Real-time automatic monitoring system for sleep apnea using single-lead electrocardiogram

Sleep apnea contributes to a variety of health threatening problems. However, there is a extremely low public and medical awareness of this disease. In order to identify sleep apnea/hyopnea, some effective features have been extracted from ECG signal, PPG signal and EEG signal. In this work, a novel combined of features characterizing physiological signals for monitoring epochs of sleep apnea is presented. They are RR interval, the amplitude of RR, TT interval, the amplitude of TT, real-time heart rate, angle of QRS, Inter-quartile range, and absolute deviation values of RR-intervals. These physiological indicators extracted from single-lead ECG signal distinguish the sleep apnea from normal events based on support vector machines with linear kernel. The aim of study was to classify a short-duration epoch of ECG data obtained from real-time detecting system. Fifteen seconds were chosen to be the epoch length. Additionally, a preprocessing method is carried out to detect QRS and T-wave from ECG signals. Associating with these techniques, a portable real-time automated monitoring system for detecting sleep apnea is designed.