The intrinsic value of HFO features as a biomarker of epileptic activity

TL;DR

This paper investigates the intrinsic value of high frequency oscillation features as biomarkers for epileptic activity, examining the appropriateness of linear manifold assumptions and estimating classification bounds to enhance clinical utility.

Contribution

It assesses the validity of linear dimensionality reduction methods for HFO analysis and evaluates the consistency of the data manifold across various dimensions, providing a foundation for clinical application.

Findings

Linear methods may not always be appropriate for HFO data.

The manifold structure varies across time, space, and patients.

Bounds on Bayes classification error inform the distinguishability of HFO classes.

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 lie on a manifold with dimension less than that of the feature space. However, previous HFO analyses have assumed a linear manifold, global across time, space (i.e. recording electrode/channel), and individual patients. Instead, we assess both a) whether linear methods are appropriate and b) the consistency of the manifold across time, space, and patients. We also estimate bounds on the Bayes classification error to quantify the distinction between two classes of HFOs (those occurring during seizures and those occurring due to other processes). This analysis provides the foundation for future clinical use of HFO features and buides the analysis for other discrete events, such as individual action potentials or multi-unit activity.