Machine Learning with Objective Serum Markers and Algorithmic Deep Learning CT Scan Analysis Predicts Brain Death Due to Trauma and Hypoxia

Prediction of which traumatic and hypoxic brain injuries will progress to brain death is currently based predominantly on history, physical examination and radiographic findings. We investigated how accurately purely objective measures including three neurologic serum markers and algorithmic CT (computed tomograph) scan analysis can predict brain death and differentiate its etiology.This prospective observational study enrolled 51 isolated trauma subjects and 19 clinically brain dead subjects that were further divided by mechanism of injury into high-velocity trauma with presumed diffuse axonal injury, cardiopulmonary/respiratory arrest, and found down groups. Levels of glial fibrillary acidic protein (GFAP), ubiquitin carboxy-terminal hydrolase L1 (UCH-L1), and S100 Calcium-Binding Protein B (S100B) were compared, and algorithmic analysis of CT scan imaging was performed using an open-source deep learning software (BLAST-CT).The prognostic value of various biomarker combinations in identifying subjects progressing to brain death was assessed using machine learning. Prediction accuracy for GFAP, UCH-L1, and S100B and algorithmic CT analysis in combination to predict brain death from among all other cohorts yielded an area under the receiver operator curve of 0.98 versus all other brain injury subjects. This model was also able to distinguish brain death attributed to cardiopulmonary/respiratory arrest from combined non-trauma controls and diffuse axonal injury with an area under the curve of 0.99.Serum concentrations of GFAP, UCH-L1, and S100B measured within 32 hours of traumatic and hypoxic brain injury (cardiopulmonary/respiratory arrest) and algorithmic CT analysis have utility in prognosticating brain death and predicting its mechanism of injury as either hypoxic or traumatic/unknown (diffuse axonal injury/found down).Abbott Labs and the Minnesota State Office of Higher Education.