129 Development and External Validation of the KIIDS-TBI Tool for Managing Children with Mild Traumatic Brain Injury and Intracranial Injuries

Abstract

INTRODUCTION: Clinical decision support may improve the post-neuroimaging management of children with mild traumatic brain injuries (mTBI) and intracranial injuries. While the CHIIDA score has been proposed for this purpose, a more sensitive risk model may have broader use. METHODS: We analyzed children <18 years-old with mTBI and intracranial injuries included in the PECARN head injury dataset (2004-2006). We used binary recursive partitioning to predict the composite outcome of neurosurgical intervention, intubation for >24 hours due to TBI, or death due to TBI. The new model, the KIIDS-TBI model, was externally validated in a separate dataset that included children treated between 2006-2019 at one of six centers participating in the pediatric TBI Research Consortium (PTRC). RESULTS: There were 839 children included in the derivation (PECARN) and 1,630 in the validation (PTRC) datasets. Derived using the PECARN dataset, the KIIDS-TBI model incorporated imaging (e.g. midline shift) and clinical (e.g. GCS score) findings. Based on the model-predicted probability of the composite outcome, three cutoffs were evaluated in the external validation (PTRC) dataset to classify patients as ‘high risk.' The most conservative cutoff (i.e. any predictor present) identified 119/119 children with the composite outcome (sensitivity 100%), but had the lowest specificity (26.3%). The other two cutoffs had worse sensitivity (94.1%-96.6%) but improved specificity (67.4%-81.3%). The CHIIDA model lacked the most conservative cutoff and otherwise showed the same or slightly worse performance compared to the other two cutoffs. CONCLUSION: The KIIDS-TBI model has high sensitivity and moderate specificity for risk-stratifying children with mTBI and intracranial injuries. Use of this clinical decision support tool may help improve the safe, resource-efficient management of this important patient population.