Bibliographic record
Abstract
Sleep apnea is a chronic respiratory disorder that is characterized by recurrent reductions in breathing during sleep. The gold standard diagnosis of sleep apnea is an overnight sleep study with polysomnography (PSG), which is expensive and time-consuming. Furthermore, questionnaires are used for screening of sleep apnea during wakefulness, but they are highly subjective and do not provide the assessment of pharyngeal airway anatomy. This thesis presents acoustic technologies to diagnose sleep apnea during sleep and to assess the pharyngeal airway dimension during wakefulness. To diagnose sleep apnea during sleep, we recruited 69 individuals who underwent full-night PSG in the sleep laboratory. Simultaneously with PSG, we recorded the tracheal breathing sounds and respiratory-related movements with a microphone and an accelerometer, respectively. We developed a novel machine-learning algorithm utilizing random forest and logistic regression; and achieved 90% accuracy in detecting sleep apnea. We also identified each respiratory event with over 80% accuracy in patients with severe sleep apnea. Furthermore, we utilized deep convolutional networks to use breathing sounds and distinguish the two major sleep apnea types, obstructive and central events, with 84% accuracy. These algorithms can be used in a wearable device for monitoring sleep apnea. To assess the pharyngeal airway during wakefulness, we investigated vowel articulation and acoustic features of vowel sounds. To measure the pharyngeal airway effectively during vowel articulation, we used ultrasonography. We have shown that ultrasonography can be effectively used to measure the dimensions of the pharyngeal airway and the dimensions are different between individuals with and without sleep apnea. Furthermore, we have shown that patients with sleep apnea have had less variation in the pharyngeal airway dimension, which can be interpreted as less tongue movement than control groups while articulating vowels. Moreover, we have shown that the vowel sound features can estimate the pharyngeal airway dimension with high accuracy. These algorithms can be used for developing a vowel-based assessment of sleep apnea. Overall, the results of these studies showed the promise of breathing and vowel sounds to assess the pharyngeal airway and monitor sleep apnea.
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 | 0.001 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
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".