Date of Award

January 2017

Document Type


Degree Name

Master of Science (MS)


Electrical Engineering

First Advisor

Reza Fazel-Rezai


The neurocognitive sequelae of a sport-related concussion and its management are poorly defined. Emerging evidence suggests that the residual deficits can persist one year or more following a brain injury. Detecting and quantifying the residual deficits are vital in making a decision about the treatment plan and may prevent further damage. For example, improper return to play (RTP) decisions in sports such as football have proven to be associated with the further chance of recurring injury, long-term neurophysiological impairments, and worsening of brain functional activity.

The reliability of traditional cognitive assessment tools is debatable, and thus attention has turned to assessments based on electroencephalogram (EEG) to evaluate subtle post-concussive alterations. In this study, we calculated neurocognitive deficits in two different datasets. One dataset contains a combination of EEG analysis with three standard post-concussive assessment tools. The data for this dataset were collected for all testing modalities from 21 adolescent athletes (seven concussive and fourteen healthy) in three different trials. Another dataset contains post-concussion eyes closed EEG signal for twenty concussed and twenty age-matched controls. For EEG assessment, along with linear frequency-based features, we introduced a set of time-frequency and nonlinear features for the first time to explore post-concussive deficits. In conjunction with traditional frequency band analysis, we also presented a new individual frequency based approach for EEG assessment. A set of linear, time-frequency and nonlinear EEG markers were found to be significantly different in the concussed group compared to their matched peers in the healthy group. Although EEG analysis exhibited discrepancies, none of the cognitive assessment resulted in significant deficits. Therefore, the evidence from the study highlight that our proposed EEG analysis and markers are more efficient at deciphering post-concussion residual neurocognitive deficits and thus has a potential clinical utility of proper concussion assessment and management.

Moreover, a number of studies have clearly demonstrated the feasibility of supervised and unsupervised pattern recognition algorithms to classify patients with various health-related issues. Inspired by these studies, we hypothesized that a set of robust features would accurately differentiate concussed athletes from control athletes. To verify it, features such as power spectral, statistical, wavelet, and other nonlinear features were extracted from the EEG signal and were used as an input to various classification algorithms to classify the concussed individuals. Various techniques were applied to classify control and concussed athletes and the performance of the classifiers was compared to ensure the best accuracy. Finally, an automated approach based on meaningful feature detection and efficient classification algorithm were presented to systematically identify concussed athletes from healthy controls with a reasonable accuracy. Thus, the study provides sufficient evidence that the proposed analysis is useful in evaluating the post-concussion deficits and may be incorporated into clinical assessments for a standard evaluation of athletes after a concussion.