Related Experiment Video
Updated: Sep 11, 2025
A Pediatric Concussion Model in Mice: Closed Head Injury with Long-Term Disorders (CHILD)
Published on: February 7, 2025
Outcome Prediction in Pediatric Traumatic Brain Injury Utilizing Social Determinants of Health and Machine Learning
Artem Kaliaev1, Maryam Vejdani-Jahromi2, Adrian Gunawan3
1From the Radiology Department of Boston University Medical Center (A.K., M.Q., M.A., B.N.S., C.F., A.M.), Boston, Massachusetts artem.kaliaev@bmc.org.
Insights
Social determinants of health significantly impact pediatric traumatic brain injury (TBI) outcomes. A machine learning algorithm using factors like age and insurance type accurately predicts head CT findings, aiding clinical decisions.
Area of Science:
- Pediatric Traumatic Brain Injury (TBI) research
- Medical Machine Learning Applications
- Public Health and Health Disparities
Background:
- Socioeconomic disparities significantly affect pediatric patients with traumatic brain injury (TBI).
- Understanding social determinants of health is crucial for improving TBI outcomes.
- Existing research highlights disparities in healthcare access and outcomes for pediatric TBI.
Purpose of the Study:
- To analyze the impact of social determinants of health on pediatric head injury outcomes.
- To develop a novel machine learning algorithm (MLA) for predicting head computed tomography (CT) findings in pediatric TBI.
- To incorporate socioeconomic factors into predictive models for pediatric head CT results.
Main Methods:
- Retrospective cohort study of 211 pediatric blunt trauma patients at a New England safety net hospital (2006-2013).
- Collected socioeconomic data (race, language, income, insurance) and clinical data (ISS, age, sex, mechanism).
- Trained and evaluated 22 multi-parametric MLAs using stratified sampling, 5-fold cross-validation, and hyperparameter tuning.
Main Results:
- Injury Severity Score (ISS), age, and insurance type were significant predictors of head CT outcomes (p<0.05).
- Children under 5 years old had a higher median age (1.8 years) with positive head CT findings compared to those without (9.1 years).
- A Fine Gaussian Support Vector Machine (SVM) model achieved the highest test Area Under the Curve (AUC) of 0.923 with an accuracy of 0.837.
Conclusions:
- Key predictors for clinically relevant head CT findings in pediatric TBI include ISS, age, and social determinants of health.
- Children under five years old are identified as a higher-risk group for significant head CT findings.
- A novel Fine Gaussian SVM model demonstrates high accuracy in predicting pediatric TBI outcomes, potentially improving clinical decision-making and reducing radiation exposure.
Background And Purpose:
Considerable socioeconomic disparities exist among pediatric patients with traumatic brain injury (TBI). This study aims to analyze the effects of social determinants of health on head injury outcomes and to create a novel machine-learning algorithm (MLA) that incorporates socioeconomic factors to predict the likelihood of a positive or negative trauma-related finding on head CT.
Materials And Methods:
A cohort of patients with blunt trauma younger than age 15 who presented to the largest safety net hospital in New England between January 2006 and December 2013 (n=211) was included in this study. Patient socioeconomic data such as race, language, household income, and insurance type were collected alongside other parameters like Injury Severity Score (ISS), age, sex, and mechanism of injury. Multivariable analysis was performed to identify significant factors in predicting a positive head CT outcome. The cohort was split into 80% training (168 samples) and 20% testing (43 samples) data sets by using stratified sampling. Twenty-two multiparametric MLAs were trained with 5-fold cross-validation and hyperparameter tuning via GridSearchCV, and top-performing models were evaluated on the test data set.
Results:
Significant factors associated with pediatric head CT outcome included ISS, age, and insurance type (P < .05). The age of the subjects with a clinically relevant trauma-related head CT finding (median = 1.8 years) was significantly different from the age of patients without such findings (median = 9.1 years). These predictors were utilized to train the machine learning models. With ISS, the fine Gaussian support vector machine (SVM) achieved the highest test AUC (0.923), with accuracy = 0.837, sensitivity = 0.647, and specificity = 0.962. The coarse tree yielded accuracy = 0.837, AUC = 0.837, sensitivity = 0.824, and specificity = 0.846. Without ISS, the narrow neural network performed best with accuracy = 0.837, AUC = 0.857, sensitivity = 0.765, and specificity = 0.885.
Conclusions:
Key predictors of clinically relevant head CT findings in pediatric TBI include ISS, age, and social determinants of health, with children younger than 5 at higher risk. A novel fine Gaussian SVM model outperformed other MLAs, offering high accuracy in predicting outcomes. This tool shows promise for improving clinical decisions while minimizing radiation exposure in children.
