Abstract
How likely is a Paediatric Intensive Care Unit (PICU) patient to survive the next six hours, or the next 12 hours? Six years of EHR big data (2120 patients) from Cambridge University Hospitals PICU will soon be validated using GOSH PICU data (2686 patients). A decision tree algorithm combined with proportional-integral-derivative analysis and polynomial modelling. 100% sensitivity and 50% specificity (AUC 0.93) for predicting death within the following six-hour time period, with 95% sensitivity and 70% specificity for a 12-hour time period (AUC 0.82) applying a gradient boosted decision tree to the Cambridge dataset. A potential means to intervene, manage or communicate regarding patient acuity on PICU.
Acknowledgements for funding or support This work was made possible through the support of the Biomedical Research Centre at the University of Cambridge/Cambridge University Hospitals NHS Foundation Trust
