Snoring sounds’ statistical characteristics depend on anthropometric parameters
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
Snoring is common in people with obstructive sleep apnea (OSA). Although not every snorer has OSA or vice-versa, many studies attempt to use snoring sounds for classification of people into two groups of OSA and simple snorers. This paper discusses the relationship between snorers’ anthropometric parameters and statistical characteristics of snoring sound (SS) and also reports on classification accuracies of methods using SS features for screening OSA from simple snorers when anthropometric parameters are either matched or unmatched. Tracheal respiratory sounds were collected from 60 snorers simultaneously with full-night Polysomnography (PSG). Energy, formant frequency, Skewness and Kurtosis were calculated from the SS segments. We also defined and calculated two features: Median Bifrequency (MBF), and projected MBF (PMBF). The statistical relationship between the extracted features and anthropometric parameters such as height, Body Mass Index (BMI), age, gender, and Apnea-Hypopnea Index (AHI) were investigated. The results showed that the SS features were not only sensitive to AHI but also to height, BMI and gender. Next, we performed two experiments to classify patients with Obstructive Sleep Apnea (OSA) and simple snorers: Experiment A: a small group of participants (22 OSA and 6 simple snorers) with matched height, BMI, and gender were selected and classified using Na?ve Bayes classifier, and Experiment B: the same number of participants with unmatched height, BMI, and gender were chosen for classification. A sensitivity of 93.2% (87.5%) and specificity of 88.4% (86.3%) was achieved for the matched (unmatched) groups.
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.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.004 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| 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 it