Towards an Accessible Speech-based Obstructive Sleep Apnea Screening Tool for Underserved Populations
Bibliographic record
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.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.002 | 0.012 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.002 | 0.001 |
| Open science | 0.001 | 0.002 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.005 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".