Predicting Early Unplanned Readmission to Critical Care Units Using Machine Learning and Metaheuristic Hyperparameter Optimization: Evidence from a Chilean Public Hospital.
Source check: Source checked. Not independent scientific confirmation.
Finding / tested result: Five ML models assessed seven-day unplanned critical-care readmission in 371 patients, with nested stratified five-fold cross-validation and fold-contained preprocessing. Logistic regression had highest AUC (75.2%) and XGBoost 75.0%; case-enriched single-center data require recalibration and external validation.
Technology: 371 Chilean public-hospital ICU discharges with 41 readmissions; logistic regression, SVC, tree, random forest and XGBoost trained from transfer-time variables. Nested stratified five-fold CV; preprocessing fit within training folds. AUC 53.3–75.2%; LR highest 75.2%, XGBoost 75.0%; case-enriched cohort.
Publication: Peer-reviewed paper · Test context: direct test. Catalog categories, not an evidence grade.
- AI contribution
- 371 Chilean public-hospital ICU discharges with 41 readmissions; logistic regression, SVC, tree, random forest and XGBoost trained from transfer-time variables. Nested stratified five-fold CV; preprocessing fit within training folds. AUC 53.3–75.2%; LR highest 75.2%, XGBoost 75.0%; case-enriched cohort.
- Limitation / still unknown
- The reviewed source does not establish prospective benefit, broad external validity, or replication beyond the reported study.
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-15-08328/article_deploy/jcm-15-08328.pdf
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 3/5 · Novelty 2/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.