Performance of a deep-learning algorithm for referable thoracic abnormalities on chest radiographs: A multicenter study of a health screening cohort
Source check: Source checked. Not independent scientific confirmation.
Finding: A commercial deep-learning radiograph algorithm was evaluated against CT-ground-truth in a multicenter health-screening cohort, with clinically specific sensitivity/specificity results.
Technology: A commercial deep-learning model detects referable thoracic abnormalities in chest radiographs.
Publication: Peer-reviewed paper · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.
- AI contribution
- A commercial deep-learning model detects referable thoracic abnormalities in chest radiographs.
- Test and result
- retrospective multicenter cohort of 5,887; CT-based reference and radiologist comparisons; AUC 0.771, sensitivity 69.6%, specificity 74.0% for referable abnormalities. Performance is moderate and screening impact was not tested.
- Limitation / still unknown
- Methods/Results: retrospective multicenter cohort of 5,887; CT-based reference and radiologist comparisons; AUC 0.771, sensitivity 69.6%, specificity 74.0% for referable abnormalities. Performance is moderate and screening impact was not tested.
Evidence sources and annotation context
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
Evidence sources: https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0246472 · https://pubmed.ncbi.nlm.nih.gov/33606779/
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.