Machine Learning for Predicting Critical Events Among Hospitalized Children.
Hospitalwide machine learning model outperformed unit-specific tools at predicting pediatric deterioration
Machine Learning for Predicting Critical Events Among Hospitalized Children.
IMPORTANCE: Unrecognized deterioration among hospitalized children is associated with a high risk of mortality and morbidity.
To develop a machine learning model for the early detection of deterioration across all units, thereby enabling a unified risk assessment throughout the patient's hospital stay.
DESIGN, SETTING, AND PARTICIPANTS: This retrospective cohort study used data from pediatric (age <18 years) admissions to inpatient and intensive care units at 3 tertiary care academic hospitals.
AUROC of 0.86 (1.0 is perfect), better discrimination than existing unit-specific tools
The cohort included 135 621 patients (mean [SD] age, 7 [6] years; 60 376 [44.5%] female).
Data from 2 hospitals were used as a derivation cohort, while patients in the third hospital constituted the hold-out external test cohort.
The deep learning models did not exhibit improved performance.
The XGB model performed better or equivalent to models trained for a specific hospital unit.
This retrospective cohort study describes the development of a novel hospitalwide model for continuously predicting the risk of critical events through the entirety of a child's stay.
The model facilitated a unified framework for risk assessment in a pediatric hospital.