Modeling the Complex Dynamics and Changing Correlations of Epileptic Events
This work addresses the challenge of modeling variable and correlated epileptic events in patients with epilepsy, offering a tool for automated clinical analysis, though it is incremental as it builds on existing Bayesian and graphical model techniques for a specific medical domain.
The authors tackled the problem of analyzing complex epileptic events, such as sub-clinical bursts and full seizures, by developing a Bayesian nonparametric Markov switching process to parse intracranial EEG data into distinct dynamic regimes, showing that the model produces intuitive state assignments for clinical analysis and enables comparison between event types.
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.