Deep Learning for Distinguishing Normal versus Abnormal Chest Radiographs and Generalization to Unseen Diseases
Source check: Source checked. Not independent scientific confirmation.
Finding: deep-learning CXR classifier was evaluated on large training cohorts and six external datasets; discrimination varied by disease and COVID AUC was limited, while triage time reduction was simulated only. The result-bearing arXiv v1 was posted on 2020-10-22; the later same-result Scientific Reports article is linked in paper_url.
Technology: Deep-learning chest-radiograph classifier
Publication: Preprint · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.
- AI contribution
- A deep-learning chest-radiograph classifier was trained on data from five Indian hospital clusters and tested on six external datasets to distinguish normal from abnormal images and assess unseen-disease performance.
- Test and result
- deep-learning CXR classifier was evaluated on large training cohorts and six external datasets; discrimination varied by disease and COVID AUC was limited, while triage time reduction was simulated only.
- Limitation / still unknown
- The reviewed study does not establish validation or benefit beyond its reported evaluation.
Evidence sources and annotation context
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
Evidence sources: https://arxiv.org/abs/2010.11375
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.