Wavelet transform and deep learning-based obstructive sleep apnea detection from single-lead ECG signals

Abstract

Sleep apnea is a common sleep disorder. To address the characteristics of ECG signals, we introduce a coordinate attention mechanism and propose an automatic sleep apnea classification model (CA-EfficientNet) based on wavelet transform and lightweight neural network. One-dimensional signals were converted into two-dimensional images by wavelet transform and in put into the proposed model for classification. The effects of input time window, wavelet transform type and data balance on classification performance were considered. PhysioNet apnea ECG database was used for training and evaluation. The 3-minute Frequency B-Spline wavelets transform of ECG signal was carried out, and Dice Loss was used to train the classification model of sleep breathing. The classification accuracy was 93.44%, precision was 93.2%, sensitivity was 88.9%, specificity was 96.2%, F1 score was 91%, and most indexes were better than other related work. Wavelet transform and CA-EfficientNet model provide a feasible diagnostic method for automatic classification of sleep apnea.