Related Experiment Video
Updated: Oct 16, 2025
A Pediatric Concussion Model in Mice: Closed Head Injury with Long-Term Disorders (CHILD)
Published on: February 7, 2025
Development of a concise injury severity prediction model for pediatric patients involved in a motor vehicle
Thomas R Hartka1, Timothy McMurry2, Ashley Weaver3
1Department of Emergency Medicine, University of Virginia, Charlottesville, Virginia.
Insights
A simplified model accurately predicts severe pediatric injury using key factors like change in velocity and ejection. This tool aids emergency medical services (EMS) in trauma triage, but real-time delta-V data is crucial.
Area of Science:
- Trauma care
- Pediatric emergency medicine
- Injury prediction modeling
Background:
- Timely transport to trauma centers reduces mortality in severely injured pediatric patients.
- Emergency medical services (EMS) require accurate and parsimonious decision support tools for pediatric trauma triage.
- Identifying the minimal set of predictors is key to developing effective triage tools.
Purpose of the Study:
- To determine the minimum set of predictors necessary for accurate prediction of severe injury in pediatric patients.
- To develop a parsimonious and highly accurate decision support tool for prehospital trauma triage.
- To evaluate the predictive accuracy of logistic regression models with reduced variable sets.
Main Methods:
- Utilized National Automotive Sampling System (NASS) and Crash Injury Support System (CISS) data for crash and patient injury information.
- Developed baseline multivariable logistic models predicting Injury Severity Score (ISS) ≥16 and Target Injury List (TIL).
- Employed Bayesian Model Averaging (BMA) to identify the most important predictors and assessed model accuracy using receiver operator curve (ROC) area under the curve (AUC).
Main Results:
- Baseline models demonstrated high accuracy (AUCs of 0.91 for ISS ≥16 and 0.90 for TIL).
- No significant accuracy decrease was observed until models were reduced to fewer than five (ISS) or six (TIL) variables.
- A reduced five-variable model (including delta-V, entrapment, ejection, restraint use, near-side collision) achieved an AUC of 0.90 for predicting ISS ≥16.
Conclusions:
- A concise logistic regression model can effectively predict severe pediatric injury for prehospital trauma triage.
- The study highlights the critical importance of obtaining change in velocity (delta-V) data in real-time for accurate triage.
- Further development of decision support tools for pediatric trauma is warranted, emphasizing essential predictor variables.
Objective:
Transporting severely injured pediatric patients to a trauma center has been shown to decrease mortality. A decision support tool to assist emergency medical services (EMS) providers with trauma triage would be both as parsimonious as possible and highly accurate. The objective of this study was to determine the minimum set of predictors required to accurately predict severe injury in pediatric patients.
Methods:
Crash data and patient injuries were obtained from the NASS and CISS databases. A baseline multivariable logistic model was developed to predict severe injury in pediatric patients using the following predictors: age, sex, seat row, restraint use, ejection, entrapment, posted speed limit, any airbag deployment, principal direction of force (PDOF), change in velocity (delta-V), single vs. multiple collisions, and non-rollover vs. rollover. The outcomes of interest were injury severity score (ISS) ≥16 and the Target Injury List (TIL). Accuracy was measured by the cross-validation mean of the receiver operator curve (ROC) area under the curve (AUC). We used Bayesian Model Averaging (BMA) based on all subsets regression to determine the importance of each variable separately for each outcome. The AUC of the highest performing model for each number of variables was compared to the baseline model to assess for a statistically significant difference (p < 0.05). A reduced variable set model was derived using this information.
Results:
The baseline models performed well (ISS ≥ 16: AUC 0.91 [95% CI: 0.86-0.95], TIL: AUC 0.90 [95% CI: 0.86-0.94]). Using BMA, the rank of the importance of the predictors was identical for both ISS ≥ 16 and TIL. There was no statistically significant decrease in accuracy until the models were reduced to fewer than five and six variables for predicting ISS ≥ 16 and TIL, respectively. A reduced variable set model developed using the top five variables (delta-V, entrapment, ejection, restraint use, and near-side collision) to predict ISS ≥ 16 had an AUC 0.90 [95% CI: 0.84-0.96]. Among the models that did not include delta-V, the highest AUC was 0.82 [95% CI: 0.77-0.87].
Conclusions:
A succinct logistic regression model can accurately predict severely injured pediatric patients, which could be used for prehospital trauma triage. However, there remains a critical need to obtain delta-V in real-time.
