AI Insight
This retrospective cohort study developed and validated machine learning models to predict unplanned readmission to the pediatric intensive care unit (PICU) within 48 hours of transfer, using data from 35,601 patients across three quaternary care PICUs in Chicago between 2012 and 2019. Four models were tested (logistic regression, elastic net, random forest, and XGBoost), achieving modest internal validation performance with AUC values between 0.70 and 0.73. However, model performance declined notably during external validation (AUC 0.60-0.69), and the most predictive variables differed across sites, indicating limited generalizability.
Why it matters
PICU readmissions are associated with higher morbidity and mortality, and a reliable prediction tool could help clinicians intervene before deterioration occurs. However, this study suggests that externally developed models are unlikely to transfer reliably across institutions, meaning hospitals would need to derive and validate their own local models.
⚠️ Preprint – Noch nicht peer-reviewed
Dieser Artikel wurde noch nicht von unabhängigen Experten begutachtet. Die Ergebnisse sind vorläufig und sollten mit Vorsicht interpretiert werden.
Objective: Readmissions to the PICU are associated with increased morbidity and mortality. A prediction model that can identify children at risk of readmission at the time of transfer can allow providers to intervene and potentially improve patient outcomes. The objective of this study was to derive and validate machine learning models to predict PICU readmission at the time of transfer. Design: Retrospective observational cohort study Setting: Three quaternary care PICUs in the city of Chicago Patients: All children admitted to the PICU between 2012 and 2019. Measurements: The primary outcome was unplanned readmission to the PICU within 48 hours of transfer to the inpatient ward. Predictor variables included vital signs, patient characteristics, and laboratory results. We developed and externally validated four models to predict PICU readmission: logistic regression, elastic net, random forest, and XGBoost. Main Results: This study included 35,601 patients, with readmission rates ranging from 2.2-3.7% by site. The performance of models during internal validation was consistent at the three sites, with the area under the receiver operating characteristic (AUC) values between 0.70 and 0.73 and no difference across the four models. Model performance decreased significantly during external validation (AUCs of 0.60-0.69). The variables most important to the prediction differed at each site. Conclusion: Machine learning models for predicting readmissions to the PICU have limited generalizability. Locally derived models demonstrated modest performance in our study and could potentially inform provider decision-making if prospectively validated. Externally developed models are unlikely to perform well at predicting PICU readmissions.
Source: Predicting Intensive Care Readmission Among Hospitalized Children