An unchanged cardiac-arrest prediction model retained discrimination in a confirmatory and external retrospective evaluation
Source check: Source checked. Not independent scientific confirmation.
Finding: An existing ICU cardiac-arrest model was evaluated in a retrospective confirmatory sample and an independent external hospital cohort. It retained discrimination and detected more pre-arrest prediction points than conventional scores at matched alarm burden. The study tests retrospective performance, not intervention benefit.
Technology: An existing recurrent-network and gradient-boosting ensemble estimates 12-hour cardiac-arrest risk from ICU data.
Publication: Peer-reviewed paper · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.
- AI contribution
- An existing recurrent-network and gradient-boosting ensemble estimates 12-hour cardiac-arrest risk from ICU data.
- Test and result
- Retrospective confirmatory assessment at the development center and external evaluation across 30,487 ICU admissions compared discrimination, lead time, calibration, and matched alarm burden.
- Limitation / still unknown
- No intervention effect is tested; performance does not establish clinical 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/PMC13762413/
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 full-text review as recorded in case evidence; record-level claim and attribution review..
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 4/5 · 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.