AI Science Tracker
EN

Deep Learning for Screening COVID-19 using Chest X-Ray Images

Not stated in the abstract reviewed · 22 Apr 2020 · medicine

Discovery

Deep Learning for Screening COVID-19 using Chest X-Ray Images

Source check: Source checked. Not independent scientific confirmation.

Finding: Approve very narrowly: transfer-learned CNN/DETL classified COVID, pneumonia, normal, and other findings on a small mixed-source CXR dataset with five-fold evaluation; no external clinical utility shown.

Technology: Pretrained CNN features support four-class image classification.

Publication: Preprint · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.

AI contribution
Pretrained CNN features support four-class image classification.
Test and result
Five-fold mixed-source dataset evaluation reports 90.13%±0.14 overall accuracy and Grad-CAM clinician-interpretation comparison.
Limitation / still unknown
Small mixed-source cohort and internal CV only; no external/clinical utility 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/2004.10507

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.

Open in the full catalog for filters, charts and related discoveries. Browse medicine discoveries.