Manifold-valued models for analysis of EEG time series data

TL;DR

This paper introduces a Riemannian manifold-based model for EEG time series data, capturing dynamics related to epilepsy, and compares different geometric approaches to improve interpretability and fit.

Contribution

It develops a novel manifold-valued model for EEG data, incorporating interpretable parameters and comparing Euclidean and affine invariant geometries for better modeling of epilepsy dynamics.

Findings

Affine invariant geometry provides a better data fit.

Distinct EEG dynamics characterize seizures and interictal periods.

Model distinguishes between epileptic seizures and interictal states.

Abstract

We propose a model for time series taking values on a Riemannian manifold and fit it to time series of covariance matrices derived from EEG data for patients suffering from epilepsy. The aim of the study is two-fold: to develop a model with interpretable parameters for different possible modes of EEG dynamics, and to explore the extent to which modelling results are affected by the choice of manifold and its associated geometry. The model specifies a distribution for the tangent direction vector at any time point, combining an autoregressive term, a mean reverting term and a form of Gaussian noise. Parameter inference is carried out by maximum likelihood estimation, and we compare modelling results obtained using the standard Euclidean geometry on covariance matrices and the affine invariant geometry. Results distinguish between epileptic seizures and interictal periods between seizures in patients: between seizures the dynamics have a strong mean reverting component and the autoregressive component is missing, while for the majority of seizures there is a significant autoregressive component and the mean reverting effect is weak. The fitted models are also used to compare seizures within and between patients. The affine invariant geometry is advantageous and it provides a better fit to the data.