Towards an Accessible Speech-based Obstructive Sleep Apnea Screening Tool for Underserved Populations

Download PDF
Open Webpage

Behrad Taghibeyglou, Alexander Chow, Parker Mclaurin, Oviga Yasokaran, Rene Adams, Majida Mohammed, Mandeep Singh, Najib Ayas, Sachin R. Pendharkar, Fernanda R. Almeida, Valeria Rac, Shumit Saha, Azadeh Yadollahi

Published: 2024, Last Modified: 12 Nov 2025EMBC 2024EveryoneRevisionsBibTeXCC BY-SA 4.0
Abstract: Obstructive sleep apnea (OSA) is a chronic respiratory disorder characterized by recurrent interruptions in breathing during sleep. OSA is highly prevalent, affecting 30-70% of people with chronic conditions like hypertension and substance use. The gold standard for clinical OSA diagnosis is the polysomnography (PSG) test, which is a rather cumbersome and expensive procedure, and accordingly can be quite inconvenient for patients. Additionally, patients often have to wait for a long time before they can undergo PSG. As a result, other alternatives for screening OSA have gained attention. For instance, speech is a cheap and accessible modality that shares similar anatomical structures that contribute to OSA. Previous studies have investigated the feasibility of speech recording during wakefulness for assessing the risk of OSA; however, most of the studies have been done in sleep clinics or hospitals in fully- or semi-supervised recording environments. Consequently, the generalizability of the developed algorithms is limited. People experiencing homelessness are specific group of patients who face several challenges accessing healthcare facilities, and due to the existence of OSA comorbidities, have high OSA prevalence. However, this population has never been included in studies related to speech and OSA. Therefore, in this study, for the first time, we demonstrated the difference in spectral speech characteristics of a small cohort (n=18) of people with and without OSA living in homeless shelters, in Toronto, Canada. We also investigated the effect of body posture on such differences and highlighted the potential differences during vowel articulation that can be used for developing an accessible speech-based OSA monitoring tool.