An Ensemble Boosting Model for Predicting Transfer to the Pediatric Intensive Care Unit
This work addresses a critical healthcare problem for pediatric patients by providing a more accurate predictive tool, though it is incremental as it builds on existing boosting methods.
The paper tackles predicting pediatric patient transfers to intensive care by developing an ensemble boosting model, showing improvements over a baseline with accuracy increasing from 0.69 to 0.77 and AUROC from 0.73 to 0.85.
Our work focuses on the problem of predicting the transfer of pediatric patients from the general ward of a hospital to the pediatric intensive care unit. Using data collected over 5.5 years from the electronic health records of two medical facilities, we develop classifiers based on adaptive boosting and gradient tree boosting. We further combine these learned classifiers into an ensemble model and compare its performance to a modified pediatric early warning score (PEWS) baseline that relies on expert defined guidelines. To gauge model generalizability, we perform an inter-facility evaluation where we train our algorithm on data from one facility and perform evaluation on a hidden test dataset from a separate facility. We show that improvements are witnessed over the PEWS baseline in accuracy (0.77 vs. 0.69), sensitivity (0.80 vs. 0.68), specificity (0.74 vs. 0.70) and AUROC (0.85 vs. 0.73).