An accurate deep learning model for wheezing in children using real world data
Source check: Source checked. Not independent scientific confirmation.
Finding: In a prospective single-hospital cohort of 76 children, a 34-layer residual CNN with attention analyzed wheeze audio alongside clinical features; reported accuracy was 91.2% and AUC 0.891. Model development and evaluation occurred within the study cohort, so prospective recruitment does not establish prospective model testing or clinical benefit.
Technology: A 34-layer residual CNN with convolutional block attention analyzes wheeze audio, with an MLP for clinical features.
Publication: Peer-reviewed paper · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.
- AI contribution
- A 34-layer residual CNN with convolutional block attention analyzes wheeze audio, with an MLP for clinical features.
- Test and result
- In a prospective single-hospital cohort of 76 children, a 34-layer residual CNN with attention analyzed wheeze audio alongside clinical features; reported accuracy was 91.2% and AUC 0.891
- Limitation / still unknown
- Model development and evaluation occurred within the study cohort, so prospective recruitment does not establish prospective model testing or clinical benefit.
Evidence sources and annotation context
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
Evidence sources: https://www.nature.com/articles/s41598-022-25953-1 · https://pubmed.ncbi.nlm.nih.gov/36577766/
Source checked · editorial details
The source page was checked against this entry. Independent confirmation is not assessed by this label.
Source type: paper. Paper: linked separately.
Review date: 22 Nov 2026. Review scope: Primary result-bearing material for the stated method, result and evaluation, with bibliographic version information..
No follow-up recorded; this is not a claim that no follow-up exists. Follow-up review scope and date are not recorded. No source-supported relationships recorded.
Editorial assessment: Impact 2/5 · Validation 2/5 · Novelty 2/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.