Computer-aided sleep apnea diagnosis from single-lead electrocardiogram using Dual Tree Complex Wavelet Transform and spectral features

In this work, Dual Tree Complex Wavelet Transform (DT-CWT) is introduced to devise an effective feature extraction scheme for physiological signal analysis. Unlike discrete wavelet transform- DT-CWT ensures limited redundancy and provides approximate shift invariance. To demonstrate the efficacy of DT-CWT for physiological signal analysis, it is applied in conjunction with spectral features to propound a feature extraction scheme for automatic sleep apnea screening using single-lead ECG. It is shown that spectral features can distinguish between apnea and normal ECG signals quite well. This is further confirmed by the p-values obtained by Kruskal-Wallis one-way analysis of variance and graphical analyses. Thus, spectral features in the DT-CWT domain may be used to characterize ECG signal and help the sleep research community to implement various classification models to put computerized apnea screening into clinical practice.