Artificial Intelligence Systems for Diagnosis and Clinical Classification of COVID-19
Source check: Source checked. Not independent scientific confirmation.
Finding: Transfer-learned VGG19 CT classification distinguished COVID-19 from other pneumonia/controls in retrospective cohorts; reported diagnostic AUC 0.95, with a separate clinical-type prediction AUC 0.90. Evidence is limited to the stated retrospective/in-silico/prototype setting.
Technology: Transfer-learned VGG19 classifies chest CT images for COVID-19 versus other pneumonia.
Publication: Peer-reviewed paper · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.
- AI contribution
- Transfer-learned VGG19 classifies chest CT images for COVID-19 versus other pneumonia.
- Test and result
- Transfer-learned VGG19 CT classification distinguished COVID-19 from other pneumonia/controls in retrospective cohorts; reported diagnostic AUC 0.95, with a separate clinical-type prediction AUC 0.90.
- Limitation / still unknown
- Methods report 186 COVID-19 patients, 113 other-pneumonia patients and 150 non-pneumonia controls, with fivefold CV. Results link imaging model and clinical laboratory variables to diagnosis/type; retrospective single-region evidence, no prospective utility.
Evidence sources and annotation context
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
Evidence sources: https://www.frontiersin.org/journals/microbiology/articles/10.3389/fmicb.2021.729455/full · https://pubmed.ncbi.nlm.nih.gov/34650534/
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.