Obstructive sleep apnea detection during wakefulness: a comprehensive methodological review.

Obstructive sleep apnea (OSA) is a chronic condition affecting up to 1 billion people, globally. Despite this spread, OSA is still thought to be underdiagnosed. Lack of diagnosis is largely attributed to the high cost, resource-intensive, and time-consuming nature of existing diagnostic technologies during sleep. As individuals with OSA do not show many symptoms other than daytime sleepiness, predicting OSA while the individual is awake (wakefulness) is quite challenging. However, research especially in the last decade has shown promising results for quick and accurate methodologies to predict OSA during wakefulness. Furthermore, advances in machine learning algorithms offer new ways to analyze the measured data with more precision. With a widening research outlook, the present review compares methodologies for OSA screening during wakefulness, and recommendations are made for avenues of future research and study designs.

A comparison of regularized logistic regression and random forest machine learning models for daytime diagnosis of obstructive sleep apnea.

A major challenge in big and high-dimensional data analysis is related to the classification and prediction of the variables of interest by characterizing the relationships between the characteristic factors and predictors. This study aims to assess the utility of two important machine-learning techniques to classify subjects with obstructive sleep apnea (OSA) using their daytime tracheal breathing sounds. We evaluate and compare the performance of the random forest (RF) and regularized logistic regression (LR) as feature selection tools and classification approaches for wakefulness OSA screening. Results show that the RF, which is a low-variance committee-based approach, outperforms the regularized LR in terms of blind-testing accuracy, specificity, and sensitivity with 3.5%, 2.4%, and 3.7% improvement, respectively. However, the regularized LR was found to be faster than the RF and resulted in a more parsimonious model. Consequently, both the RF and regularized LR feature reduction and classification approaches are qualified to be applied for the daytime OSA screening studies, depending on the nature of data and applications' purposes. Graphical Abstract.

Acoustic characterization of upper airway variations from wakefulness to sleep with respect to obstructive sleep apnea.

The upper airway (UA) is in general thicker and narrower in obstructive sleep apnea (OSA) population than in normal. Additionally, the UA changes during sleep are much more in the OSA population. The UA changes can alter the tracheal breathing sound (TBS) characteristics. Therefore, we hypothesize the TBS changes from wakefulness to sleep are significantly correlated to the OSA severity; thus, they may represent the physiological characteristics of the UA. To investigate our hypothesis, we recorded TBS of 18 mild-OSA (AHI < 15) and 22 moderate/severe-OSA (AHI > 15) during daytime (wakefulness) and then during sleep. The power spectral density (PSD) of the TBS was calculated and compared within the two OSA groups and between wakefulness and sleep. The average PSD of the mild-OSA group in the low-frequency range (< 280 Hz) was found to be decreased significantly from wakefulness to sleep (p-value < 10-4). On the other hand, the average PSD of the moderate/severe-OSA group in the high-frequency range (> 900 Hz) increased marginally significantly from wakefulness to sleep (p-value < 9 × 10-3). Our findings show that the changes in spectral characteristics of TBS from wakefulness to sleep correlate with the severity of OSA and can represent physiological variations of UA. Therefore, TBS analysis has the potentials to assist with diagnosis and clinical management decisions in OSA patients based on their OSA severity stratification; thus, obviating the need for more expensive and time-consuming sleep studies. Graphical abstract Tracheal breathing sound (TBS) changes from wakefulness to sleep and their correlation with Obstructive sleep apnea (OSA) were investigated in individuals with different levels of OSA severity. We also assessed the classification power of the spectral characteristics of these TBS for screening purposes. Consequently, we analyzed and compared spectral characteristics of TBS recorded during wakefulness (a combination of mouth and nasal TBS) to those during sleep for mild and moderate/severe OSA groups.

Regularized logistic regression for obstructive sleep apnea screening during wakefulness using daytime tracheal breathing sounds and anthropometric information.

Obstructive sleep apnea (OSA) is a prevalent health problem. Developing a technology for quick OSA screening is momentous. In this study, we used regularized logistic regression to predict the OSA severity level of 199 individuals (116 males) with apnea/hypopnea index (AHI) ≥ 15 (moderate/severe OSA) and AHI < 5 (non-OSA) using their tracheal breathing sounds (TBS) recorded during daytime, while they were awake. The participants were guided to breathe through their nose, and then through their mouth at their deep breathing rate. The least absolute shrinkage and selection operator (LASSO) feature selection approach was used to select the discriminative features from the power spectra of the TBS and the anthropometric information. Using a five-fold cross-validation procedure, five different training sets and their corresponding blind-testing sets were formed. The average blind-testing classification accuracy over the five different folds was found to be 79.3% ± 6.1 with the sensitivity (specificity) of 82.2% ± 7.2% (75.8% ± 9.9%). The accuracy for the entire dataset was found to be 81.1% with sensitivity (specificity) of 84.4% (77.0%). The feature selection and classification procedures were intelligible and fast. The selected features were physiologically meaningful. Overall, the results show that TBS analysis can be used as a quick and reliable prediction of the presence and severity of OSA during wakefulness without a sleep study. Graphical abstract Wakefulness screening of obstructive sleep apnea using tracheal breathing sounds and anthropometric information by means of regularized logistic regression with the least absolute shrinkage and selection operator approach for feature selection and classification.