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

Achieving Better Understanding of Obstructive Sleep Apnea Treatment Effects on Cardiovascular Disease Outcomes through Machine Learning Approaches: A Narrative Review

Obstructive sleep apnea (OSA) affects almost a billion people worldwide and is associated with a myriad of adverse health outcomes. Among the most prevalent and morbid are cardiovascular diseases (CVDs). Nonetheless, randomized controlled trials (RCTs) of OSA treatment have failed to show improvements in CVD outcomes. A major limitation in our field is the lack of precision in defining OSA and specifically subgroups with the potential to benefit from therapy. Further, this has called into question the validity of using the time-honored apnea-hypopnea index as the ultimate defining criteria for OSA. Recent applications of advanced statistical methods and machine learning have brought to light a variety of OSA endotypes and phenotypes. These methods also provide an opportunity to understand the interaction between OSA and comorbid diseases for better CVD risk stratification. Lastly, machine learning and specifically heterogeneous treatment effects modeling can help uncover subgroups with differential outcomes after treatment initiation. In an era of data sharing and big data, these techniques will be at the forefront of OSA research. Advanced data science methods, such as machine-learning analyses and artificial intelligence, will improve our ability to determine the unique influence of OSA on CVD outcomes and ultimately allow us to better determine precision medicine approaches in OSA patients for CVD risk reduction. In this narrative review, we will highlight how team science via machine learning and artificial intelligence applied to existing clinical data, polysomnography, proteomics, and imaging can do just that.

The influence of mouth opening on pharyngeal pressure loss and its underlying mechanism: A computational fluid dynamic analysis

Objective: During inspiration, mechanical energy generated from respiratory muscle produces a negative pressure gradient to fulfill enough pulmonary ventilation. The pressure loss, a surrogate for energy loss, is considered as the portion of negative pressure without converting into the kinetic energy of airflow. Mouth opening (MO) during sleep is a common symptom in patients with obstructive sleep apnoea-hypopnea syndrome (OSAHS). This study aimed to evaluate the effects of mouth opening on pharyngeal pressure loss using computational fluid dynamics (CFD) simulation. Methods: A total of four subjects who were morphologically distinct in the pharyngeal characteristics based on Friedman tongue position (FTP) grades were selected. Upper airway computed tomography (CT) scan was performed under two conditions: Mouth closing (MC) and mouth opening, in order to reconstruct the upper airway models. computational fluid dynamics was used to simulate the flow on the two different occasions: Mouth closing and mouth opening. Results: The pharyngeal jet was the typical aerodynamic feature and its formation and development were different from mouth closing to mouth opening in subjects with different Friedman tongue position grades. For FTP I with mouth closing, a pharyngeal jet gradually formed with proximity to the velopharyngeal minimum area plane (plane_Amin). Downstream the plane_Amin, the jet impingement on the pharyngeal wall resulted in the frictional loss associated with wall shear stress (WSS). A rapid luminal expansion led to flow separation and large recirculation region, corresponding to the interior flow loss. They all contributed to the pharyngeal total pressure loss. While for FTP I with mouth opening, the improved velopharyngeal constriction led to smoother flow and a lower total pressure loss. For FTP IV, the narrower the plane_Amin after mouth opening, the stronger the jet formation and its impingement on the pharyngeal wall, predicting a higher frictional loss resulted from higher WSS. Besides, a longer length of the mouth opening-associated constant constrictive segment was another important morphological factor promoting frictional loss. Conclusion: For certain OSAHS patients with higher Friedman tongue position grade, mouth opening-related stronger jet formation, more jet breakdown and stronger jet flow separation might contribute to the increased pharyngeal pressure loss. It might require compensation from more inspiratory negative static pressure that would potentially increase the severity of OSAHS.

Anatomical determinants of upper airway collapsibility in obstructive sleep apnea: A systematic review and meta-analysis

Upper airway (UA) collapsibility is one of the key factors that determine the severity of obstructive sleep apnea (OSA). Interventions for OSA are aimed at reducing UA collapsibility, but selecting the optimal alternative intervention for patients who fail CPAP is challenging because currently no validated method predicts how anatomical changes affect UA collapsibility. The gold standard objective measure of UA collapsibility is the pharyngeal critical pressure (P_crit). A systematic literature review and meta-analysis were performed to identify the anatomical factors with the strongest correlation with P_crit. A search using the PRISMA methodology was performed on PubMed for English language scientific papers that correlated P_crit to anatomic variables and OSA severity as measured by the apnea-hypopnea index (AHI). A total of 29 papers that matched eligibility criteria were included in the quantitative synthesis. The meta-analysis suggested that AHI has only a moderate correlation with P_crit (estimated Pearson correlation coefficient r = 0.46). The meta-analysis identified four key anatomical variables associated with UA collapsibility, namely hyoid position (r = 0.53), tongue volume (r = 0.51), pharyngeal length (r = 0.50), and waist circumference (r = 0.49). In the future, biomechanical models that quantify the relative importance of these anatomical factors in determining UA collapsibility may help identify the optimal intervention for each patient. Many anatomical and structural factors such as airspace cross-sectional areas, epiglottic collapse, and palatal prolapse have inadequate data and require further research.

Diagnosis of obstructive sleep apnea with prediction of flow characteristics according to airway morphology automatically extracted from medical images: Computational fluid dynamics and artificial intelligence approach

BACKGROUND

Obstructive sleep apnea syndrome (OSAS) is being observed in an increasing number of cases. It can be diagnosed using several methods such as polysomnography.

OBJECTIVES

To overcome the challenges of time and cost faced by conventional diagnostic methods, this paper proposes computational fluid dynamics (CFD) and machine-learning approaches that are derived from the upper-airway morphology with automatic segmentation using deep learning.

