Obstructive Sleep Apnea in Women: Study of Speech and Craniofacial Characteristics

Abstract

BackgroundObstructive sleep apnea (OSA) is a common sleep disorder characterized by frequent cessation of breathing lasting 10 seconds or longer. The diagnosis of OSA is performed through an expensive procedure, which requires an overnight stay at the hospital. This has led to several proposals based on the analysis of patients’ facial images and speech recordings as an attempt to develop simpler and cheaper methods to diagnose OSA.ObjectiveThe objective of this study was to analyze possible relationships between OSA and speech and facial features on a female population and whether these possible connections may be affected by the specific clinical characteristics in OSA population and, more specifically, to explore how the connection between OSA and speech and facial features can be affected by gender.MethodsAll the subjects are Spanish subjects suspected to suffer from OSA and referred to a sleep disorders unit. Voice recordings and photographs were collected in a supervised but not highly controlled way, trying to test a scenario close to a realistic clinical practice scenario where OSA is assessed using an app running on a mobile device. Furthermore, clinical variables such as weight, height, age, and cervical perimeter, which are usually reported as predictors of OSA, were also gathered.Acoustic analysis is centered in sustained vowels. Facial analysis consists of a set of local craniofacial features related to OSA, which were extracted from images after detecting facial landmarks by using the active appearance models. To study the probable OSA connection with speech and craniofacial features, correlations among apnea-hypopnea index (AHI), clinical variables, and acoustic and facial measurements were analyzed.ResultsThe results obtained for female population indicate mainly weak correlations (r values between .20 and .39). Correlations between AHI, clinical variables, and speech features show the prevalence of formant frequencies over bandwidths, with F2/i/ being the most appropriate formant frequency for OSA prediction in women. Results obtained for male population indicate mainly very weak correlations (r values between .01 and .19). In this case, bandwidths prevail over formant frequencies. Correlations between AHI, clinical variables, and craniofacial measurements are very weak.ConclusionsIn accordance with previous studies, some clinical variables are found to be good predictors of OSA. Besides, strong correlations are found between AHI and some clinical variables with speech and facial features. Regarding speech feature, the results show the prevalence of formant frequency F2/i/ over the rest of features for the female population as OSA predictive feature. Although the correlation reported is weak, this study aims to find some traces that could explain the possible connection between OSA and speech in women. In the case of craniofacial measurements, results evidence that some features that can be used for predicting OSA in male patients are not suitable for testing female population.

Assessment of cephalometric parameters and correlation with the severity of the obstructive sleep apnea syndrome

“…For instance, Lee et al reported that OSAS patients often exhibit broader and flatter mid- and lower-thirds of the face, accompanied by reduced maxillary and mandibular lengths [ 45 ]. Similarly, Tyan et al identified significant correlations between craniofacial measurements and the severity of OSAS [ 46 ].…”

Craniofacial morphology in patients with obstructive sleep apnea: cephalometric evaluation

“…Craniofacial soft tissue evaluation is another important aspect. 31 Many authors evaluated OSA patients by using photographic evaluation or the 3D surface scanning of the face. 32 , 33 Lee et al 32 suggested that patients with OSA showed a wider and flatter mid-third and lower-third of the face.…”

“…Tyan et al showed a significant correlation between craniofacial measurements (i.e., cervico-mental contour ratio, Face-width ratio, tragion-ramus-stomion angle) and AHI in OSA patients. 31 Liu et al described the craniofacial and cephalometric parameters observed in OSA patients, and their influence in OSA treatment with mandibular advancement devices. 34 The authors suggested two types of craniofacial and soft tissue shape of OSA patients: subjects with a forward maxilla, a small oropharynx, less erupted maxillary molars, small incisor overjet, and a small soft palate, and patients with maxilla retrusion, a larger oropharynx, a larger soft palate, and over-erupted maxillary molars.…”

Prediction of obstructive sleep apnea using facial landmarks

“…In the first approach, using the existing training dataset a statistical model of the face is generated to fit test images. This approach, which is used in Tyan et al (2017) as an automatic annotation to predict OSA, has limitations in dealing with variations of the images (scale, pose, illumination, etc). In the second approach, face landmarks are localized by solving the regression problem which relates the features of the training datasets and their associated landmarks.…”

“…Such quantity provides a standard platform to evaluate the performance of classifications. In Tyan et al (2017) the same set of features and landmarks as Espinoza-Cuadros et al (2015) were automatically generated and used to predict OSA from facial features for female subjects, and a correlation between those features and AHI was shown. Although Espinoza-Cuadros et al (2015) and Tyan et al (2017) used the same landmarks, it is difficult to compare the performance of the automatic versus manual landmarking processes as different datasets were used.…”