F. del Campo

Utility of Approximate Entropy From Overnight Pulse Oximetry Data in the Diagnosis of the Obstructive Sleep Apnea Syndrome

Approximate entropy (ApEn) is a family of statistics introduced as a quantification of regularity in time series without any a priori knowledge about the system generating them. The aim of this preliminary study was to assess whether a time series analysis of arterial oxygen saturation (SaO2) signals from overnight pulse oximetry by means of ApEn could yield essential information on the diagnosis of obstructive sleep apnea (OSA) syndrome. We analyzed SaO2 signals from 187 subjects: 111 with a positive diagnosis of OSA and 76 with a negative diagnosis of OSA. We divided our data in a training set (44 patients with OSA Positive and 30 patients with OSA Negative) and a test set (67 patients with OSA Positive and 46 patients with OSA Negative). The training set was used for algorithm development and optimum threshold selection. Results showed that recurrence of apnea events in patients with OSA determined a significant increase in ApEn values. This method was assessed prospectively using the test dataset, where we obtained 82.09% sensitivity and 86.96% specificity. We conclude that ApEn analysis of SaO2 from pulse oximetric recording could be useful in the study of OSA

Nonlinear characteristics of blood oxygen saturation from nocturnal oximetry for obstructive sleep apnoea detection.

Nocturnal oximetry is an attractive option for the diagnosis of obstructive sleep apnoea (OSA) syndrome because of its simplicity and low cost compared to polysomnography (PSG). The present study assesses nonlinear analysis of blood oxygen saturation (SaO(2)) from nocturnal oximetry as a diagnostic test to discriminate between OSA positive and OSA negative patients. A sample of 187 referred outpatients, clinically suspected of having OSA, was studied using nocturnal oximetry performed simultaneously with complete PSG. A positive OSA diagnosis was found for 111 cases, while the remaining 76 cases were classified as OSA negative. The following oximetric indices were obtained: cumulative time spent below a saturation of 90% (CT90), oxygen desaturation indices of 4% (ODI4), 3% (ODI3) and 2% (ODI2) and the delta index (Delta index). SaO(2) records were subsequently processed applying two nonlinear methods: central tendency measure (CTM) and Lempel-Ziv (LZ) complexity. Significant differences (p < 0.01) were found between OSA positive and OSA negative patients. Using CTM we obtained a sensitivity of 90.1% and a specificity of 82.9%, while with LZ the sensitivity was 86.5% and the specificity was 77.6%. CTM and LZ accuracies were higher than those provided by ODI4, ODI3, ODI2 and CT90. The results suggest that nonlinear analysis of SaO(2) signals from nocturnal oximetry could yield useful information in OSA diagnosis.

Automated Prediction of the Apnea-Hypopnea Index from Nocturnal Oximetry Recordings

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.

Linear and nonlinear analysis of airflow recordings to help in sleep apnoea–hypopnoea syndrome diagnosis

This paper focuses on the analysis of single-channel airflow (AF) signal to help in sleep apnoea-hypopnoea syndrome (SAHS) diagnosis. The respiratory rate variability (RRV) series is derived from AF by measuring time between consecutive breathings. A set of statistical, spectral and nonlinear features are extracted from both signals. Then, the forward stepwise logistic regression (FSLR) procedure is used in order to perform feature selection and classification. Three logistic regression (LR) models are obtained by applying FSLR to features from AF, RRV and both signals simultaneously. The diagnostic performance of single features and LR models is assessed and compared in terms of sensitivity, specificity, accuracy and area under the receiver-operating characteristics curve (AROC). The highest accuracy (82.43%) and AROC (0.903) are reached by the LR model derived from the combination of AF and RRV features. This result suggests that AF and RRV provide useful information to detect SAHS.

Nonlinear measure of synchrony between blood oxygen saturation and heart rate from nocturnal pulse oximetry in obstructive sleep apnoea syndrome

This study focuses on analysis of the relationship between changes in blood oxygen saturation (SaO(2)) and heart rate (HR) recordings from nocturnal pulse oximetry (NPO) in patients suspected of suffering from obstructive sleep apnoea (OSA) syndrome. Two different analyses were developed: a classical frequency analysis based on the magnitude squared coherence (MSC) and a nonlinear analysis by means of a recently developed measure of synchrony, the cross-approximate entropy (cross-ApEn). A data set of 187 subjects was studied. We found significantly higher correlation and synchrony between oximetry signals from OSA positive patients compared with OSA negative subjects. We assessed the diagnostic ability to detect OSA syndrome of both the classical and nonlinear approaches by means of receiver operating characteristic (ROC) analyses with tenfold cross-validation. The nonlinear measure of synchrony significantly improved the results obtained with classical MSC: 69.2% sensitivity, 90.9% specificity and 78.1% accuracy were reached with MSC, whereas 83.7% sensitivity, 84.3% specificity and 84.0% accuracy were obtained with cross-ApEn. Our results suggest that the use of nonlinear measures of synchrony could provide essential information from oximetry signals, which cannot be obtained with classical spectral analysis.

The classification of oximetry signals using Bayesian neural networks to assist in the detection of obstructive sleep apnoea syndrome.

