Related Experiment Video
Updated: Jan 4, 2026
A Data-Driven Approach to Quantifying Immune States in Sepsis
Published on: February 7, 2025
Pediatric Severe Sepsis Prediction Using Machine Learning
Sidney Le1, Jana Hoffman1, Christopher Barton1,2
1Dascena Inc., Oakland, CA, United States.
Insights
A machine learning algorithm can predict severe sepsis in children using electronic health records (EHR). This AI tool shows promise for earlier detection and treatment of pediatric severe sepsis.
Area of Science:
- Pediatric critical care medicine
- Health informatics
- Machine learning in healthcare
Background:
- Early detection of pediatric severe sepsis is crucial for effective treatment.
- Novel methods are needed to improve the early identification of severe sepsis in children.
- Machine learning offers a potential avenue for enhancing sepsis detection.
Purpose of the Study:
- To evaluate a machine learning algorithm's ability to predict severe sepsis onset in pediatric patients.
- To assess the algorithm's performance using electronic healthcare record (EHR) data.
- To compare the algorithm's predictive power against existing clinical scores.
Main Methods:
- Retrospective analysis of de-identified EHR data from pediatric inpatient and emergency encounters (ages 2-17).
- Data collected from UCSF Medical Center between June 2011 and March 2016.
- A machine learning algorithm was developed and evaluated using 4-fold cross-validation.
Main Results:
- The study identified 101 cases of severe sepsis among 9,486 pediatric patients.
- The machine learning algorithm achieved an AUROC of 0.916 at sepsis onset and 0.718 at 4 hours prior.
- The algorithm significantly outperformed PELOD-2 and SIRS scores in predicting severe sepsis 4 hours before onset.
Conclusions:
- A machine learning algorithm utilizing EHR data can effectively detect and predict pediatric severe sepsis.
- Automated monitoring of EHR data holds potential for earlier sepsis recognition and treatment initiation in pediatric inpatients.
- This approach may significantly improve outcomes for children with severe sepsis.
Abstract:
Background: Early detection of pediatric severe sepsis is necessary in order to optimize effective treatment, and new methods are needed to facilitate this early detection. Objective: Can a machine-learning based prediction algorithm using electronic healthcare record (EHR) data predict severe sepsis onset in pediatric populations? Methods: EHR data were collected from a retrospective set of de-identified pediatric inpatient and emergency encounters for patients between 2-17 years of age, drawn from the University of California San Francisco (UCSF) Medical Center, with encounter dates between June 2011 and March 2016. Results: Pediatric patients (n = 9,486) were identified and 101 (1.06%) were labeled with severe sepsis following the pediatric severe sepsis definition of Goldstein et al. (1). In 4-fold cross-validation evaluations, the machine learning algorithm achieved an AUROC of 0.916 for discrimination between severe sepsis and control pediatric patients at the time of onset and AUROC of 0.718 at 4 h before onset. The prediction algorithm significantly outperformed the Pediatric Logistic Organ Dysfunction score (PELOD-2) (p < 0.05) and pediatric Systemic Inflammatory Response Syndrome (SIRS) (p < 0.05) in the prediction of severe sepsis 4 h before onset using cross-validation and pairwise t-tests. Conclusion: This machine learning algorithm has the potential to deliver high-performance severe sepsis detection and prediction through automated monitoring of EHR data for pediatric inpatients, which may enable earlier sepsis recognition and treatment initiation.
