Viability of Preictal High-Frequency Oscillation Rates as a Biomarker for Seizure Prediction

Jared M. Scott,Stephen V. Gliske,William C. Stacey,Levin Kuhlmann

doi:10.3389/fnhum.2020.612899

Abstract

Motivation: There is an ongoing search for definitive and reliable biomarkers to forecast or predict imminent seizure onset, but to date most research has been limited to EEG with sampling rates <1,000 Hz. High-frequency oscillations (HFOs) have gained acceptance as an indicator of epileptic tissue, but few have investigated the temporal properties of HFOs or their potential role as a predictor in seizure prediction. Here we evaluate time-varying trends in preictal HFO rates as a potential biomarker of seizure prediction.Methods: HFOs were identified for all interictal and preictal periods with a validated automated detector in 27 patients who underwent intracranial EEG monitoring. We used LASSO logistic regression with several features of the HFO rate to distinguish preictal from interictal periods in each individual. We then tested these models with held-out data and evaluated their performance with the area-under-the-curve (AUC) of their receiver-operating curve (ROC). Finally, we assessed the significance of these results using non-parametric statistical tests.Results: There was variability in the ability of HFOs to discern preictal from interictal states across our cohort. We identified a subset of 10 patients in whom the presence of the preictal state could be successfully predicted better than chance. For some of these individuals, average AUC in the held-out data reached higher than 0.80, which suggests that HFO rates can significantly differentiate preictal and interictal periods for certain patients.Significance: These findings show that temporal trends in HFO rate can predict the preictal state better than random chance in some individuals. Such promising results indicate that future prediction efforts would benefit from the inclusion of high-frequency information in their predictive models and technological architecture.

Highlights

One of the most debilitating aspects of epilepsy is the uncertainty patients feel, not knowing when the seizure will occur
To form our patient cohort, we looked at all patients with refractory epilepsy who had undergone intracranial EEG monitoring at the University of Michigan from 2016 to 2018
In order to ensure that sufficient data was available for training and testing our models, we required patients with the following: (1) a defined seizure onset zone, (2) at least three recorded seizures that were each preceded by non-zero high-frequency oscillations (HFOs) rates, and (3) the availability of at least 24 h of data; applying these criteria to the 32 available patients resulted in 27 patients

Summary

Introduction

One of the most debilitating aspects of epilepsy is the uncertainty patients feel, not knowing when the seizure will occur. Though seizures themselves account for an extremely small percentage of an individual’s time (Cook et al, 2013), the constant threat of a seizure can make the planning of normal day-to-day activities an impossibility for some (Bishop and Allen, 2003). This has led many investigators to search for methods to predict when seizure might occur (Mormann et al, 2005; Freestone et al, 2015, 2017; Gadhoumi et al, 2016; Kuhlmann et al, 2018a). The data have two important limitations: the data were acquired at low sampling rate (200 Hz) that does not allow analysis of high-resolution EEG signals, and more importantly, since the trial ended no similar chronic recordings have been collected

Methods

Results

Discussion

Conclusion