Resting state EEG microstate profiling and a machine-learning based classifier model in epilepsy

Abstract

Electroencephalography-based (EEG) microstate analysis is a promising and widely studied method in which spontaneous cerebral activity is segmented into sub second level quasi-stable states and analyzed. Currently it is being widely explored due to increasing evidence of the association of microstates with cognitive functioning and large-scale brain networks identified by functional magnetic resonance imaging (fMRI). In our study using the four archetypal microstates (A, B, C and D), we investigated the changes in resting state EEG microstate dynamics in persons with temporal lobe epilepsy (TLE) and idiopathic generalized epilepsy (IGE) compared to healthy controls (HC). Machine learning was applied to study its feasibility in differentiating between different groups using microstate statistics. We found significant differences in all parameters related to Microstate D (fronto-parietal network) in TLE patients and Microstate B (visual processing) in IGE patients compared to HCs. Occurrence, duration and time coverage of Microstate B was highest in IGE when compared to the other groups. We also found significant deviations in transition probabilities for both epilepsy groups, particularly into Microstate C (salience network) in IGE. Classification accuracy into clinical groups was found to exceed 70% using microstate parameters which improved on incorporating neuropsychological test differences. To the best of our knowledge, the current study is the first to compare and validate the use of microstate features to discriminate between two disparate epilepsy syndromes (TLE, IGE) and HCs using machine learning suggesting that resting state EEG microstates can be used for endophenotyping and to study resting state dysfunction in epilepsy.

Supplementary information: The online version contains supplementary material available at 10.1007/s11571-024-10095-z.

Keywords: EEG microstates; Idiopathic generalized epilepsy; Machine learning; Resting-state EEG; Temporal lobe epilepsy.

Fig. 1

10 s eyes closed EEG data of a healthy control (notch filtered and band pass filtered 1–40 Hz) and corresponding GFP signal

Fig. 2

EEG microstates identified- phonological processing (Microstate A), visual processing (Microstate B), salience network (Microstate C) and fronto-parietal network related to attentional switching (Microstate D)

Fig. 3

Ten second eyes closed EEG data of a healthy control and corresponding GFP signal backfitted with the microstate prototypes

Fig. 4

Graphical Representation of microstate parameters

Fig. 5

A, B depict ROC curves using microstate parameters and microstate-neuropsychological parameters on TLE-HC comparisons respectively