Modeling the complex dynamics and changing correlations of epileptic events

DOI10.1016/J.ARTINT.2014.05.006zbMATH Open1408.92011arXiv1402.6951OpenAlexW2015875947WikidataQ42686536 ScholiaQ42686536MaRDI QIDQ460608FDOQ460608

Authors: Drausin F. Wulsin, Emily B. Fox, Brian Litt 

Publication date: 13 October 2014

Published in: Artificial Intelligence (Search for Journal in Brave)

Abstract: Patients with epilepsy can manifest short, sub-clinical epileptic "bursts" in addition to full-blown clinical seizures. We believe the relationship between these two classes of events---something not previously studied quantitatively---could yield important insights into the nature and intrinsic dynamics of seizures. A goal of our work is to parse these complex epileptic events into distinct dynamic regimes. A challenge posed by the intracranial EEG (iEEG) data we study is the fact that the number and placement of electrodes can vary between patients. We develop a Bayesian nonparametric Markov switching process that allows for (i) shared dynamic regimes between a variable number of channels, (ii) asynchronous regime-switching, and (iii) an unknown dictionary of dynamic regimes. We encode a sparse and changing set of dependencies between the channels using a Markov-switching Gaussian graphical model for the innovations process driving the channel dynamics and demonstrate the importance of this model in parsing and out-of-sample predictions of iEEG data. We show that our model produces intuitive state assignments that can help automate clinical analysis of seizures and enable the comparison of sub-clinical bursts and full clinical seizures.

Full work available at URL: https://arxiv.org/abs/1402.6951

Recommendations

• Nonparametric multi-level clustering of human epilepsy seizures
• Nonstationarity in epileptic EEG and implications for neural dynamics
• Evolving Network Model That Almost Regenerates Epileptic Data
• Statistical information approaches for the modelling of the epileptic brain
• Epilepsziás agyi hálózatok egysejt-aktivitásának jellemzése Hawkes-folyamatok segítségével

zbMATH Keywords

time seriesgraphical modelEEGBayesian nonparametricfactorial hidden Markov model

Mathematics Subject Classification ID

Applications of statistics to biology and medical sciences; meta analysis (62P10) Medical applications (general) (92C50) Software, source code, etc. for problems pertaining to biology (92-04)

Cites Work

• Multivariate time series modeling and classification via hierarchical VAR mixtures
• Reversible jump Markov chain Monte Carlo computation and Bayesian model determination
• Title not available (Why is that?)
• Title not available (Why is that?)
• Hyper Markov laws in the statistical analysis of decomposable graphical models
• Handbook of Markov Chain Monte Carlo
• A sticky HDP-HMM with application to speaker diarization
• Hierarchical Dirichlet Processes
• Exact and approximate sum representations for the Dirichlet process
• Simulation of hyper-inverse Wishart distributions in graphical models
• Factorial hidden Markov models

Cited In (9)

• Cooperative hierarchical Dirichlet processes: superposition vs. maximization
• A Bayesian nonparametric model for multi-label learning
• Nonparametric multi-level clustering of human epilepsy seizures
• Onset of polyspike complexes in a mean-field model of human electroencephalography and its application to absence epilepsy
• Evolving Network Model That Almost Regenerates Epileptic Data
• Computational Sensitivity Analysis on a Mathematical Model of Epileptic Seizures
• The Convex Mixture Distribution: Granger Causality for Categorical Time Series
• Synaptic plasticity based model for epileptic seizures
• Epilepsziás agyi hálózatok egysejt-aktivitásának jellemzése Hawkes-folyamatok segítségével

Uses Software

• BayesDA

This page was built for publication: Modeling the complex dynamics and changing correlations of epileptic events

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q460608)