Related Experiment Video
Updated: Jan 8, 2026
Author Spotlight: Advancing Rapid Detection of Respiratory Pathogens Using Microfluidic Chip
Published on: March 29, 2024
Early prediction of antibiotic need and bacteremia risk in non-immunocompromised pediatric emergency patients using
Tom Velez1, Oluwakemi Badaki-Makun2, Danielle Hirsch3
1Computer Technology Associates, Cardiff, CA, USA.
Insights
A new dual machine learning framework helps doctors decide when to give antibiotics to children in the emergency room. This tool improves patient safety and antibiotic stewardship by predicting infection risk and potential deterioration.
Area of Science:
- Pediatric Emergency Medicine
- Machine Learning in Healthcare
- Infectious Disease Diagnostics
Background:
- Accurate diagnosis of serious bacterial infections in pediatric emergency departments is crucial.
- Nonspecific early symptoms in non-immunocompromised children complicate diagnosis.
- Unnecessary antibiotic use contributes to adverse effects and antimicrobial resistance.
Purpose of the Study:
- To develop and evaluate a dual machine learning framework for informing early antibiotic decisions in pediatric emergency patients.
- To support individualized decision-making for antibiotic treatment in children.
- To improve patient safety and antibiotic stewardship.
Main Methods:
- Developed a two-part machine learning framework using retrospective electronic health record data from 5706 pediatric patients.
- Model 1 predicted clinical deterioration in children initially not receiving antibiotics.
- Model 2 predicted bacteremia likelihood in children receiving early empiric antibiotics.
- Utilized XGBoost and cross-validation for model development and evaluation.
Main Results:
- The framework demonstrated strong performance with high area under the curve values.
- Negative predictive values exceeded 96% for both models.
- Key predictive features included supplemental oxygen use, fever, low oxygen saturation, age, and abnormal laboratory values.
Conclusions:
- The dual-model framework provides interpretable, evidence-based support for early antibiotic treatment decisions.
- This approach can enhance patient safety by identifying children who may benefit from or safely avoid early antibiotics.
- The study introduces a novel, harmonized multi-center approach with explainability for clinical use.
Background:
Timely identification of serious bacterial infections in children presenting to emergency departments is critical, especially among non-immunocompromised children, where early symptoms can be nonspecific. Although many children receive empiric antibiotic treatment based on clinical suspicion, true bloodstream infection is relatively uncommon, and unnecessary antibiotics can contribute to adverse effects and antimicrobial resistance.
Methods:
To support individualized decision-making, we developed and evaluated a two-part machine learning framework using retrospective electronic health record data from 5706 pediatric patients aged 3 months to 17 years across six emergency departments. The first model predicted clinical deterioration-defined as admission to intensive care, use of vasopressors, mechanical ventilation, or in-hospital death-among children in whom antibiotics were initially withheld. The second model predicted the likelihood of bacteremia among those who received early empiric antibiotics. Both models were built using XGBoost and evaluated through cross-validation.
Results:
Performance was strong, with high area under the curve values and negative predictive values above 96%. Predictive features included supplemental oxygen use, fever, low oxygen saturation, age, and abnormal laboratory values.
Conclusions:
This dual-model framework offers interpretable, evidence-based support for early treatment decisions and could improve both patient safety and antibiotic stewardship in pediatric emergency care.
Impact:
This study introduces a dual machine learning framework that informs early antibiotic decisions in non-immunocompromised pediatric emergency patients. It adds a novel two-model approach: one to predict deterioration when antibiotics are initially withheld, and another to predict bacteremia in those treated. Unlike prior tools, it uses harmonized multi-center EHR data and SHAP-based explain ability to support bedside clinical use. The impact lies in enhancing antibiotic stewardship and patient safety by identifying who may benefit from early antibiotics and who may safely avoid them.
Related Concept Videos
01:26Pharmacokinetics in Pediatric Patients: Drug Excretion
01:18Steps in Outbreak Investigation
01:28Acute Pyelonephritis II: Diagnostic Studies and Management