Development and external validation of an interpretable machine learning model for predicting prolonged postoperative ICU length of stay in coronary artery bypass grafting patients using MIMIC-IV 3.1 and eICU-CRD 2.0
Source check: Source checked. Not independent scientific confirmation.
Finding: Nine models on MIMIC-IV CABG development (n=6,919) with eICU external validation (n=5,972), predicting ICU stay >3 days from first 24h features. CatBoost internal test AUC .774 and external AUC .645; calibration close to ideal. Full Methods/Results read. Modest external discrimination; prospective validation required. Publisher citation metadata lists 2026/12; the checked first result-bearing source version is dated 2026-06-27.
Technology: Nine machine-learning models use first-day ICU data to predict prolonged postoperative ICU stay after CABG; CatBoost is externally evaluated.
Publication: Peer-reviewed paper · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.
- AI contribution
- Nine machine-learning models use first-day ICU data to predict prolonged postoperative ICU stay after CABG; CatBoost is externally evaluated.
- Test and result
- Nine models on MIMIC-IV CABG development (n=6,919) with eICU external validation (n=5,972), predicting ICU stay >3 days from first 24h features. CatBoost internal test AUC .774 and external AUC .645; calibration close to ideal. Full Methods/Results read. Modest external discrimination; prospective validation required.
- Limitation / still unknown
- The study does not establish performance or consequences beyond the reported cohort, datasets, task or experimental setup.
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/s12911-026-03659-y
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 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.