SVM-Based Sleep Apnea Identification Using Optimal RR-Interval Features of the ECG Signal

Clinically, sleep apnea (SA) is divided into Obstructive Sleep Apnea (OSA) and Central Sleep Apnea (CSA). OSA, being the most common SA, is generally caused by a collapse of the upper respiratory airway. The cessations lasting in more than 10 seconds considered as apnea event might occur 5 to 30 times in an hour and up to 400 per night. Day and night time symptoms of SA include impaired concentration, depression, memory loss, snoring, nocturnal arousals, sweating and restless sleep. Polysomnography (PSG) is the current and traditional testing process which records many biometrics such as the breath airflow, respiratory movement, oxygen saturation, body saturation, body position, EEG, EOG, EMG, and ECG to determine the sleep stages. Over the past few years, most of the related research has focused on detecting OSA through statistical features of different bio-signals. However, PSG needs to be replaced by more convenient detection methods and faster treatment. In this regard, we present a fully automated approach of the apnea periods identification which is based on Support Vector Machines (SVMs) using an optimum feature set of the RR-inter-beat interval series of the ECG signal. This can be used as an early warning diagnosis sign for a patient who might be subject to an apnea attack.