Machine learning prediction of PICC-associated thrombotic complications in critically ill patients.
Source check: Source checked. Not independent scientific confirmation.
Finding: primary Methods/Results document the AI-enabled result, evaluation and bounded interpretation.
Technology: Random Forest and four comparator machine-learning models
Publication: Peer-reviewed paper · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.
- AI contribution
- Predicts PICC-associated thrombosis from clinical variables in MIMIC-IV; Random Forest was the best of five evaluated models.
- Test and result
- Five models were trained on 8,145 PICC insertions from 6,376 MIMIC-IV patients. Random Forest had AUC 0.809 (95% CI 0.780–0.838); patient-clustered splitting reduced AUC to 0.696, indicating within-patient correlation affected the primary split.
- Limitation / still unknown
- The reported evaluation does not establish prospective benefit or performance beyond the studied setting.
Evidence sources and annotation context
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
Evidence sources: https://link.springer.com/article/10.1186/s12911-026-03607-w
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.