Learning classifies concurrent cardiac injury markers in cancer and COVID-19
Source check: Source checked. Not independent scientific confirmation.
Finding: A random forest combined eight laboratory and chest-imaging measures in 201 cancer patients with COVID-19. Internal evaluation distinguished patients with troponin-defined cardiac injury, with reported AUC 0.94. Predictor timing relative to injury was not established, and outcome-informed screening preceded validation. This supports an exploratory concurrent classification result, not prediction before injury or improved patient outcomes.
Technology: Random forest; LASSO feature screening
Publication: Peer-reviewed paper · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.
- AI contribution
- A random forest learns relationships between selected laboratory/imaging measurements and recorded biochemical cardiac-injury status.
- Test and result
- Retrospective comparison with troponin-defined injury status in 67 cases and 134 non-cases, with reported ten-fold internal validation.
- Limitation / still unknown
- Pre-injury forecasting, independent diagnostic validation and clinical benefit remain unestablished; imputation and outcome-informed feature ranking may introduce optimism.
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/PMC11797975/
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: 21 Nov 2026. Review scope: Primary relevant model Methods, Results and limitations; exact primary identity and current primary PubMed correction/retraction relationships checked..
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.