Early Prediction of Critical Care Interventions From Pediatric Emergency Department Triage.
Machine learning model flagged 88% of pediatric emergency departments patients who needed critical care at triage
Early Prediction of Critical Care Interventions From Pediatric Emergency Department Triage.
Most pediatric emergency departments (emergency departments) in the United States use Emergency Severity Index (Emergency Severity Index) system to triage patients.
Because the 5-level classification provides limited risk stratification, this study aims to improve patient prioritization by developing an operationally useful model that predicts risk of critical care interventions using only information available during emergency departments triage.
We conducted a retrospective study at a large urban academic pediatric emergency departments from 2016 to 2024.
Among 886 183 emergency departments visits, 26 721 (3.0%) received critical care interventions.
The neural network had the highest Average Precision of 0.6 (95% CI 0.59-0.61).
Supplementing Emergency Severity Index with these risk predictions would have increased the proportion of critical care patients being timely evaluated by physicians from 23.3% to 75.0% for Emergency Severity Index 3 patients.
Similarly, improvements would have been achieved for other Emergency Severity Index levels.
We developed models capable of quickly identifying emergency departments pediatric patients at risk of requiring critical care interventions without causing alarm fatigue.
Potential improvements in time-to-pediatrician for at-risk patients suggest utility of our machine learning-support triage framework in improving patient care and safety in pediatric emergency departments.