A Machine Learning Predictive Model for Post-Ureteroscopy Urosepsis Needing Intensive Care Unit Admission: A Case-Control YAU Endourology Study from Nine European Centres
Source check: Source checked. Not independent scientific confirmation.
Finding: A random-forest model used nine-center case-control data to predict ICU-level urosepsis after ureteroscopy, with an internal 70/30 split; it classified 14/17 sepsis cases and 12/15 controls correctly in the test set. The small matched sample and lack of external validation limit generalization.
Technology: Random-forest classification predicts post-ureteroscopy urosepsis requiring ICU admission.
Publication: Peer-reviewed paper · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.
- AI contribution
- Random-forest classification predicts post-ureteroscopy urosepsis requiring ICU admission.
- Test and result
- Random forest with 300 trees on clinical/procedural factors, random 70/30 train/test split (seed 1234). Nine European centers supplied 57 ICU-urosepsis cases and 57 controls. Test performance: 82% cases, 80% controls; AUC 0.89; authors call for external validation.
- Limitation / still unknown
- A random-forest model used nine-center case-control data to predict ICU-level urosepsis after ureteroscopy, with an internal 70/30 split; it classified 14/17 sepsis cases and 12/15 controls correctly in the test set. The small matched sample and lack of external validation limit generalization.
Evidence sources and annotation context
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
Evidence sources: https://mdpi-res.com/d_attachment/jcm/jcm-10-03888/article_deploy/jcm-10-03888.pdf · https://pubmed.ncbi.nlm.nih.gov/34501335/
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.