In the present study, multilayer perceptron (MLP) neural networks were applied to help in the diagnosis of obstructive sleep apnoea syndrome (OSAS). Oxygen saturation (SaO(2)) recordings from nocturnal pulse oximetry were used for this purpose. We performed time and spectral analysis of these signals to extract 14 features related to OSAS. The performance of two different MLP classifiers was compared: maximum likelihood (ML) and Bayesian (BY) MLP networks. A total of 187 subjects suspected of suffering from OSAS took part in the study. Their SaO(2) signals were divided into a training set with 74 recordings and a test set with 113 recordings. BY-MLP networks achieved the best performance on the test set with 85.58% accuracy (87.76% sensitivity and 82.39% specificity). These results were substantially better than those provided by ML-MLP networks, which were affected by overfitting and achieved an accuracy of 76.81% (86.42% sensitivity and 62.83% specificity). Our results suggest that the Bayesian framework is preferred to implement our MLP classifiers. The proposed BY-MLP networks could be used for early OSAS detection. They could contribute to overcome the difficulties of nocturnal polysomnography (PSG) and thus reduce the demand for these studies.

Applying Neural Network Classifiers in the Diagnosis of the Obstructive Sleep Apnea Syndrome from Nocturnal Pulse Oximetric Recordings

The aim of this study was to assess the ability of neural networks as an assistant tool for the diagnosis of the obstructive sleep apnea syndrome (OSAS). A total of 187 subjects suspected of suffering from OSAS (111 with a positive diagnosis of OSAS and 76 with a negative diagnosis of OSAS) took part in the study. The initial population was divided into training, validation and test sets for deriving and testing our neural classifiers. Our method was based on spectral and nonlinear features extracted from overnight arterial oxygen saturation (SaO2) recordings. A seven-element input vector was used for patient classification. We selected four spectral features from the estimated power spectral density (PSD) of SaO2. In addition, three input features were computed from non-linear analysis of SaO2. Two neural classifiers were assessed: the multilayer perceptron (MLP) network and the radial basis function (RBF) network. The RBF classifier provided the best diagnostic performance with an accuracy of 86.3% (89.9% sensitivity and 81.1% specificity).

Approximate Entropy from Overnight Pulse Oximetry for the Obstructive Sleep Apnea Syndrome

The aim of this preliminary study was to asses whether a time series analysis from overnight pulse oximetry by means of approximate entropy (ApEn) could yield essential information on the diagnosis of obstructive sleep apnea (OSA) syndrome. We analyzed the oxygen saturation (SaO2) signals of 74 patients (44 with a positive diagnosis of OSA and 30 with a negative diagnosis of OSA) by means of ApEn, which quantified the regularity (or complexity) of time series. Results showed that recurrence of apnea events in patients with OSA determined a significant increase in ApEn values with a mean plusmnstandard deviation (SD) of 1.07 plusmn 0.30. A mean plusmn SD ApEn value of 0.47 plusmn 0.25 was estimated in patients without OSA. We obtained an area under the ROC curve of 0.94. The optimum threshold was selected at 0.81, where we achieved a 79.5% sensitivity and 90% specificity. Further analyses are necessary with new and larger data set to test the potential value of our methodology prospectively

Classification Methods from Heart Rate Variability to Assist in SAHS Diagnosis

The aim of this study is to analyze different feature classification methods applied to heart rate variability (HRV) signals in order to help in sleep apnea-hypopnea syndrome (SAHS) diagnosis. A total of 240 recordings from patients suspected of suffering from SAHS were available. This initial dataset was divided into training set (96 subjects) and test set (144 subjects). For this study, spectral and nonlinear features have been extracted. Spectral characteristics were obtained from the power spectral density (PSD) from HRV records. On the other hand, the nonlinear features were obtained from HRV records in the time domain. Afterwards, some features were selected automatically by forward stepwise logistic regression (FSLR). We constructed two classifiers based on logistic regression (LR) and support vector machines (SVMs) with the selected features. Our results suggest that there are significant differences in various spectral and nonlinear parameters between SAHS positive and SAHS negative groups. The highest sensitivity, specificity and accuracy values were reached by the SVMs classifier: 70.8%, 79.2% and 73.6%, respectively. Results showed that feature selection of optimumcharacteristics from HRV signals could be useful to assist in SAHS diagnosis.

Obstructive Sleep Apnea Detection Using Clustering Classification of Nonlinear Features from Nocturnal Oximetry

This study is focused on the classification of patients suspected of suffering from obstructive sleep apnea (OSA) by means of cluster analysis. We assessed the diagnostic ability of three clustering algorithms: k-means, hierarchical and fuzzy c-means (FCM). Nonlinear features of blood oxygen saturation (SaO2) from nocturnal oximetry were used as inputs to the clustering methods. Three nonlinear methods were used: approximate entropy (ApEn), central tendency measure (CTM) and Lempel-Ziv (LZ) complexity. A population of 74 subjects (44 OSA positive and 30 OSA negative) was studied. 90.5%, 87.8% and 86.5% accuracies were reached with k-means, hierarchical and FCM algorithms, respectively. The diagnostic accuracy values improved those obtained with each nonlinear method individually. Our results suggest that nonlinear analysis and clustering classification could provide useful information to help in the diagnosis of OSA syndrome.