Related Experiment Video
Updated: Sep 19, 2025
A Data-Driven Approach to Quantifying Immune States in Sepsis
Published on: February 7, 2025
Machine learning model for daily prediction of pediatric sepsis using Phoenix criteria
Daniela Chanci1, Jocelyn R Grunwell2,3, Alireza Rafiei4
1Department of Biomedical Engineering, Duke University, Durham, NC, USA. daniela.chanciarrubla@duke.edu.
Insights
This study developed a machine learning model to predict sepsis in critically ill children using electronic health records. The CatBoost model achieved high accuracy, aiding early sepsis recognition and improving outcomes.
Area of Science:
- Pediatric critical care medicine
- Machine learning applications in healthcare
- Clinical informatics
Background:
- Sepsis diagnosis in critically ill children is crucial for timely treatment and improved survival rates.
- Existing models lack validation using readily available electronic medical record (EMR) data.
- Early identification of sepsis prevents organ failure progression in pediatric intensive care units (PICUs).
Purpose of the Study:
- To develop and validate a machine learning (ML) model for predicting sepsis onset in PICU patients.
- Utilize EMR data and the Phoenix Sepsis Score Criteria for model development.
- Enhance early sepsis detection in critically ill children.
Main Methods:
- Data from 63,875 PICU encounters were analyzed from two PICUs within a single healthcare system.
- Four ML models were trained and tested using vital signs, lab results, demographics, medications, and organ dysfunction scores.
- The Phoenix Sepsis Score Criteria were used to identify sepsis cases.
Main Results:
- The Categorical Boosting (CatBoost) model demonstrated superior performance.
- CatBoost achieved an area under the receiver operating characteristic curve (AUROC) of 0.98.
- The model also yielded an area under the precision-recall curve (AUPRC) of 0.83.
Conclusions:
- The developed ML model can predict sepsis onset based on the Phoenix Sepsis Score criteria.
- Implementation may assist clinicians in more efficient sepsis recognition and management.
- This tool has the potential to reduce morbidity and mortality associated with pediatric sepsis.
Background:
Early sepsis diagnosis is essential for initiating prompt treatment, preventing the progression of organ failure, and improving the survival rate of critically ill children. The aim of this study was to develop and validate a machine learning sepsis prediction model for patients admitted to a pediatric intensive care unit (PICU) who met the Phoenix Sepsis Score Criteria using EMR data.
Methods:
Data were obtained from two PICUs within the same healthcare system. Readily available variables were used to develop and validate machine learning models predicting the onset of sepsis in critically ill children.
Results:
A total of 63,875 PICU encounters were included, of which there were 5248 who met the criteria for Phoenix Sepsis. We trained and tested 4 machine learning models using vital signs, laboratory tests, demographic data, medications, and organ dysfunction scores. The Categorical Boosting (CatBoost) model had the best performance with an AUROC of 0.98 (95% CI, 0.98-0.98), and an AUPRC of 0.83 (95% CI, 0.82-0.83).
Conclusions:
The implementation of our model capable of predicting the onset of sepsis defined by the Phoenix Sepsis Score criteria may help clinicians recognize and manage children with sepsis more efficiently to reduce morbidity and mortality.
Impact:
Sepsis is a life-threatening condition with high rates of morbidity and mortality in children, especially in pediatric critical care units. However, there is no validated model using readily available variables in the electronic medical record data to identify critically ill patients with sepsis. The use of machine learning and electronic medical health records data to develop a predictive model can automate the identification of patients at high risk for sepsis-related organ dysfunction. The implementation of this tool can improve recognition of sepsis and prevent the progression of sepsis-related organ dysfunction leading to death.
