Shift-invariant waveform learning on epileptic ECoG

TL;DR

This paper introduces a shift-invariant waveform learning method using k-means clustering on ECoG data to identify physiologically meaningful patterns for seizure prediction, improving interpretability and classification accuracy.

Contribution

The study presents a novel shift-invariant k-means approach to discover recurrent waveforms in ECoG data for seizure prediction, enhancing interpretability and physiological relevance.

Findings

Identified recurrent non-sinusoidal waveforms associated with seizures

Waveforms serve as interpretable features for seizure prediction

Method achieves meaningful classification performance

Abstract

Seizure detection algorithms must discriminate abnormal neuronal activity associated with a seizure from normal neural activity in a variety of conditions. Our approach is to seek spatiotemporal waveforms with distinct morphology in electrocorticographic (ECoG) recordings of epileptic patients that are indicative of a subsequent seizure (preictal) versus non-seizure segments (interictal). To find these waveforms we apply a shift-invariant k-means algorithm to segments of spatially filtered signals to learn codebooks of prototypical waveforms. The frequency of the cluster labels from the codebooks is then used to train a binary classifier that predicts the class (preictal or interictal) of a test ECoG segment. We use the Matthews correlation coefficient to evaluate the performance of the classifier and the quality of the codebooks. We found that our method finds recurrent non-sinusoidal waveforms that could be used to build interpretable features for seizure prediction and that are also physiologically meaningful.