We have previously reported a system suitable for detection and classification of sleep apnea syndromes. This paper reports the results of the clinical evaluation of the proposed system. In the current implementation, the system uses breathing signals: nasal flow, thorax movement, and abdomen movement. The detection part of the system uses only the nasal flow signal to detect apnea employing two engines used in series. It then feeds segments labeled as abnormal to the classification part of the system, which uses the center of gravity of each segment to determine the type of abnormality: obstructive, central or hypopnea. In comparison to other systems, this implementation can be shown to be simpler and more accurate. When the low implementation cost is taken into consideration, the proposed system has a substantial potential for being used as a screening device.
Background
Obstructive sleep apnea (OSA) is a common condition in the general population that is highly correlated to obesity, and it is associated with major cardiovascular morbidity and mortality. In Egypt, obesity rates are known to be high; however, OSA remains largely under-diagnosed, and data on its current magnitude is very scarce. Thus, the aims of the study were to identify the percentage of OSA in a large sample of patients referred for polysomnography and to determine the effect of different demographic data on the severity of the disease.
Results
This retrospective study included 1012 patients. Medical data were reviewed by sleep specialists. The correlation between age, body mass index (BMI), and neck circumference (NC) with apnea hypoapnea index (AHI) was explored. Also, gender differences were analyzed. A total of 838 patients (81% males, 19% females) were diagnosed with OSA. Patients with mild, moderate, and severe OSA were 204 (24%), 146 (17%), and 488 (58%), respectively. Females were older than males (58.87 ± 10.25 versus 54.39 ± 22.96, p = 0.001) and BMI was not significantly different between both sexes (34.18 ± 13.53 versus 36.73 ± 23.25, p = 0.07), but NC was higher in men (43.56 ± 5.3 versus 39.34 ± 4.41, p = 0.001). AHI was significantly increased in men compared to women (47.97 ± 31.22 versus 37.95 ± 31.72, p = 0.001) and severe OSA was commonly diagnosed in men than women (p = 0.001). A positive significant correlation was found between BMI, NC with AHI, arousal index, average SpO2, and desaturation index.
Conclusion
OSA is highly prevalent among our patients. Additionally, BMI and NC independently affected the severity of their disease.
The aim of this work is to develop an automatic system that can be used as an assistant tool for the detection and diagnosis of different kinds of sleep Apnea (Obstructive, Hypopnea and Central Apnea, respectively). Three nonlinear techniques were used for feature extraction: Central tendency measures (CTM), Lempel-Ziv complexity (LZC) and Approximate Entropy (ApEn) for oxygen saturation signals (SaO2). A statistical Comparison using (t -test) was performed for comparing the population mean of normal group with each of the Sleep Apnea groups for the nonlinear parameters. Three Hidden Markov Models (HMMs), based on Baum-Welch algorithm were proposed to estimate the optimal number of the parameters. The results have showed that the use of HMM and the nonlinear features gave promising results used for classifying Sleep Apnea diseases.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.