Date of Graduation

Spring 5-19-2017

Document Type


Degree Name

Master of Science in Health Informatics (MSHI)


School of Nursing and Health Professions

First Advisor

Dr. William Bosl


In this thesis, I will expand upon each step in the process of acquiring and analyzing electroencephalogram (EEG) for the classification of benign childhood epilepsy with centrotemporal spikes. Despite huge advancements in the field of health informatics—natural language processing, machine learning, predictive modeling—there are significant barriers to the access of clinical data. These barriers include information blocking, privacy policy concerns, and a lack of stakeholder support. We will see that these roadblocks are all responsible for stunting biomedical research in some way, including my own experiences in acquiring the data for the second chapter of this thesis.

This second chapter expands upon just one possible advancement that can be achieved when researchers attain clinical data (in this case, EEG data). BECTS is a type of epilepsy that only displays epileptiform activity on night-time EEGs. We hypothesize that a brain affected by BECTS is also developmentally different during the daytime, and based on this assumption, our analysis aims to uncover these electrodynamic distinctions. After course-graining raw EEG segments, we extracted sample entropy, recurrence rate, laminarity, and determinism using recurrence quantitative analysis. Our results displayed two major findings. First, awake BECTS and control patients can be classified with no overlap using all of these features. Second, BECTS patients show differences in sleep state RQA values from centrotemporal and non-centrotemporal regions. We cannot confirm if these differences display epileptiform activity, however, because we do not have controls for sleep studies. With proper development and implementation, this research has the potential to become a clinical decision support tool and decrease the need for inconvenient sleep studies.