Related Experiment Video
Updated: Apr 8, 2026
Author Spotlight: Simulating Pediatric Cardiac Surgery Using a Neonatal Piglet Model
Published on: May 26, 2023
Evidence-Based Pediatric Outcome Predictors to Guide the Allocation of Critical Care Resources in a Mass Casualty
Philip Toltzis1, Gerardo Soto-Campos, Christian R Shelton
11Division of Critical Care, Department of Pediatrics, Rainbow Babies and Children's Hospital, Cleveland, OH. 2Virtual PICU Systems LLC, Los Angeles, CA. 3National Outcomes Center, Children's Hospital of Wisconsin, Milwaukee, Wisconsin. 4Pediatric Critical Care Medicine, Department of Pediatrics, Virginia Tech Carilion School of Medicine, Roanoke, VA. 5National Center for Disaster Preparedness, Columbia University, New York, NY. 6Department of Anesthesiology Critical Care Medicine, Children's Hospital of Los Angeles, Los Angeles, CA.
Insights
This study developed a predictive tool to help allocate pediatric intensive care unit (PICU) resources during emergencies. The goal is to improve survival rates by prioritizing children most likely to benefit from short-term critical care interventions.
Area of Science:
- Pediatric Critical Care Medicine
- Health Systems Management
- Biostatistics and Predictive Modeling
Background:
- Mass casualty events can overwhelm Intensive Care Unit (ICU) resources, necessitating Crisis Standards of Care (CSC).
- CSC involves diverting critical care from patients least likely to benefit to improve overall population survival.
- A specific triage allocation scheme for children during CSC is needed.
Purpose of the Study:
- To devise a Crisis Standards of Care triage allocation scheme specifically for children.
- To develop evidence-based predictive tools to guide resource allocation in pediatric critical care during mass casualty events.
Main Methods:
- Proposed a triage scheme dividing patients by need for mechanical ventilation upon Pediatric Intensive Care Unit (PICU) presentation.
- Evaluated mortality probability and predicted resource consumption (PICU length of stay, mechanical ventilation duration).
- Utilized logistic/linear regression and Machine Learning on 150,000 records from 110 American PICUs to develop prediction equations.
Main Results:
- Prediction equations for mortality probability achieved an area under the receiver operating characteristic curve > 0.87.
- Machine learning independently verified the triage sequence, demonstrating strong predictive power for mortality.
- The developed tool can identify children likely to benefit from short-duration ICU interventions.
Conclusions:
- An evidence-based predictive tool for pediatric resource allocation during Crisis Standards of Care has been developed.
- This tool aims to improve population outcomes by guiding selection of patients likely to benefit from ICU interventions.
- The scheme prioritizes children based on predicted mortality and resource utilization.
Objective:
ICU resources may be overwhelmed by a mass casualty event, triggering a conversion to Crisis Standards of Care in which critical care support is diverted away from patients least likely to benefit, with the goal of improving population survival. We aimed to devise a Crisis Standards of Care triage allocation scheme specifically for children.
Design:
A triage scheme is proposed in which patients would be divided into those requiring mechanical ventilation at PICU presentation and those not, and then each group would be evaluated for probability of death and for predicted duration of resource consumption, specifically, duration of PICU length of stay and mechanical ventilation. Children will be excluded from PICU admission if their mortality or resource utilization is predicted to exceed predetermined levels ("high risk"), or if they have a low likelihood of requiring ICU support ("low risk"). Children entered into the Virtual PICU Performance Systems database were employed to develop prediction equations to assign children to the exclusion categories using logistic and linear regression. Machine Learning provided an alternative strategy to develop a triage scheme independent from this process.
Setting:
One hundred ten American PICUs
Subjects:
: One hundred fifty thousand records from the Virtual PICU database.
Interventions:
None.
Measurements And Main Results:
The prediction equations for probability of death had an area under the receiver operating characteristic curve more than 0.87. The prediction equation for belonging to the low-risk category had lower discrimination. R for the prediction equations for PICU length of stay and days of mechanical ventilation ranged from 0.10 to 0.18. Machine learning recommended initially dividing children into those mechanically ventilated versus those not and had strong predictive power for mortality, thus independently verifying the triage sequence and broadly verifying the algorithm.
Conclusion:
An evidence-based predictive tool for children is presented to guide resource allocation during Crisis Standards of Care, potentially improving population outcomes by selecting patients likely to benefit from short-duration ICU interventions.
Related Concept Videos
01:25Cardiopulmonary Resuscitation IV: Pharmacological Management
01:23Types of Biopharmaceutical Studies: Controlled and Non-Controlled Approaches
Non-controlled studies, commonly employed for initial exploration, lack a control group, rendering them susceptible to biases and external influences. In contrast,...
01:21Cancer Survival Analysis