Diagnosis of Pediatric Obstructive Sleep Apnea via Face Classification with Persistent Homology and Convolutional Neural Networks

Obstructive sleep apnea is a serious condition causing a litany of health problems especially in the pediatric population. However, this chronic condition can be treated if diagnosis is possible. The gold standard for diagnosis is an overnight sleep study, which is often unobtainable by many potentially su ff ering from this condition. Hence, we attempt to develop a fast noninvasive diagnostic tool by training a classifier on 2D and 3D facial images of a patient to recognize facial features associated with obstructive sleep apnea. In this comparative study, we consider both persistent homology and geometric shape analysis from the field of computational topology as well as con-volutional neural networks, a powerful method from deep learning whose success in image and specifically facial recognition has already been demonstrated by computer scientists. Keywords: obstructive sleep apnea, machine learning, persistent homology, shape analysis 1. Introduction Obstructive sleep apnea (OSA) is a chronic condition characterized by frequent episodes of upper airway collapse during sleep. Pediatric OSA is a serious health problem as even mild forms of untreated pediatric OSA can cause high blood pressure, changes to the heart, and challenging behaviors, or even alter the childs growth. Unlike adults, the symptoms of childhood-onset OSA are more varied and change with developmental age which creates di fficulties in both the diagnosis and patient management. Prevalence of OSA in children and adolescents is in the range of 1-5%. It is also believed to negatively influence school performance and learning potential. Prompt treatment is a necessity, but long wait times and delays in diagnosis are overly prevalent. The gold standard for diagnosis of pediatric OSA is by overnight polysomnography (PSG) in a hospital or sleep clinic. In many countries, access to PSG is severely limited, and many children do not have confirmation of the diagnosis before treatment. Consequently, some children who do not have OSA will undergo unnecessary surgery to remove their tonsils and adenoids while other children with serious OSA will go untreated. Thus, simple and accessible options to identify children with OSA are greatly needed. A possible simpler approach to diagnosis than PSG might be to examine the structure of a patient's face with the goal of identifying facial features that indicate a high risk for the presence of OSA. Face verification consists of representations of a patient's face that extract important features. A distance measure can be used to determine the similarities and dissimilarities between pairs of faces. Mathematically, the face features lie in a metric space, a space where the distance between two objects can be defined.