Related Experiment Video
Updated: Jul 18, 2025
A Data-Driven Approach to Quantifying Immune States in Sepsis
Published on: February 7, 2025
Sepsis Prediction in Hospitalized Children: Model Development and Validation
Rebecca J Stephen1,2,3, Michael S Carroll1,4, Jeremy Hoge3
1Department of Pediatrics, Northwestern Feinberg School of Medicine.
Insights
This study developed a two-tiered prediction model for pediatric sepsis in hospitals. The model improves early recognition and situational awareness, aiding timely treatment for better patient outcomes.
Area of Science:
- Pediatric critical care medicine
- Clinical informatics
- Health services research
Background:
- Early recognition and treatment of pediatric sepsis are crucial for improving patient outcomes.
- While many pediatric sepsis cases are identified in the emergency department, some patients develop sepsis during hospitalization.
- There is a need for improved sepsis recognition within the inpatient setting.
Purpose of the Study:
- To develop and validate a prediction model for pediatric sepsis in the inpatient setting.
- To enhance the early recognition of sepsis in hospitalized children.
- To improve clinical decision-making for pediatric sepsis management.
Main Methods:
- A prediction model was developed using data from 2012-2018, incorporating variables from an existing model.
- A 2-tier threshold (Alert and Aware) was established using a precision-recall curve.
- The model was prospectively validated in the electronic health record during 2019.
Main Results:
- The final model included 13 variables and demonstrated strong performance with an area under the curve of 0.96 in the validation set.
- The 'Aware' tier achieved 100% sensitivity, increasing situational awareness.
- The 'Alert' tier had a positive predictive value of 14% (number needed to alert of 7), balancing sensitivity and specificity.
Conclusions:
- A 2-tiered prediction model for inpatient pediatric sepsis was successfully derived and validated.
- The model is designed to enhance situational awareness and minimize false alerts, facilitating prompt bedside evaluation.
- The model was integrated into the electronic health record as clinical decision support.
Background And Objectives:
Early recognition and treatment of pediatric sepsis remain mainstay approaches to improve outcomes. Although most children with sepsis are diagnosed in the emergency department, some are admitted with unrecognized sepsis or develop sepsis while hospitalized. Our objective was to develop and validate a prediction model of pediatric sepsis to improve recognition in the inpatient setting.
Methods:
Patients with sepsis were identified using intention-to-treat criteria. Encounters from 2012 to 2018 were used as a derivation to train a prediction model using variables from an existing model. A 2-tier threshold was determined using a precision-recall curve: an "Alert" tier with high positive predictive value to prompt bedside evaluation and an "Aware" tier with high sensitivity to increase situational awareness. The model was prospectively validated in the electronic health record in silent mode during 2019.
Results:
A total of 55 980 encounters and 793 (1.4%) episodes of sepsis were used for derivation and prospective validation. The final model consisted of 13 variables with an area under the curve of 0.96 (95% confidence interval 0.95-0.97) in the validation set. The Aware tier had 100% sensitivity and the Alert tier had a positive predictive value of 14% (number needed to alert of 7) in the validation set.
Conclusions:
We derived and prospectively validated a 2-tiered prediction model of inpatient pediatric sepsis designed to have a high sensitivity Aware threshold to enable situational awareness and a low number needed to Alert threshold to minimize false alerts. Our model was embedded in our electronic health record and implemented as clinical decision support, which is presented in a companion article.
