A compression-enabled approach to analyze seizures for people with refractory epilepsy
Abstract/Contents
- Abstract
- This dissertation presents an information theoretic measure called the inverse compression ratio (ICR)—an unbiased estimate of joint entropy (measure of signal complexity)—and demonstrates its potential for seizure detection. First, a minimally disruptive, scalable platform to acquire 10 kHz research-quality, intracranial EEG (iEEG) in a hospital setting was deployed to build the Brain Interfacing Laboratory iEEG repository. Second, ICR was implemented using the DEFLATE algorithm (a time independent and lossless encoder), and it outperformed other conventional, model-free algorithms. Third, leveraging video compressors, it was determined that some degrees of time dependence and lossiness in the compression encoding can improve ICR performance for seizure detection. Finally, when quantifying seizure detection performance, positive-centric performance metrics—those that ignore true negatives (e.g., area under the precision-recall curve)—were found to be more informative than others. Compression-enabled measures, without linear assumptions or parametric modeling, provide a promising direction for qEEG analyses.
Description
Type of resource | text |
---|---|
Form | electronic resource; remote; computer; online resource |
Extent | 1 online resource. |
Place | California |
Place | [Stanford, California] |
Publisher | [Stanford University] |
Copyright date | 2023; ©2023 |
Publication date | 2023; 2023 |
Issuance | monographic |
Language | English |
Creators/Contributors
Author | Yamada, Lisa |
---|---|
Degree supervisor | Nuyujukian, Paul Herag |
Thesis advisor | Nuyujukian, Paul Herag |
Thesis advisor | Nishimura, Dwight George |
Thesis advisor | Weissman, Tsachy |
Degree committee member | Nishimura, Dwight George |
Degree committee member | Weissman, Tsachy |
Associated with | Stanford University, School of Engineering |
Associated with | Stanford University, Department of Electrical Engineering |
Subjects
Genre | Theses |
---|---|
Genre | Text |
Bibliographic information
Statement of responsibility | Lisa Yamada. |
---|---|
Note | Submitted to the Department of Electrical Engineering. |
Thesis | Thesis Ph.D. Stanford University 2023. |
Location | https://purl.stanford.edu/sr482rc2034 |
Access conditions
- Copyright
- © 2023 by Lisa Yamada
Also listed in
Loading usage metrics...