An ensemble model approach for identifying pulmonary tuberculosis on chest X-ray.
Source check: Source checked. Not independent scientific confirmation.
Finding: Ensemble models detect pulmonary tuberculosis on chest radiographs with independent testing.
Technology: Transfer-learned CNNs and performance-weighted ensemble for chest-X-ray TB classification
Publication: Peer-reviewed paper · Test context: prospective or independent check. Catalog categories, not an evidence grade.
- AI contribution
- Classifies chest X-rays for pulmonary tuberculosis; the ensemble weights nine CNN prediction scores, with weights based on internal-test AUC.
- Test and result
- Nine transfer-learned CNNs and four ensembles were evaluated on internal and independent external CXR data. Performance-weighted averaging achieved external-validation AUC 0.880 and F1 0.861; the best single model, VGG19, achieved AUC 0.853.
- Limitation / still unknown
- Performance fell on independent external validation; the study did not establish deployment benefit.
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/PMC13563563/
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 4/5 · Novelty 3/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.