A Quantitative Approach to the Diagnosis of Head Injuries Through a Spatio-Temporal Model of the Electrophysiological Assessment of Working Memory

• Activity Number: 243
• Type: Contributed
• Date/Time: Monday, August 4, 2014 : 2:00 PM to 3:50 PM
• Sponsor: Section on Statistics in Imaging
• Author(s): Pavel Chernyavskiy*+ and Caitlin M. Hudac and Dennis L. Molfese and David B. Marx
• Companies: University of Nebraska-Lincoln and University of Nebraska-Lincoln and University of Nebraska-Lincoln and University of Nebraska
• Keywords: spatio-temporal ; brain injuries ; space-time ; TBI ; ERP

Abstract

National awareness of traumatic brain injuries (TBI) is increasing given higher prevalence in both military and athletic settings. TBI affects both short-term and long-term brain and behavior mechanisms associated with cognitive deficits. Unfortunately, a quantitative approach to the identification and diagnosis of TBI has not yet been established. In this paper, authors use a spatio-temporal sum-metric model to represent electrophysiological assessments of working memory in college athletes. Athlete-specific parameter estimates are then used to evaluate two classification algorithms: Quadratic Discriminant Analysis and Nearest-k Neighbors in accurately predicting brain injuries. First, we demonstrate that a sum-metric model can be used to describe electrophysiological brain response in both temporal and spatial domains (i.e. across electrode locations). Second, we provide spatio-temporal profiles of injured and uninjured athletes. Finally, we show that both classifiers accurately predict head injuries using our estimated model parameters.