Goal: This paper presents a methodology for the automatic detection of sleep apnea from single-lead ECG. Methods: It uses two novel features derived from the ECG, and two well-known features in heart rate variability analysis, namely the standard deviation and the serial correlation coefficients of the RR interval time series. The first novel feature uses the principal components of the QRS complexes, and it describes changes in their morphology caused by an increased sympathetic activity during apnea. The second novel feature extracts the information shared between respiration and heart rate using orthogonal subspace projections. Respiratory information is derived from the ECG by means of three state-of-the-art algorithms, which are implemented and compared here. All features are used as input to a least-squares support vector machines classifier, using an RBF kernel. In total, 80 ECG recordings were included in the study. Results: Accuracies of about 85% are achieved on a minute-by-minute basis, for two independent datasets including both hypopneas and apneas together. Separation between apnea and normal recordings is achieved with 100% accuracy. In addition to apnea classification, the proposed methodology determines the contamination level of each ECG minute. Conclusion: The performances achieved are comparable with those reported in the literature for fully automated algorithms. Significance: These results indicate that the use of only ECG sensors can achieve good accuracies in the detection of sleep apnea. Moreover, the contamination level of each ECG segment can be used to automatically detect artefacts, and to highlight segments that require further visual inspection.
