Related Experiment Video
Updated: Aug 14, 2025
A Data-Driven Approach to Quantifying Immune States in Sepsis
Published on: February 7, 2025
Risk Factors for Pediatric Sepsis in the Emergency Department: A Machine Learning Pilot Study
Laura Mercurio1, Sovijja Pou2, Susan Duffy
1From the Section of Pediatric Emergency Medicine, Department of Emergency Medicine, Alpert Medical School of Brown University, Providence, RI.
Insights
Machine learning identified key pediatric sepsis risk factors in the emergency department (ED). It highlighted underappreciated links between sepsis and patient age, immunization status, and demographics, alongside known predictors like heart rate.
Area of Science:
- Pediatric Emergency Medicine
- Machine Learning in Healthcare
- Clinical Informatics
Background:
- Sepsis is a life-threatening condition in children, requiring early identification of risk factors.
- Existing sepsis prediction models may not capture all relevant pediatric risk factors.
- Pediatric emergency departments (EDs) are critical points for initial sepsis assessment.
Purpose of the Study:
- To identify underappreciated sepsis risk factors in children presenting to a pediatric ED.
- To leverage machine learning to analyze diverse patient data for sepsis prediction.
- To improve early sepsis detection in pediatric populations.
Main Methods:
- Retrospective observational study of 35,074 pediatric ED encounters (2017-2019).
- Utilized machine learning models (e.g., random forest) to predict sepsis based on clinical and sociodemographic data.
- Extracted top 20 features to identify significant risk factors for pediatric sepsis.
Main Results:
- Machine learning models achieved up to 93% sensitivity and 84% specificity in identifying sepsis.
- Maximum heart rate and mean arterial pressure were top predictors.
- Underappreciated risk factors included immunization status, patient age, and zip code.
Conclusions:
- Machine learning effectively identified pediatric sepsis predictors using ED data.
- Confirmed known risk factors (heart rate, blood pressure) and revealed novel associations.
- Findings emphasize the importance of considering age, immunization, and demographics in pediatric sepsis risk assessment.
Objective:
To identify underappreciated sepsis risk factors among children presenting to a pediatric emergency department (ED).
Methods:
A retrospective observational study (2017-2019) of children aged 18 years and younger presenting to a pediatric ED at a tertiary care children's hospital with fever, hypotension, or an infectious disease International Classification of Diseases (ICD)-10 diagnosis. Structured patient data including demographics, problem list, and vital signs were extracted for 35,074 qualifying ED encounters. According to the Improving Pediatric Sepsis Outcomes Classification, confirmed by expert review, 191 patients met clinical sepsis criteria. Five machine learning models were trained to predict sepsis/nonsepsis outcomes. Top features enabling model performance (N = 20) were then extracted to identify patient risk factors.
Results:
Machine learning methods reached a performance of up to 93% sensitivity and 84% specificity in identifying patients who received a hospital diagnosis of sepsis. A random forest classifier performed the best, followed by a classification and regression tree. Maximum documented heart rate was the top feature in these models, with importance coefficients (ICs) of 0.09 and 0.21, which represent how much an individual feature contributes to the model. Maximum mean arterial pressure was the second most important feature (IC 0.05, 0.13). Immunization status (IC 0.02), age (IC 0.03), and patient zip code (IC 0.02) were also among the top features enabling models to predict sepsis from ED visit data. Stratified analysis revealed changes in the predictive importance of risk factors by race, ethnicity, oncologic history, and insurance status.
Conclusions:
Machine learning models trained to identify pediatric sepsis using ED clinical and sociodemographic variables confirmed well-established predictors, including heart rate and mean arterial pressure, and identified underappreciated relationships between sepsis and patient age, immunization status, and demographics.
Related Concept Videos
01:18Steps in Outbreak Investigation
01:26Factors Affecting the Risk of Infection
The integrity and count of the white blood cells help the body resist pathogens and fight infection. When impaired, it reduces the body's resistance to pathogens. The acidic pH levels of the gastrointestinal, genitourinary tracts, and skin...