In the United States, 2.8 million people every year seek medical attention for traumatic brain injury (TBI), of which 80% are considered to have a mild TBI (i.e. concussion). Even in those with mild injuries, 10-20% of individuals will suffer long-term disability including seizures and emotional and behavioral issues. One of the primary challenges in TBI care is appropriately classifying this heterogeneous injury and identifying patients at risk for these chronic impairments. Conventional imaging studies, including magnetic resonance imaging (MRI) and computed tomography (CT), are commonly used to classify TBI, but do not reliably capture the full extent of the injury, particularly in those patients with mild injuries. Currently, there are few molecular markers to assist in the assessment of an individual's unique injury and subsequent recovery and biomarkers are desperately needed in the field that correlate with these varied endophenotypes, track the progress of the disease, and predict clinical outcomes. To address this challenge, we propose to develop a microchip-based platform that can be used to characterize TBI and its recovery using the RNA cargo found in brain-derived circulating extracellular vesicles (EVs), including exosomes. Unlike prior work that has mainly focused on single biomarkers, our approach measures a panel of circulating EV miRNA markers processed with machine learning algorithms, to more comprehensively capture the state of the injured and recovering brain. Our proposal combines surface marker-specific nanomagnetic isolation of brain-derived EVs from a variety of cell types, biomarker discovery using RNA sequencing, and machine learning processing of EV miRNA cargo to measure the state of injury and recovery in TBI.