This study focuses on the analysis of blood oxygen saturation (SaO2) from nocturnal pulse oximetry (NPO) to help in the diagnosis of the obstructive sleep apnea (OSA) syndrome. A population of 148 patients suspected of suffering from OSA syndrome was studied. A wide set of 16 features was used to characterize changes in the SaO2 profile during the night. Our feature set included common statistics in the time and frequency domains, conventional spectral characteristics from the power spectral density (PSD) function, and nonlinear features. We performed feature selection by means of a step-forward logistic regression (LR) approach with leave-one-out cross-validation. Second- and fourth-order statistical moments in the time domain (M2t and M4t), the relative power in the 0.014-0.033 Hz frequency band (PR), and the Lempel-Ziv complexity (LZC) were automatically selected. 92.0% sensitivity, 85.4% specificity, and 89.7% accuracy were obtained. The optimum feature set significantly improved the diagnostic ability of each feature individually. Furthermore, our results outperformed classic oximetric indexes commonly used by physicians. We conclude that simultaneous analysis in the time and frequency domains by means of statistical moments, spectral and nonlinear features could provide complementary information from NPO to improve OSA diagnosis.
The aim of this study is to assess the utility of traditional statistical pattern recognition techniques to help in obstructive sleep apnoea (OSA) diagnosis. Classifiers based on quadratic (QDA) and linear (LDA) discriminant analysis, K-nearest neighbours (KNN) and logistic regression (LR) were evaluated. Spectral and nonlinear input features from oxygen saturation (SaO(2)) signals were applied. A total of 187 recordings from patients suspected of suffering from OSA were available. This initial dataset was divided into training set (74 subjects) and test set (113 subjects). Twelve classification algorithms were developed by applying QDA, LDA, KNN and LR with spectral features, nonlinear features and combination of both groups. The performance of each algorithm was measured on the test set by means of classification accuracy and receiver operating characteristic (ROC) analysis. QDA, LDA and LR showed better classification capability than KNN. The classifier based on LDA with spectral features provided the best diagnostic ability with an accuracy of 87.61% (91.05% sensitivity and 82.61% specificity) and an area under the ROC curve (AROC) of 0.925. The proposed statistical pattern recognition techniques could be applied as an OSA screening tool.
7 August 2013 in International Journal of Neural Systems
Nocturnal polysomnography (PSG) is the gold-standard for sleep apnea-hypopnea syndrome (SAHS) diagnosis. It provides the value of the apnea-hypopnea index (AHI), which is used to evaluate SAHS severity. However, PSG is costly, complex, and time-consuming. We present a novel approach for automatic estimation of the AHI from nocturnal oxygen saturation (SaO2) recordings and the results of an assessment study designed to characterize its performance. A set of 240 SaO2 signals was available for the assessment study. The data were divided into training (96 signals) and test (144 signals) sets for model optimization and validation, respectively. Fourteen time-domain and frequency-domain features were used to quantify the effect of SAHS on SaO2 recordings. Regression analysis was performed to estimate the functional relationship between the extracted features and the AHI. Multiple linear regression (MLR) and multilayer perceptron (MLP) neural networks were evaluated. The MLP algorithm achieved the highest performance with an intraclass correlation coefficient (ICC) of 0.91. The proposed MLP-based method could be used as an accurate and cost-effective procedure for SAHS diagnosis in the absence of PSG.