Related Experiment Video
Updated: Nov 8, 2025
A Modified Sonographic Algorithm for Image Acquisition in Life-Threatening Emergencies in the Critically Ill Newborn
Published on: April 7, 2023
Development and validation of an early warning tool for sepsis and decompensation in children during emergency
Louis Ehwerhemuepha1, Theodore Heyming2, Rachel Marano2
1Children's Health of Orange County, 1201 W La Veta Ave, Orange, CA, 92868, USA. lehwerhemuepha@choc.org.
Insights
This study developed an early warning system for pediatric sepsis using a predictive model. The system accurately identifies sepsis-related critical decompensation in emergency departments, improving patient outcomes.
Area of Science:
- Pediatric Emergency Medicine
- Clinical Informatics
- Machine Learning in Healthcare
Background:
- Sepsis is a life-threatening condition requiring early detection.
- Existing sepsis detection methods in pediatric emergency departments (EDs) can be improved.
Purpose of the Study:
- To develop and validate an early warning system (EWS) for predicting critical decompensation in pediatric sepsis.
- To identify key predictors of sepsis-related outcomes in a large pediatric ED population.
Main Methods:
- Utilized electronic medical record data from 537,837 pediatric ED visits (March 2013-December 2019).
- Developed a multiclass stochastic gradient boosting model incorporating triage vital signs, diagnoses, medications, and prior healthcare utilization.
- Evaluated model performance using area under the receiver operator characteristic curve (AUROC) and area under the precision recall curve.
Main Results:
- The model identified early warning signs for death, severe sepsis, non-severe sepsis, and bacteremia.
- Key predictors included age, heart rate, prior hospitalization length of stay, temperature, systolic blood pressure, and prior sepsis.
- Achieved high AUROCs for predicting death (0.979), severe sepsis (0.990), non-severe sepsis (0.976), and bacteremia (0.968).
- The multi-class macro average AUROC was 0.977.
Conclusions:
- An automated early warning decision tool for sepsis was developed based on the study findings.
- Implementation in pediatric EDs can enable rapid and accurate prediction of sepsis-related critical decompensation.
- This EWS has the potential to significantly improve sepsis management and patient outcomes in pediatric emergency care.
Abstract:
This study was designed to develop and validate an early warning system for sepsis based on a predictive model of critical decompensation. Data from the electronic medical records for 537,837 visits to a pediatric Emergency Department (ED) from March 2013 to December 2019 were collected. A multiclass stochastic gradient boosting model was built to identify early warning signs associated with death, severe sepsis, non-severe sepsis, and bacteremia. Model features included triage vital signs, previous diagnoses, medications, and healthcare utilizations within 6 months of the index ED visit. There were 483 patients who had severe sepsis and/or died, 1102 had non-severe sepsis, 1103 had positive bacteremia tests, and the remaining had none of the events. The most important predictors were age, heart rate, length of stay of previous hospitalizations, temperature, systolic blood pressure, and prior sepsis. The one-versus-all area under the receiver operator characteristic curve (AUROC) were 0.979 (0.967, 0.991), 0.990 (0.985, 0.995), 0.976 (0.972, 0.981), and 0.968 (0.962, 0.974) for death, severe sepsis, non-severe sepsis, and bacteremia without sepsis respectively. The multi-class macro average AUROC and area under the precision recall curve were 0.977 and 0.316 respectively. The study findings were used to develop an automated early warning decision tool for sepsis. Implementation of this model in pediatric EDs will allow sepsis-related critical decompensation to be predicted accurately after a few seconds of triage.
