Acoustical analysis of the swallowing mechanism for diagnosis of dysphagia
Bibliographic record
Abstract
Swallowing dysfunction (dysphagia) is a common disorder in patients with neurological impairments, head/neck injuries or brain-stem stroke. The main objectives of this thesis were to use acoustical analysis of swallowing and breath sounds for 1) understanding the swallowing mechanism and the main cause of dysphagia, and 2) developing a noninvasive diagnostic technology to detect swallowing aspiration (the entry of bolus into airway); thus, identifying individuals at high risk of severe dysphagia. As the first objective of the study, swallowing mechanism modeling in two groups of healthy individuals and dysphagic patients (due to cerebral palsy or stroke) was approached by using two different assumptions to relate the swallowing sounds either to the pharyngeal response or to the neural activities that initiate the swallow. The results showed that the model with the assumption of neural activities as the cause of dysphagia was a better fit to the available data. As the second main objective of the study, we analyzed breathing and swallowing sounds of 50 dysphagic individuals during the fiberoptic endoscopic evaluation of swallowing (FEES) or the videofluoroscopic swallowing study (VFS). The results showed 91% sensitivity and 85% specificity in identifying patients with severe aspirations. Also, the algorithm was able to detect the silent aspiration among the swallows of each patient. The proposed methods led to development of a non-invasive and reliable diagnostic/screening tool as an aid to the clinical examination of swallowing. The proposed acoustic method can be performed at the patients’ bedside to determine the appropriate further assessment or a dietetic treatment; thus, reducing the health care cost by prioritizing the patients’ referrals to the VFS/FEES tests.
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 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.002 | 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".