Related Experiment Video
Updated: Oct 11, 2025
A Pediatric Concussion Model in Mice: Closed Head Injury with Long-Term Disorders (CHILD)
Published on: February 7, 2025
Development and validation of machine learning models for the prediction of blunt cerebrovascular injury in children
Cyrus A Farzaneh1, John Schomberg2, Brittany G Sullivan1
1Department of Surgery, University of California, Irvine, 101 The City Drive South, Orange, CA 92868, United States.
Insights
A new prediction model effectively identifies blunt cerebrovascular injury (BCVI) in pediatric trauma patients. This machine learning approach improves upon existing models for diagnosing BCVI in children.
Area of Science:
- Pediatric Trauma Surgery
- Vascular Injury Diagnosis
- Machine Learning in Medicine
Background:
- Blunt cerebrovascular injury (BCVI) is rare in pediatric trauma.
- Existing adult-based prediction models (Denver, Memphis) are inadequate for children.
- A need exists for a pediatric-specific BCVI prediction model.
Purpose of the Study:
- To develop and validate a novel prediction model for BCVI specifically in pediatric patients.
- To improve the accuracy of identifying children who require further imaging for BCVI.
Main Methods:
- Utilized the National Trauma Databank (NTDB) from 2007-2015.
- Developed a random forest machine learning model using 885,100 pediatric trauma cases.
- Validated the model against existing Denver and Memphis criteria.
Main Results:
- The new model identified 94.4% of pediatric BCVI cases and 76.1% of non-BCVI cases.
- Skull, extremity, and vertebral fractures were associated with increased BCVI risk.
- Existing Denver and Memphis criteria identified only 13.4% of BCVI patients.
Conclusions:
- The developed prediction model significantly enhances the identification of pediatric BCVI.
- This tool can guide further imaging decisions in children with blunt trauma.
- The model offers a superior alternative to adult-derived criteria for pediatric BCVI screening.
Background:
Blunt cerebrovascular injury (BCVI) is a rare finding in trauma patients. The previously validated BCVI (Denver and Memphis) prediction model in adult patients was shown to be inadequate as a screening option in injured children. We sought to improve the detection of BCVI by developing a prediction model specific to the pediatric population.
Methods:
The National Trauma Databank (NTDB) was queried from 2007 to 2015. Test and training datasets of the total number of patients (885,100) with complete ICD data were used to build a random forest model predicting BCVI. All ICD features not used to define BCVI (2268) were included within the random forest model, a machine learning method. A random forest model of 1000 decision trees trying 7 variables at each node was applied to training data (50% of the dataset, 442,600 patients) and validated with test data in the remaining 50% of the dataset. In addition, Denver and Memphis model variables were re-validated and compared to our new model.
Results:
A total of 885,100 pediatric patients were identified in the NTDB to have experienced blunt pediatric trauma, with 1,998 (0.2%) having a diagnosis of BCVI. Skull fractures (OR 1.004, 95% CI 1.003-1.004), extremity fractures (OR 1.001, 95% 1.0006-1.002), and vertebral injuries (OR 1.004, 95% CI 1.003-1.004) were associated with increased risk for BCVI. The BCVI prediction model identified 94.4% of BCVI patients and 76.1% of non-BCVI patients within the NTDB. This study identified ICD9/ICD10 codes with strong association to BCVI. The Denver and Memphis criteria were re-applied to NTDB data to compare validity and only correctly identified 13.4% of total BCVI patients and 99.1% of non BCVI patients.
Conclusion:
The prediction model developed in this study is able to better identify pediatric patients who should be screened with further imaging to identify BCVI.
Level Of Evidence:
Retrospective diagnostic study-level III evidence.
