Automatic Detection of Obstructive Sleep Apnea Using Wavelet Transform and Entropy-Based Features From Single-Lead ECG Signal

Abstract

Obstructive Sleep Apnea (OSA) is a prevalent sleep disorder, and highly affects the quality of human life. Currently, gold standard for OSA detection is Polysomnogram. Since this method is time consuming and cost inefficient, practical systems focus on the usage of electrocardiogram (ECG) signals for OSA detection. In this paper, a novel automatic OSA detection method using a single-lead ECG signal has been proposed. A non-linear feature extraction using Wavelet Transform (WT) coefficients obtained by an ECG signal decomposition is employed. In addition, different classification methods are investigated. ECG signals are decomposed into 8 levels using a Symlet function as a mother Wavelet function with third-order. Then, the entropy-based features including fuzzy/approximate/sample/correct conditional entropy as well as other non-linear features including interquartile range, mean absolute deviation, variance, Poincare plot and recurrence plot are extracted from WT coefficients. The best features are chosen using the automatic sequential forward feature selection algorithm. In order to assess the introduced method, 95 single-lead ECG recordings are used. SVM classifier having a RBF kernel leads to an accuracy of 94.63% (Sens: 94.43%, Spec: 94.77%) and 95.71% (Sens: 95.83%, Spec: 95.66%) for minute-by-minute and subject-by-subject classifications, respectively. The results show that applying entropy-based features for extracting hidden information of the ECG signals outperforms other available automatic OSA detection methods. The results indicate that a highly accurate OSA detection is attained by just exploiting the single-lead ECG signals. Furthermore, due to the low computational load in the proposed method, it can easily be applied to the home monitoring systems.

A Novel Microwave Treatment for Sleep Disorders and Classification of Sleep Stages Using Multi-Scale Entropy

“…However, these methods are computationally complex, with some requiring 41 features to be extracted from EEG and physiological signals. These models are also accurate enough to meet clinical needs [ 32 , 33 , 34 ]. The microwave modulation and detection technology proposed in this paper can avoid the physiological artifact of patients and can improve successfully the recognition accuracy of sleep stages by combining with the multiscale entropy features that can better distinguish different types of information.…”

“…Quantifying the dynamic irregularity of time series is an important challenge in signal processing. Entropy is an effective and extensive method for measuring the irregularity and uncertainty of time series [ 32 ]. The complexity of the time series characterized by entropy value shows different trends with the increase of the time scale.…”

Obstrüktif Uyku Apnesi Tanıma için Öznitelik Seçimi

“…In all scenarios, we never use an instance in testing if we used it in training and vice versa. In order to be comparable with similar studies in [2], [48], [27], 10-fold cross-validation is used for the WSwSS scenario. For the BSwSS, we keep one subject (e.g., A03) for testing and use the rest (e.g., A01, A02, and A04) for training purpose.…”

“…Compared with our multimodal method, which performs better, the success may lie on the early-fusion scheme. BSwDS (Acc %) Shi et al [48] 97.3 89.8 -SVM [27] 82.24 --C4.5 [27] 80.91 --Bagging Reptree [27] 84.4 --Bagging ADtree [27] 79.85 --FT Trees [27] 79.32 --AdaBoost [27] 77.79 --REP Tree [27] 81.33 --kNN [27] 81.65 --Decision Table [27] 80.79 --MLP [27] 81.6 --Our Method (MM-PCA-SVM) 99.49 95.6 95.07 kNN [2] 92.52 --ANN [2] 91.36 --LDA [2] 79.92 --QDA [2] 61.16 --GentleBoost [2] 89.27 --NB [2] 44.04 --LR [2] 73.7 --SVM(RBF) [2] 92.98 --SVM(POL) [2] 90.3 --SVM(LIN) [2] 82.65 --…”

“…The frequent occurrence of OSA may cause several symptoms such as sleepiness, memory deficits, and depression. Undiagnosed OSA is also associated with diseases such as arrhythmias, brain stroke, ischemia, and higher blood pressures [2] and this results in billions of dollars costs due to the sleepiness-related accidents and health costs to the governments.…”