Obstructive Sleep Apnea Detection based on ECG Signal using Statistical Features of Wavelet Subband

Abstract

One of the respiratory disorders is obstructive sleep apnea (OSA). OSA occurs when a person sleeps. OSA causes breathing to stop momentarily due to obstruction in the airways. In this condition, people with OSA will be deprived of oxygen, sleep awake and short of breath. Diagnosis of OSA by a doctor can be done by confirming the patient's complaints during sleep, sleep patterns, and other symptoms that point to OSA. Another way of diagnosing OSA is a polysomnography (PSG) examination in the laboratory to analyze apnea and hypopnea. However, this examination tends to be high cost and time consuming. An alternative diagnostic tool is an electrocardiogram (ECG) examination referring to changes in the mechanism of ECG-derived respiration (EDR). So digital ECG signal analysis is a potential tool for OSA detection. Therefore, in this study, it is proposed to classify OSA based on ECG signals using wavelets and statistical parameters. Statistical parameters include mean, variance, skewness kurtosis entropy calculated on the signal decomposition results. The validation performance of the proposed method is carried out using a support vector machine, k-nearest neighbor (k-NN), and ensemble classifier. The proposed method produces the highest accuracy of 89.2% using a bagged tree where all features are used as predictors. From this study, it is hoped that ECG signal analysis can be used to complete clinical diagnosis in detecting OSA.