Obstructive sleep apnea detection using discrete wavelet transform-based statistical features

• Published in: Computers in biology and medicine 2021-03, Vol.130, p.104199-104199, Article 104199
• Main Authors: Rajesh, Kandala.N.V.P.S., Dhuli, Ravindra, Kumar, T. Sunil
• Format: Article
• Language: English
• Subjects: Apnea; Cardiovascular diseases; Classifiers; Diabetes mellitus; Discrete Wavelet Transform; Discriminant analysis; EKG; Electrocardiography; Electroencephalography; Energy and statistical features; Heart rate; Hypertension; Older people; Organs; Particle swarm optimization; Physiology; PSO; Random forest; Single lead ECG; Sleep; Sleep apnea; Sleep disorders; Support vector machines; Waveforms; Wavelet transforms
• ISSN: 0010-4825; 1879-0534
• DOI: 10.1016/j.compbiomed.2020.104199

Obstructive sleep apnea (OSA) is a sleep disorder identified in nearly 10% of middle-aged people, which deteriorates the normal functioning of human organs, notably that of the heart. Furthermore, untreated OSA is associated with increased hypertension, diabetes, stroke, and cardiovascular diseases, thereby increasing the mortality risk. Therefore, early identification of sleep apnea is of significant interest. In this paper, an automated approach for OSA diagnosis using a single-lead electrocardiogram (ECG) has been reported. Three sets of features, namely moments of power spectrum density (PSD), waveform complexity measures, and higher-order moments, are extracted from the 1-min segmented ECG subbands obtained from discrete wavelet transform (DWT). Later, correlation-based feature selection with particle swarm optimization (PSO) search strategy is employed for getting an optimum feature vector. This process retained 18 significant features from initially computed 32 features. Finally, the acquired feature set is fed to different classifiers including, linear discriminant analysis, nearest neighbors, support vector machine, and random forest to perform per segment classification. Experiments on the publicly available physionet single-lead ECG dataset show that the proposed approach using the random forest classifier effectively discriminates normal and OSA ECG signals. Specifically, our method achieved an accuracy of 89% and 90%, with 50-50 hold-out validation and 10-fold cross-validation, respectively. Besides, in both these validation scenarios, our method obtained 96% of the area under ROC. Importantly, our proposed approach provided better performance results than most of the existing methodologies. •The discrete wavelet transform-based time-frequency feature representation is presented.•The correlation-based feature selection with particle swarm optimization is used to reduce feature vector length.•Statistical analysis is performed to show the significance of the computed features.•Four different classifiers, including SVM, k-NN, LDA, and Random Forest, are used for testing.•The proposed approach achieved an appreciable accuracy of 90.3 % in detecting OSA using a random forest classifier.