Machine Learning with Objective Serum Markers and Algorithmic Deep Learning Computed Tomography Scan Analysis for Classification of Brain Injury

BackgroundBrain injury is pathophysiologically diverse, with many cases presenting with mixed pathologies. Utilizing objective measures to investigate the pathophysiology of injury would aid in understanding prognosis and targeting therapeutics. ObjectiveThe goal of this study is to develop a traumatic brain injury classification scheme based on open source deep learning computer tomography (CT) analysis and the two serum biomarkers, glial fibrillary acidic protein (GFAP) and ubiquitin carboxy-terminal L1 (UCH-L1). MethodsMachine learning was utilized to develop a novel algorithm capable of classifying the type of brain injury based on a CT scan analysis algorithm and GFAP and UCH-L1 concentrations. Injury was stratified into one of four groups: spontaneous hemorrhage, oxygen deprivation, trauma resulting in vascular injury or high-velocity trauma with negative CT scan. Outcomes100 research subjects were enrolled. Using a combination of CT analysis and serum markers, the subjects with CT positive trauma were distinguishable from those with spontaneous hemorrhage, ischemic injury, CT negative trauma and controls with AUCs of 0.96, 0.99., 0.98 and 1.00 respectively. Ischemic injury was distinguishable from CT positive trauma with an AUC of 0.98. All forms of brain injury could be distinguished from controls with AUC = 1.00. DiscussionAn open source algorithmic CT scan analysis algorithm and serum biomarkers accurately classified the nature of brain injury across major etiologies. Further implementation of such algorithms and addition of other objective measures will enable better prognostication of injury and improved development of therapeutics.