Deep learning, computer-aided radiography reading for tuberculosis: a diagnostic accuracy study from a tertiary hospital in India
Source check: Source checked. Not independent scientific confirmation.
Finding: Against microbiological confirmation, qXR reached AUC 0.81, 71% sensitivity and 80% specificity; radiologist sensitivity was 56% with 80% specificity. Retrospective case-control cohort of 317 confirmed cases and 612 controls at one tertiary hospital; specificity/sensitivity limits and need for prospective studies are stated by the authors.
Technology: The learned qXR computer-aided detection system classifies chest radiographs for tuberculosis and related abnormalities.
Publication: Peer-reviewed paper · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.
- AI contribution
- The learned qXR computer-aided detection system classifies chest radiographs for tuberculosis and related abnormalities.
- Test and result
- Against microbiological confirmation, qXR reached AUC 0.81, 71% sensitivity and 80% specificity; radiologist sensitivity was 56% with 80% specificity.
- Limitation / still unknown
- Retrospective case-control cohort of 317 confirmed cases and 612 controls at one tertiary hospital; specificity/sensitivity limits and need for prospective studies are stated by the authors.
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/s41598-019-56589-3.pdf · https://pubmed.ncbi.nlm.nih.gov/31937802/
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 source full text Methods and Results; version/date checked against bibliographic record..
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.