Related Experiment Video
Updated: Dec 12, 2025
Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack
Published on: May 15, 2020
Identifying children at high risk for infection-related decompensation using a predictive emergency department-based
Robert J Sepanski1,2, Arno L Zaritsky2, Sandip A Godambe2
1Department of Quality and Safety, Children's Hospital of The King's Daughters, Norfolk, VA, USA.
Insights
A new electronic tool accurately identifies pediatric sepsis in the emergency department (ED), improving early detection and treatment for critically ill children. This sepsis prediction tool offers high sensitivity and a low false alarm rate.
Area of Science:
- Pediatric Emergency Medicine
- Clinical Informatics
- Sepsis Detection
Background:
- Existing electronic alert systems for pediatric sepsis in the emergency department (ED) have limitations, often leading to frequent false alarms or missed early signs of decompensation.
- Timely identification and treatment are crucial for preventing severe outcomes in pediatric sepsis.
Purpose of the Study:
- To develop and evaluate a novel predictive tool for identifying potential sepsis in children presenting to the ED.
- The tool aims to improve the accuracy and efficiency of sepsis detection compared to existing systems.
Main Methods:
- A predictive tool was developed using electronic health record data from approximately 1.2 million children across 169 hospitals.
- The tool incorporates updated vital sign standards and was trained using gold standard (GS) sepsis cases and high severity of illness (SOI) outcomes.
- An iterative process assigned weights to factors significantly associated with GS sepsis and high SOI to maximize sensitivity and positive predictive value.
Main Results:
- The implemented tool achieved 77% sensitivity for identifying GS sepsis within 48 hours and a 22.5% positive predictive value for major/extreme SOI outcomes.
- The system demonstrated a low overall firing rate of 2% among ED patients.
- Patients admitted with positive alerts had significantly longer hospitalizations compared to those without alerts.
Conclusions:
- The developed ED-based electronic tool effectively combines high sensitivity for predicting GS sepsis with a high predictive value for physiologic decompensation and a low false alarm rate.
- This tool has the potential to optimize critical treatment pathways for high-risk pediatric patients experiencing sepsis.
Objectives:
Electronic alert systems to identify potential sepsis in children presenting to the emergency department (ED) often either alert too frequently or fail to detect earlier stages of decompensation where timely treatment might prevent serious outcomes.
Methods:
We created a predictive tool that continuously monitors our hospital's electronic health record during ED visits. The tool incorporates new standards for normal/abnormal vital signs based on data from ∼1.2 million children at 169 hospitals. Eighty-two gold standard (GS) sepsis cases arising within 48 h were identified through retrospective chart review of cases sampled from 35,586 ED visits during 2012 and 2014-2015. An additional 1,027 cases with high severity of illness (SOI) based on 3 M's All Patient Refined - Diagnosis-Related Groups (APR-DRG) were identified from these and 26,026 additional visits during 2017. An iterative process assigned weights to main factors and interactions significantly associated with GS cases, creating an overall "score" that maximized the sensitivity for GS cases and positive predictive value for high SOI outcomes.
Results:
Tool implementation began August 2017; subsequent improvements resulted in 77% sensitivity for identifying GS sepsis within 48 h, 22.5% positive predictive value for major/extreme SOI outcomes, and 2% overall firing rate of ED patients. The incidence of high-severity outcomes increased rapidly with tool score. Admitted alert positive patients were hospitalized nearly twice as long as alert negative patients.
Conclusions:
Our ED-based electronic tool combines high sensitivity in predicting GS sepsis, high predictive value for physiologic decompensation, and a low firing rate. The tool can help optimize critical treatments for these high-risk children.
