Automated detection of sleep apnea from electrocardiogram signals using nonlinear parameters

Abstract

Sleep apnoea is a very common sleep disorder which can cause symptoms such as daytime sleepiness, irritability and poor concentration. To monitor patients with this sleeping disorder we measured the electrical activity of the heart. The resulting electrocardiography (ECG) signals are both non-stationary and nonlinear. Therefore, we used nonlinear parameters such as approximate entropy, fractal dimension, correlation dimension, largest Lyapunov exponent and Hurst exponent to extract physiological information. This information was used to train an artificial neural network (ANN) classifier to categorize ECG signal segments into one of the following groups: apnoea, hypopnoea and normal breathing. ANN classification tests produced an average classification accuracy of 90%; specificity and sensitivity were 100% and 95%, respectively. We have also proposed unique recurrence plots for the normal, hypopnea and apnea classes. Detecting sleep apnea with this level of accuracy can potentially reduce the need of polysomnography (PSG). This brings advantages to patients, because the proposed system is less cumbersome when compared to PSG.