You are hereEpilepsy: Automatic Seizure Detection and Focus Localization for Drug-Resistant Patients
Epilepsy: Automatic Seizure Detection and Focus Localization for Drug-Resistant Patients
Epilepsy affects 50 million people worldwide, and 30% remain drug-resistant. This has increased interest in both chronic and responsive neurostimulation, which is most effective when administered at or near the foci and immediately prior to or at the seizure onset. Precise focus localization and automatic online seizure detection (AOSD) from intracranial EEG (iEEG) recordings are therefore critical for closed-loop intervention, but remain challenging problems. Automated localization schemes have primarily been developed using univariate and bivariate features but lack consistency and accuracy. Several AOSD algorithms has been proposed thus far (to name only a few) and though they are highly sensitive (large number of true positives), these algorithms generally have low specificity (large number of false positives), which limits their clinical use. The lack of specificity presumably occurs because (i) they compute statistics from a few channels at a time which may not capture network dynamics of the brain, (ii) the channels used may be too far from the focus, and/or (iii) the detection thresholds are not explicitly optimized to maximize AOSD performance.
This program proposes a novel computational framework for seizure foci localization and AOSD that involves (i) constructing multivariate statistics from all electrodes to localize foci and distinguish between non-ictal vs. ictal states; (ii) modeling the evolution of these statistics in each state and the state-transition probabilities; and, (iii) developing an optimal model-based strategy to detect transitions to ictal states from sequential neural measurements. This strategy is formulated as the Bayesian “Quickest Detection” (QD) of the seizure onset, is solved via control optimization tools, and explicitly minimizes both the distance between detected and unequivocal onset times and the probability of false positives. Our team of clinicians and engineers will combine state of the art tools from matrix theory, system identification, and control theory to construct this framework using iEEG recordings from epilepsy patients.
This work is done in collaboration with Drs Nathan Crone and Stan Anderson at Johns Hopkins Hospital, and Drs John Gale and Jorge Gonzalez-Martinez at the Cleveland Clinic.