Leveraging electrophysiologic correlates of word encoding to map seizure onset zone in focal epilepsy: Task-dependent changes in epileptiform activity, spectral features, and functional connectivity

Individualized Seizure Cluster Prediction Using Machine Learning and Chronic Ambulatory Intracranial EEG

Epilepsy patients often experience acute repetitive seizures, known as seizure clusters, which can progress to prolonged seizures or status epilepticus if left untreated. Predicting the onset of seizure clusters is crucial to enable patients to receive preventative treatments. Additionally, studying the patterns of seizure clusters can help predict the seizure type (isolated or cluster) after observing a just occurred seizure. This paper presents machine learning models that use bivariate intracranial EEG (iEEG) features to predict seizure clustering. Specifically, we utilized relative entropy (REN) as a bivariate feature to capture potential differences in brain region interactions underlying isolated and cluster seizures. We analyzed a large ambulatory iEEG dataset collected from 15 patients and spanned up to 2 years of recordings for each patient, consisting of 3341 cluster seizures (from 427 clusters) and 369 isolated seizures. The dataset's substantial number of seizures per patient enabled individualized analyses and predictions. We observed that REN was significantly different between isolated and cluster seizures in majority of the patients. Machine learning models based on REN: 1) predicted whether a seizure will occur soon after a given seizure with up to 69.5% Area under the ROC Curve (AUC), 2) predicted if a seizure is the first one in a cluster with up to 55.3% AUC, outperforming baseline techniques. Overall, our findings could be beneficial in addressing the clinical burden associated with seizure clusters, enabling patients to receive timely treatments and improving their quality of life.

Uses and abuses of the neuropsychological assessment in the presurgical evaluation of epilepsy surgery candidates

•

Results from the neuropsychological assessment must be integrated into the wider clinical picture for all epilepsy surgery candidates.

•

Motivation for surgery must be fully explored to ensure informed consent, even in ‘ideal’ surgical candidates.

•

Inappropriate weight should not be given to standalone neuropsychological scores in the surgical decision making process.

Recent guidelines from the International League Against Epilepsy (ILAE) delineating the role of the neuropsychologist in the assessment of epilepsy surgery patients stress the collaborative contribution neuropsychologists should make to seizure characterization, lateralization and localization in the pre-surgical setting. The role they should play in the comprehensive counselling of surgical candidates, including exploration of the patient’s expectations of surgical treatment is also mandated. In this paper we present two contrasting case studies which illustrate the importance of these roles and the impact they can have on patient outcomes. In Case A we describe the patient journey of a 69-year-old women with left hippocampal sclerosis and concordant neurophysiology and seizure semiology. We present the series of discussions and decisions which led her to reject the surgical option following a detailed exploration of her motivations for surgery and the likely cognitive consequences of the procedure. In Case B we describe the series of errors and omissions which led to the failure of a clinical team to correctly interpret and integrate neuropsychological findings into the larger clinical picture of a 19-year-old woman with a seven year history of seizures. These errors ultimately culminated in the patient undergoing a right temporal lobe resection to treat psychogenic nonepileptic seizures (PNES).

The extent of integration of the data from the clinical neuropsychological assessment in the full presurgical evaluation was critical in determining the outcomes in both of these cases. Surgery did not solve Case B’s problems and left her with the lifelong cognitive vulnerabilities that are associated with unilateral temporal lobe resection. In contrast, Case A was a good surgical candidate, but comprehensive integration of the neuropsychological findings into the larger clinical picture established that surgery was not the best solution to the problem she wished to solve.