Predicting Treatment Outcomes in Obstructive Sleep Apnea: A Distribution-based Spectral Analysis of Low-Sampled Snoring Vibrations
Bibliographic record
Abstract
Obstructive sleep apnea (OSA) is a prevalent condition characterized by complete (apnea) or partial (hypopnea) reductions in airflow due to a collapsed upper airway during sleep. Oral appliances, which reposition the lower jaw or tongue forward to maintain an open airway, are commonly used for OSA treatment. A major advantage of oral appliances over other treatment options such as positive airway pressure machines is a higher adherence to treatment. However, sleep physicians are hesitant to prescribe oral appliances since it is hard to predict who would respond to this treatment. Previous studies have explored invasive techniques like drug-induced sleep endoscopy (DISE) and awake nasendoscopy, as well as clinical tools such as polysomnography-based sleep phenotyping, to predict oral appliance treatment success. However, these methods require clinical expertise and are challenging for patients. In this study, we investigated the feasibility of using snoring vibrations recorded by a portable at-home OSA test device to predict the effectiveness of mandibular advancement devices, a common type of oral appliance. Snoring vibrations were recorded in 20 patients over a 5-month follow-up period. Our findings highlight that by utilizing distribution-based spectral features extracted solely from snoring vibrations and employing machine learning techniques along with feature selection methods, we can predict the efficacy of mandibular advancement device with an accuracy of 90% using leave-one-subject-out cross-validation. This approach offers a non-invasive and patient-friendly alternative for assessing the efficacy of oral appliances, which can aid sleep physicians in making informed treatment decisions.
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) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 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".