A Time-Series Scale Mixture Model of EEG with a Hidden Markov Structure for Epileptic Seizure Detection

TL;DR

This paper introduces a novel time-series scale mixture model with a hidden Markov structure for EEG-based epileptic seizure detection, capturing stochastic covariance fluctuations and temporal state transitions.

Contribution

It presents a new probabilistic model combining scale mixtures and Markov chains to improve seizure detection accuracy in EEG signals.

Findings

High sensitivity seizure detection achieved

Outperforms baseline models

Effective across multiple EEG frequency bands

Abstract

In this paper, we propose a time-series stochastic model based on a scale mixture distribution with Markov transitions to detect epileptic seizures in electroencephalography (EEG). In the proposed model, an EEG signal at each time point is assumed to be a random variable following a Gaussian distribution. The covariance matrix of the Gaussian distribution is weighted with a latent scale parameter, which is also a random variable, resulting in the stochastic fluctuations of covariances. By introducing a latent state variable with a Markov chain in the background of this stochastic relationship, time-series changes in the distribution of latent scale parameters can be represented according to the state of epileptic seizures. In an experiment, we evaluated the performance of the proposed model for seizure detection using EEGs with multiple frequency bands decomposed from a clinical dataset. The results demonstrated that the proposed model can detect seizures with high sensitivity and outperformed several baselines.