Dissociation between objectively quantified snoring and sleep quality.

BACKGROUND: The impact of simple snoring on sleep structure and sleepiness has not been well described. In several studies, self-reported snoring was associated with increased daytime sleepiness. However, most studies did not distinguish patients with simple snoring from those with coexisting obstructive sleep apnea (OSA) using objective measures. We therefore evaluated the relationship between objectively measured snoring and both sleep structure and daytime sleepiness in patients with no or mild OSA. METHODS: Subjects referred for suspected sleep disorders underwent polysomnography (PSG) during which breath sounds were recorded by a microphone. Those with an apnea-hypopnea index (AHI) <15/h were analyzed. Individual snores were identified by a computer algorithm, from which the snore index (SI) was calculated as the number of snores/h of sleep. Sleep stages and arousals were quantified. Daytime sleepiness was evaluated using the Epworth Sleepiness Scale (ESS) score. RESULTS: 74 (35 males) subjects were included (age, mean ±â€¯SD: 46.4 ±â€¯15.3 years and body mass index: 29.8 ±â€¯7.0 kg/m2). The mean SI was 266 ±â€¯243 snores/h. Subjects were categorized according to their SI into 3 tertiles: SI < 100, between 100-350, and >350. No sleep structure indeces, arousals, or ESS score differed among SI tertiles (p > 0.13). There was no correlation between SI and any of these variables (p > 0.29). In contrast, the AHI was significantly related to frequency of arousals (r = 0.23, p = 0.048). CONCLUSIONS: These findings suggest that simple snoring assessed objectively is not related to indices of sleep structure or subjective sleepiness.

Diagnosis of Obstructive Sleep Apnea during Wakefulness Using Upper Airway Negative Pressure and Machine Learning.

Background and Rational: Obstructive Sleep Apnea (OSA) is a common disorder, affecting almost 10% of adults, but very underdiagnosed. This is largely due to limited access to overnight sleep testing using polysomnography (PSG). Our goal was to distinguish OSA from healthy individual using a simple maneuver during wakefulness in combination with machine learning methods. Methods: Participants have undergone an overnight PSG to determine their ground truth OSA severity. Separately, they were asked to breathe through a nasal mask or a mouth piece through which negative pressure (NP) was applied, during wakefulness. Airflow waveforms were acquired and several features were extracted and used to train various classifiers to predict OSA. Results and Discussion: The performance of each classifier and experimental setup was calculated. The best results were obtained using Random Forest classifier for distinguishing OSA from healthy individuals with a very good area under the curve of 0.80. To the best of our knowledge, this is the first study to deploy machine learning and NP with promising path to diagnose OSA during wakefulness.