Screening obstructive sleep apnoea syndrome from electrocardiogram recordings using support vector machines

A machine learning technique [support vector machines (SVM)] for automated recognition of obstructive sleep apnoea syndrome OSAS types from their nocturnal ECG recordings is investigated. Total 70 sets of nocturnal ECG recordings [35 sets (learning set) and 35 sets (test set)] from normal subjects (OSAS-) and subjects with OSAS (OSAS+) were collected from physionet. Features extracted from successive wavelet coefficient levels after wavelet decomposition of RR intervals and QRS amplitudes of whole record were presented as inputs to train the SVM mode to recognize OSAS+/- subjects. The optimally trained SVM showed that a SVM using a subset of selected combination of HRV and EDR features correctly recognized 20 out of 20 OSAS+ subjects and 10 out of 10 OSAS- subjects. For estimating the relative severity of OSAS, the posterior probabilities of SVM outputs were calculated.