The Intrinsic Value of HFO Features As A Biomarker of Epileptic Activity

Abstract

High frequency oscillations (HFOs) are a promising biomarker of epileptic brain tissue and activity. HFOs additionally serve as a prototypical example of challenges in the analysis of discrete events in high-temporal resolution, intracranial EEG data. Two primary challenges are 1) dimensionality reduction, and 2) assessing feasibility of classification. Dimensionality reduction assumes that the data cluster in features space around a lower-dimensional manifold. However, previous HFO analysis have assumed a linear manifold, global across time, space (i.e. recording electrode/channel), and individual patients. We instead provide a protocol for assessing both a) the appropriateness of linear methods and b) consistency of the manifold across time, space, and patients. Additionally, we utilize bounds on the Bayes classification error to quantify the distinction between two classes HFOs (those occurring during seizures and those occurring due to other processes). This analysis not only provides the foundation for future clinical use of HFO features, but guides the analysis for other discrete events, such as individual action potentials or multi-unit activity.