Computational analysis of airflow dynamics for predicting collapsible sites in the upper airways: machine learning approach.

Obstructive sleep apnea (OSA) is a common sleep breathing disorder. With the use of computational fluid dynamics (CFD), this study provides a quantitative standard for accurate diagnosis and effective surgery based on the investigation of the relationship between airway geometry and aerodynamic characteristics. Based on computed tomography data from patients having normal geometry, 4 major geometric parameters were selected and a total of 160 idealized cases were modeled and simulated. We created a predictive model using Gaussian process regression (GPR) through a data set obtained through numerical method. The results demonstrated that the mean accuracy of the overall GPR model was ~72% with respect to the CFD results for the realistic upper airway model. A support vector machine model was also used to identify the degree of OSA symptoms in patients as normal-mild and moderate and severe. We achieved an accuracy of 82.5% with the training data set and an accuracy of 80% with the test data set.NEW & NOTEWORTHY There have been many studies on the analysis of obstructive sleep apnea (OSA) through computational fluid dynamics and finite element analysis. However, these methods are not useful for practical medical applications because they have limited information for OSA symptom. This study employs the machine learning algorithm to predict flow characteristics quickly and to determine the symptoms of the patient's OSA. The overall Gaussian process regression model's mean accuracy was ~72%, and the accuracy for the classification of OSA was >80%.

Computational analysis of airflow dynamics for predicting collapsible sites in the upper airways: a preliminary study.

The present study aimed to detail the relationship between the flow and structure characteristics of the upper airways and airway collapsibility in obstructive sleep apnea. Using a computational approach, we performed simulations of the flow and structure of the upper airways in two patients having different facial morphologies: retruding and protruding jaws, respectively. First, transient flow simulation was performed using a prescribed volume flow rate to observe flow characteristics within upper airways with an unsteady effect. In the retruding jaw, the maximum magnitude of velocity and pressure drop with velocity shear and vortical motion was observed at the oropharyngeal level. In contrast, in the protruding jaw, the overall magnitude of velocity and pressure was relatively small. To identify the cause of the pressure drop in the retruding jaw, pressure gradient components induced by flow were examined. Of note, vortical motion was highly associated with pressure drop. Structure simulation was performed to observe the deformation and collapsibility of soft tissue around the upper airways using the surface pressure obtained from the flow simulation. At peak flow rate, the soft tissue of the retruding jaw was highly expanded, and a collapse was observed at the oropharyngeal and epiglottis levels. NEW & NOTEWORTHY Aerodynamic characteristics have been reported to correlate with airway occlusion. However, a detailed mechanism of the phenomenon within the upper airways and its impact on airway collapsibility remain poorly understood. This study provides in silico results for aerodynamic characteristics, such as vortical structure, pressure drop, and exact location of the obstruction using a computational approach. Large deformation of soft tissue was observed in the retruding jaw, suggesting that it is responsible for obstructive sleep apnea.