PHILADELPHIA – ” according to a study presented at the annual meeting of the American Academy of Neurology.
Traumatic brain injury (TBI) damages brain tissue and causes subsequent volume loss, which may result in clinical symptoms. It is a prevalent worldwide health problem caused by a mechanical insult to the head, resulting in transient or permanent alteration to brain tissue and/or function. Standard neuroimaging with computerized cranial tomography (CT) and structural magnetic resonance imaging (MRI) is often unrevealing during the evaluation of patients with TBI, particularly those classified as mild TBI. I
In this study, James Rock, MD, of Penn Presbyterian Medical Center and the University of Pennsylvania, and his colleagues sought to examine the value of quantitative analysis of regional brain volumes in the evaluation of TBI. The investigators reviewed the medical records and MRI imaging from 44 patients with TBI evaluated at a Level I trauma center. They also read clinical notes to assess reported symptoms and physical findings.
Regional volumes from TBI subjects were derived using the software package Freesurfer image analysis suite, which utilizes a T1-weighted structural scan to calculate volumetric information. A machine learning algorithm, random forests, was employed across volume measurements from 25 regions of interest to determine the most important regions for classifying subjects based on clinical outcome and symptomology.
Basal ganglia volume showed the highest variable importance with regards to classifying subjects who exhibited symptoms of cognitive dysfunction (Mean Decrease in Gini = 1.067, Mean Decrease in Accuracy = 5.966e-03) in quantitative analysis. Left lateral ventricle volume was important in classifying subjects with motor and vestibular alterations (Mean Decrease in Gini = 2.037, Mean Decrease in Accuracy = 2.92e-02). Left choroid plexus volume was the most important region for classifying subjects with sensation and somatic dysfunction (Mean Decrease in Gini = 0.271, Mean Decrease in Accuracy = 4.82e-03).
The researchers noted that their study is ongoing, in an abstract. “It will be extended to a larger cohort to determine whether volume changes in specific [regions of interest] can act as useful clinical biomarkers for chronic symptoms,” they said.
Dr. Diaz-Arrastia received personal compensation from Neural Analytics, Inc, BrainBox Solutions, Inc, and Bioscience Pharma Partners. Dr. Diaz-Arrastia holds stock and/or stock options in Neural Analytics, Inc. and has received research support from BrainBox Solutions. The other authors reported not having anything to disclose..
SOURCE: Rock J et al. AAN 2019. Abstract S2.006 .