Close
This site uses cookies

By using this site, you consent to our use of cookies. You can view our terms and conditions for more information.

Return to Session

Classification of sleep stages with high frequency oscillations

Authors
Dr. Michael D. Nunez
University of California, Los Angeles ~ Psychiatry and Biobehavioral Sciences
Krit Charupanit
N/A
Indranil Sen-Gupta
N/A
Jack Lin
N/A
Beth Lopour
N/A
Abstract

High frequency oscillations (HFOs) have been empirically found in intracranial recordings and the frequency of these discrete events can help localize epileptic tissue for surgical resection. Using long-term intracranial EEG from 16 subjects, we fit Poisson and Negative Binomial mixture models that describe HFO dynamics and include the ability to switch between two discrete brain states. Oscillatory dynamics of HFO occurrences were found to be predictive of sleep state such that these model-found brain states corresponded to (1) non-REM (NREM) sleep and (2) awake and rapid eye movement (REM) sleep in two patients. In patients without expert sleep-staged data, one model-found brain state had significantly larger delta (1 - 4 Hz) power in 8/16 patients (p < .001), further suggesting that latent brain states based on HFO dynamics can predict sleep state. Parameters in each latent brain state that describe the HFO rate and clumping dynamics can be used to predict seizure onset zone (SOZ) in patients. We discuss future directions and improvements for mixture modeling of HFO dynamics. This work suggests that classification of epileptic tissue without sleep-staging can be developed using mixture modeling of HFO dynamics.

Tags

Keywords

Neurocognitive modeling
Bayesian modeling
sleep
epilepsy
high-frequency oscillations (HFOs)

Topics

Cognitive Modeling
Bayesian Modeling
Cognitive Neuromodeling
Discussion
New

Hi Michael, cool stuff! I was wondering how your methods compare to existing sleep stage and seizure onset classification. I know very little about these fields but I do know they have been working on that for years. How does your model improve on that? Is the Hierarchical bayes the key factor? Or something else?

Marieke Van Vugt 1 comment

Thanks for your talk Michael it's really nice to see hierarchical Bayesian neural modeling applied to patient data. I have a question about this application. The core idea is to use hierarchical methods which to me, when working with patient data, both seems a blessing (as we usually have scarce data) but also a curse. The hypothetical curse, ba...

Mr. Gabriel Weindel 3 comments