…”

A Review of Methods and Applications for a Heart Rate Variability Analysis

“…The WPD method has been gaining more popularity for HRV analyses in recent years than other decomposition methods mentioned above [52]. Notable applications of a WPD-based HRV analysis include automatic sleep apnea detection [53], depression [54], etc.…”