A diagnostic system for sleep apnea based on oxygen saturation and RR intervals obtained from the EKG (electrocardiogram) is proposed with the goal to detect and quantify minute long segments of sleep with breathing pauses. We measured the discriminative capacity of combinations of features obtained from RR series and oximetry to evaluate improvements of the performance compared to oximetry-based features alone. Time and frequency domain variables derived from oxygen saturation (SpO2) as well as linear and non-linear variables describing the RR series have been explored in recordings from 70 patients with suspected sleep apnea. We applied forward feature selection in order to select a minimal set of variables that are able to locate patterns indicating respiratory pauses. Linear discriminant analysis (LDA) was used to classify the presence of apnea during specific segments. The system will finally provide a global score indicating the presence of clinically OPEN ACCESSEntropy 2015, 17 2933 significant apnea integrating the segment based apnea detection. LDA results in an accuracy of 87%; sensitivity of 76% and specificity of 91% (AUC = 0.90) with a global classification of 97% when only oxygen saturation is used. In case of additionally including features from the RR series; the system performance improves to an accuracy of 87%; sensitivity of 73% and specificity of 92% (AUC = 0.92), with a global classification rate of 100%.

Our contribution focuses on the characterization of sleep apnea from a cardiac rate point of view, using Recurrence Quantification Analysis (RQA), based on a Heart Rate Variability (HRV) feature selection process. Three parameters are crucial in RQA: those related to the embedding process (dimension and delay) and the threshold distance. There are no overall accepted parameters for the study of HRV using RQA in sleep apnea. We focus on finding an overall acceptable combination, sweeping a range of values for each of them simultaneously. Together with the commonly used RQA measures, we include features related to recurrence times, and features originating in the complex network theory. To the best of our knowledge, no author has used them all for sleep apnea previously. The best performing feature subset is entered into a Linear Discriminant classifier. The best results in the “Apnea-ECG Physionet database” and the “HuGCDN2014 database” are, according to the area under the receiver operating characteristic curve, 0.93 (Accuracy: 86.33%) and 0.86 (Accuracy: 84.18%), respectively. Our system outperforms, using a relatively small set of features, previously existing studies in the context of sleep apnea. We conclude that working with dimensions around 7–8 and delays about 4–5, and using for the threshold distance the Fixed Amount of Nearest Neighbours (FAN) method with 5% of neighbours, yield the best results. Therefore, we would recommend these reference values for future work when applying RQA to the analysis of HRV in sleep apnea. We also conclude that, together with the commonly used vertical and diagonal RQA measures, there are newly used features that contribute valuable information for apnea minutes discrimination. Therefore, they are especially interesting for characterization purposes. Using two different databases supports that the conclusions reached are potentially generalizable, and are not limited by database variability.

We investigated the hypothesis that asthmatic patients have an increased cholinergic tone by measuring tracheobronchial cross-sectional areas during transient voluntary apnea. This allowed us to assess bronchomotor tone without the influence of changes in lung recoil or lung volume. Three groups of subjects with potentially different levels of tracheobronchial tone were studied: 14 healthy volunteers (N), 18 stable asthmatic patients (A), and 10 double lung transplant recipients (T). Using the acoustic reflection technique, we measured changes in tracheobronchial cross-sectional areas during short periods (5 to 10 s) of voluntary apnea. In a subset of subjects, studies were repeated before and after the inhalation of the muscarinic antagonist ipratropium. During breath-holding, glottis and extrathoracic trachea remained unchanged but intrathoracic tracheal area decreased by 30 +/- 8% (mean +/- standard error of the mean) in N, by 27 +/- 3% in A, and by 9 +/- 4% in the T group. Bronchial areas decreased by 24 +/- 8% in N, by 45 +/- 3% in A, and by 10 +/- 4% in T. These differences among groups were statistically significant at the tracheal and bronchial levels (p < 0.05), and ipratropium significantly inhibited this airway constriction (p < 0.05) only in the asthmatic group. Assuming that changes in cross-sectional airway areas voluntary apnea reflect airway tone, these results support the view that in humans this tone is mainly vagally controlled and that it is significantly increased in asthmatic compared with nonasthmatic subjects.

The aim of this investigation was to evaluate the contribution of cephalometry to a statistical model integrating clinical, physical, and oximetric variables, to reduce demands for polysomnographies. Two hundred and twenty-five consecutive patients that had been referred to the sleep clinic for suspected obstructive sleep apnea (OSA) were studied. The clinical assessment of all patients consisted of a sleep related questionnaire, the Epworth sleepiness scale, and a physical examination. In addition, they all underwent spirometry, cephalometry, and a full polysomnography. The clinical variables related with OSA were questions concerning witnessing of apneas by bed partners, intensity of snoring, a history of hypertension, and nocturia. A significant relation was also found with score on the Epworth scale, sex, age, body mass index, neck and waist circumferences, total number and frequency of oxygen desaturations, and the lowest oxygen saturation value. Significant cephalometric measurements were: the linear distance from gonion to gnathion, from the hyoid bone to the mandibular plane, and from the posterior nasal spine to the tip of the soft palate, and the thickness of the uvula as well. A statistical model was built to estimate a patient's probability of having OSA based on clinical variables, physical examination, pulse oximetry, and cephalometry. The validation of this model demonstrated a remarkable ability in reducing the number of polysomnographic studies. We conclude that cephalometry combined with clinical variables, physical examination, and nocturnal oximetry is useful in the diagnosis of OSA and enables the sparing of a considerable number of polysomnographies.

No abstract