METHOD

We adopted a 3D UNet deep-learning model to perform medical image segmentation. 3D UNet prevents the feature-extraction loss that may occur by concatenating layers and extracts the anteroposterior coordination and width of the airway morphology. To create flow characteristics of the upper airway training data, we analyzed the changes in flow characteristics according to the upper-airway morphology using CFD. A multivariate Gaussian process regression (MVGPR) model was used to train the flow characteristic values. The trained MVGPR enables the prompt prediction of the aerodynamic features of the upper airway without simulation. Unlike conventional regression methods, MVGPR can be trained by considering the correlation between the flow characteristics. As a diagnostic step, a support vector machine (SVM) with predicted aerodynamic and biometric features was used in this study to classify patients as healthy or suffering from moderate OSAS. SVM is beneficial as it is easy to learn even with a small dataset, and it can diagnose various flow characteristics as factors while enhancing the feature via the kernel function. As the patient dataset is small, the Monte Carlo cross-validation was used to validate the trained model. Furthermore, to overcome the imbalanced data problem, the oversampling method was applied.

RESULT

The segmented upper-airway results of the high-resolution and low-resolution models present overall average dice coefficients of 0.76±0.041 and 0.74±0.052, respectively. Furthermore, the classification accuracy, sensitivity, specificity, and F1-score of the diagnosis algorithm were 81.5%, 89.3%, 86.2%, and 87.6%, respectively.

CONCLUSION

The convenience and accuracy of sleep apnea diagnosis are improved using deep learning and machine learning. Further, the proposed method can aid clinicians in making appropriate decisions to evaluate the possible applications of OSAS.

Applications of artificial intelligence and machine learning in orthodontics: a scoping review

Introduction

This scoping review aims to provide an overview of the existing evidence on the use of artificial intelligence (AI) and machine learning (ML) in orthodontics, its translation into clinical practice, and what limitations do exist that have precluded their envisioned application.

Methods

A scoping review of the literature was carried out following the PRISMA-ScR guidelines. PubMed was searched until July 2020.

Results

Sixty-two articles fulfilled the inclusion criteria. A total of 43 out of the 62 studies (69.35%) were published this last decade. The majority of these studies were from the USA (11), followed by South Korea (9) and China (7). The number of studies published in non-orthodontic journals (36) was more extensive than in orthodontic journals (26). Artificial Neural Networks (ANNs) were found to be the most commonly utilized AI/ML algorithm (13 studies), followed by Convolutional Neural Networks (CNNs), Support Vector Machine (SVM) (9 studies each), and regression (8 studies). The most commonly studied domains were diagnosis and treatment planning—either broad-based or specific (33), automated anatomic landmark detection and/or analyses (19), assessment of growth and development (4), and evaluation of treatment outcomes (2). The different characteristics and distribution of these studies have been displayed and elucidated upon therein.

Conclusion

This scoping review suggests that there has been an exponential increase in the number of studies involving various orthodontic applications of AI and ML. The most commonly studied domains were diagnosis and treatment planning, automated anatomic landmark detection and/or analyses, and growth and development assessment.

Supplementary Information

The online version contains supplementary material available at 10.1186/s40510-021-00361-9.

Computational fluid dynamics modelling of human upper airway: A review

BACKGROUND AND OBJECTIVE

Human upper airway (HUA) has been widely investigated by many researchers covering various aspects, such as the effects of geometrical parameters on the pressure, velocity and airflow characteristics. Clinically significant obstruction can develop anywhere throughout the upper airway, leading to asphyxia and death; this is where recognition and treatment are essential and lifesaving. The availability of advanced computer, either hardware or software, and rapid development in numerical method have encouraged researchers to simulate the airflow characteristics and properties of HUA by using various patient conditions at different ranges of geometry and operating conditions. Computational fluid dynamics (CFD) has emerged as an efficient alternative tool to understand the airflow of HUA and in preparing patients to undergo surgery. The main objective of this article is to review the literature that deals with the CFD approach and modeling in analyzing HUA.

METHODS

This review article discusses the experimental and computational methods in the study of HUA. The discussion includes computational fluid dynamics approach and steps involved in the modeling used to investigate the flow characteristics of HUA. From inception to May 2020, databases of PubMed, Embase, Scopus, the Cochrane Library, BioMed Central, and Web of Science have been utilized to conduct a thorough investigation of the literature. There had been no language restrictions in publication and study design of the database searches. A total of 117 articles relevant to the topic under investigation were thoroughly and critically reviewed to give a clear information about the subject. The article summarizes the review in the form of method of studying the HUA, CFD approach in HUA, and the application of CFD for predicting HUA obstacle, including the type of CFD commercial software are used in this research area.

RESULTS

This review found that the human upper airway was well studied through the application of computational fluid dynamics, which had considerably enhanced the understanding of flow in HUA. In addition, it assisted in making strategic and reasonable decision regarding the adoption of treatment methods in clinical settings. The literature suggests that most studies were related to HUA simulation that considerably focused on the aspects of fluid dynamics. However, there is a literature gap in obtaining information on the effects of fluid-structure interaction (FSI). The application of FSI in HUA is still limited in the literature; as such, this could be a potential area for future researchers. Furthermore, majority of researchers present the findings of their work through the mechanism of airflow, such as that of velocity, pressure, and shear stress. This includes the use of Navier-Stokes equation via CFD to help visualize the actual mechanism of the airflow. The above-mentioned technique expresses the turbulent kinetic energy (TKE) in its result to demonstrate the real mechanism of the airflow. Apart from that, key result such as wall shear stress (WSS) can be revealed via turbulent kinetic energy (TKE) and turbulent energy dissipation (TED), where it can be suggestive of wall injury and collapsibility tissue to the HUA.