Kocanaogullari, Deniz
(2024)
Detection and Assessment of Spatial Neglect Using a Novel Augmented Reality-Guided Eeg-Based Brain-Computer Interface.
Doctoral Dissertation, University of Pittsburgh.
(Unpublished)
Abstract
Spatial neglect (SN) is a prevalent visuospatial attention disorder caused by stroke, typically from unilateral brain injuries. SN causes inattention to the contralesional space. Traditional neglect detection methods like the Behavioral Inattention Test - Conventional (BIT-C) lack the capability to assess the full extent and severity of neglect. Additionally, functional neglect assessments like Catherine Bergego Scale (CBS) do not provide information about the specific field of view affected by SN, even though they provide valuable clinical information. These shortcomings show that there is a clear need to have a more reliable and robust tool for SN assessments. BCI systems establish a communication link between an individual and their surroundings, facilitating interaction in both healthcare and non-healthcare contexts. EEG is heavily used in BCI systems due to their effectiveness, non-invasive nature and ease-of-use. Virtual reality (VR) systems have been shown to detect SN, but do not provide a real-life environment where there are distractors.
To overcome the shortcomings of classical tests and to provide a robust SN assessment tool, a novel brain-computer interface (BCI) that incorporates augmented reality (AR) headsets and electroencephalography (EEG) is developed, known as AR-based EEG-guided Neglect Detection, Assessment and Rehabilitation System (AREEN). A combined dataset comprising of 38 subjects from both AREEN and its precursor, Computer-based BCI, is used in various analyses. The goal of the system is to detect and assess the severity of spatial neglect in a plug-and-play manner, with little to no calibration to individual patients. Additionally, neglect detection and severity assessment tasks are addressed, providing (i) successful machine learning modalities to detect neglect and assess the severity of neglect through field of view (FOV) estimation and (ii) features that are informative about the nature of SN.
Share
| Citation/Export: |
|
| Social Networking: |
|
Details
| Item Type: |
University of Pittsburgh ETD
|
| Status: |
Unpublished |
| Creators/Authors: |
|
| ETD Committee: |
|
| Date: |
6 September 2024 |
| Date Type: |
Publication |
| Defense Date: |
2 July 2024 |
| Approval Date: |
6 September 2024 |
| Submission Date: |
22 July 2024 |
| Access Restriction: |
No restriction; Release the ETD for access worldwide immediately. |
| Number of Pages: |
109 |
| Institution: |
University of Pittsburgh |
| Schools and Programs: |
Swanson School of Engineering > Electrical and Computer Engineering |
| Degree: |
PhD - Doctor of Philosophy |
| Thesis Type: |
Doctoral Dissertation |
| Refereed: |
Yes |
| Uncontrolled Keywords: |
spatial neglect, machine learning, signal processing |
| Date Deposited: |
06 Sep 2024 20:04 |
| Last Modified: |
06 Sep 2024 20:04 |
| URI: |
http://d-scholarship.pitt.edu/id/eprint/46718 |
Metrics
Monthly Views for the past 3 years
Plum Analytics
Actions (login required)
 |
View Item |
![[feed]](/images/feed-icon-32x32.png){kind=icon}