Decoding working memory task condition using magnetoencephalography source level long-range phase coupling patterns

Abstract

Objective. The objective of the study is to identify phase coupling patterns that are shared across subjects via a machine learning approach that utilises source space magnetoencephalography (MEG) phase coupling data from a working memory (WM) task. Indeed, phase coupling of neural oscillations is putatively a key factor for communication between distant brain areas and is therefore crucial in performing cognitive tasks, including WM. Previous studies investigating phase coupling during cognitive tasks have often focused on a few a priori selected brain areas or a specific frequency band, and the need for data-driven approaches has been recognised. Machine learning techniques have emerged as valuable tools for the analysis of neuroimaging data since they catch fine-grained differences in the multivariate signal distribution. Here, we expect that these techniques applied to MEG phase couplings can reveal WM-related processes that are shared across individuals. Approach. We analysed WM data collected as part of the Human Connectome Project. The MEG data were collected while subjects (n = 83) performed N-back WM tasks in two different conditions, namely 2-back (WM condition) and 0-back (control condition). We estimated phase coupling patterns (multivariate phase slope index) for both conditions and for theta, alpha, beta, and gamma bands. The obtained phase coupling data were then used to train a linear support vector machine in order to classify which task condition the subject was performing with an across-subject cross-validation approach. The classification was performed separately based on the data from individual frequency bands and with all bands combined (multiband). Finally, we evaluated the relative importance of the different features (phase couplings) for classification by the means of feature selection probability. Main results. The WM condition and control condition were successfully classified based on the phase coupling patterns in the theta (62% accuracy) and alpha bands (60% accuracy) separately. Importantly, the multiband classification showed that phase coupling patterns not only in the theta and alpha but also in the gamma bands are related to WM processing, as testified by improvement in classification performance (71%). Significance. Our study successfully decoded WM tasks using MEG source space functional connectivity. Our approach, combining across-subject classification and a multidimensional metric recently developed by our group, is able to detect patterns of connectivity that are shared across individuals. In other words, the results are generalisable to new individuals and allow meaningful interpretation of task-relevant phase coupling patterns.

MVPAlab: A Machine Learning decoding toolbox for multidimensional electroencephalography data

“…The latest release supports different signal characteristics as features, such as the power envelope or the instantaneous phase of the signal. Recent studies [90] implement different feature engineering techniques, concatenating data from different frequency bands, to improve the classification result. Currently, MVPAlab does not implement these strategies.…”

A novel description of the network dynamics underpinning working memory

“…During and following the early stimulus encoding phase, several WM neurophysiological studies report an eventrelated desynchronisation (ERD) of the occipital alpha activity 11,[38][39][40] . This effect resembles the significant deactivation of state 2 between 200-500 ms PST.…”

“…The broadband activity of this state reflects the diversified frequency bands (theta, alpha, beta, and gamma) associated with maintenance, recall, matching, and motor plan 32,55,56 , and the intertwined development of these processes during an n-back task. A developing research line identifies cross-frequency coupling as the underlying mechanism for WM subprocesses, explaining the broadband activity reported by traditional works 40,[56][57][58] . In this context, we would suggest that the broadband spectral profile of state 5 results from cross-frequency interactions.…”

Long-Term and Meditation-Specific Modulations of Brain Connectivity Revealed Through Multivariate Pattern Analysis

“…Indeed, it has been demonstrated that MVPA can be successfully used to discriminate patterns of brain activation in perceptual and cognitive tasks (Cichy et al 2014 ; Guidotti et al 2020 ; Kragel and LaBar 2016 ; Tosoni et al 2016 ). The same approach has been used by exploiting functional connectivity patterns to decode discrete functions such as working memory (Syrjälä et al 2021 ) or continuous variables such as brain maturity or age (Dosenbach et al 2010 ; Liem et al 2017 ). Moreover, MVPA has been applied in mindfulness studies to predict age using voxel-based morphometry (Luders et al 2016 ) and to classify patterns of functional connectivity before and after a body-mind training course (Tang et al 2017 ).…”