AUTHOR=Bose Sanjukta N. , Greenstein Joseph L. , Fackler James C. , Sarma Sridevi V. , Winslow Raimond L. , Bembea Melania M. 

TITLE=Early Prediction of Multiple Organ Dysfunction in the Pediatric Intensive Care Unit

JOURNAL=Frontiers in Pediatrics

VOLUME=Volume 9 - 2021

YEAR=2021

URL=https://www.frontiersin.org/journals/pediatrics/articles/10.3389/fped.2021.711104

DOI=10.3389/fped.2021.711104

ISSN=2296-2360

ABSTRACT=Objective: To build models for early prediction of risk for developing multiple organ dysfunction (MOD) in pediatric intensive care unit (PICU) patients. 
Design: Retrospective observational cohort study.
Setting:  Single academic PICU at the Johns Hopkins Hospital, Baltimore, MD.
Patients: Patients <18 years of age admitted to the PICU between July 2014 – October 2015. 
Measurements and Main Results: Organ dysfunction labels were generated every minute from preceding 24-hour time windows using the international pediatric sepsis consensus conference (IPSCC) and Proulx et al. MOD criteria. Early MOD prediction models were built using four machine learning methods: Random Forest, XGBoost, GLMBoost and Lasso-GLM. An optimal threshold learned from training data was used to detect high-risk alert events (HRA). The early prediction models from all methods achieved an area under the receiver operating characteristics curve ≥0.91 for both IPSCC and Proulx criteria. The best performance in terms of maximum F1-score was achieved with Random Forest (sensitivity: 0.72, positive predictive value: 0.70, F1-score: 0.71) and XGBoost (sensitivity: 0.8, positive predictive value: 0.81, F1-score: 0.81) for IPSCC and Proulx criteria respectively. The median early warning time was 22.7 hours for Random Forest and 37 hours for XGBoost models for IPSCC and Proulx criteria, respectively. Applying spectral clustering on risk-score trajectories over 24 hours following early warning provided a high-risk group with ≥0.93 positive predictive value. 
Conclusions: Early predictions from risk-based patient monitoring could provide more than 22 hours of lead-time for MOD onset, with ≥0.93 positive predictive value for a high-risk group identified pre-MOD.