Clinical validation of the Swaasa® artificial intelligence platform using cough sounds for screening and aid in diagnosis of respiratory diseases.
Source check: Source checked. Not independent scientific confirmation.
Finding: The cough-based AI platform screened respiratory conditions with reported clinical-validation accuracy.
Technology: Swaasa® cough-audio AI platform
Publication: Peer-reviewed paper · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.
- AI contribution
- Processes cough recordings to classify respiratory risk, spirometric pattern and severity, and disease categories against spirometry and clinician diagnoses.
- Test and result
- The prospective monocentric study compared cough-audio classifications with spirometry and physician-established diagnoses. It reported 90% accuracy for normal/abnormal classification and 79–84% accuracy for spirometric patterns, 76–84.5% for severity, and 83–93% for disease categories; recordings repeated within participants were not independent patients.
- Limitation / still unknown
- This was a monocentric exploratory diagnostic study; it does not establish improved patient outcomes or performance across other care settings.
Evidence sources and annotation context
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
Evidence sources: https://pmc.ncbi.nlm.nih.gov/articles/PMC13751465/
Source checked · editorial details
The source page was checked against this entry. Independent confirmation is not assessed by this label.
Source type: paper. Paper: not linked in this catalog; this does not mean no paper exists.
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 3/5 · Validation 2/5 · Novelty 3/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.