Computerized respiratory sounds in paediatrics: A systematic review
Bibliographic record
Abstract
Diagnosing and monitoring of children with respiratory disorders is often challenging. Respiratory sounds (RS) are simple, non-invasive and universally available measures that are directly related to movement of air, within the tracheobronchial tree. Thus, RS may be valuable indicators of respiratory health, their characteristics in the paediatric population are scattered in the literature and not systematized. Systematically review the different acoustic RS properties in healthy children and in children with different respiratory disorders. Methods: MEDLINE, EMBASE, AMED and CINHAL databases were searched on Sept 2020. One author extracted data and two independently assessed the quality of the articles using the National Heart Lung and Blood Institute quality assessment tool. Twenty-eight studies were included with a total 2032 participants (44% with a respiratory condition, such as asthma, bronchiolitis, cystic fibrosis, presence of wheezing and non-specified low respiratory tract infections). A high heterogeneity in the procedures, outcomes and outcome measures used was found. Healthy participants showed lower values of F50 (from 194 ± 26 to 521 ± 18Hz) than those with asthma (from 140 ± 8 to 769 ± 85Hz) or bronchiolitis (from 100 to 80Hz). F50 tend to increase with provocation tests (136 ± 9 to 909 ± 81Hz) and decrease with treatments (128 ± 6 to 781 ± 57Hz). Wheeze rates ranged from 0 to 24.7 ± 25% on asthmatic participants. Crackles findings ranged from 6% on people with recurrent wheezing to 30.8% in middle lobe atelectasis. RS show different acoustic properties in healthy children vs with different respiratory disorders and thus may be useful in the diagnostic and monitoring on paediatrics.
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 | 0.003 | 0.019 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.006 | 0.005 |
| Bibliometrics | 0.009 | 0.010 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.002 | 0.001 |
| Insufficient payload (model declined to judge) | 0.008 | 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".