Decoding intracranial EEG data with multiple kernel learning method

Machine learning models have been successfully applied to neuroimaging data to make predictions about behavioral and cognitive states of interest. While these multivariate methods have greatly advanced the field of neuroimaging, their application to electrophysiological data has been less common especially in the analysis of human intracranial electroencephalography (iEEG, also known as electrocorticography or ECoG) data, which contains a rich spectrum of signals recorded from a relatively high number of recording sites.
In the present work, we introduce a novel approach to determine the contribution of different bandwidths of EEG signal in different recording sites across different experimental conditions using the Multiple Kernel Learning (MKL) method.
To validate and compare the usefulness of our approach, we applied this method to an ECoG dataset that was previously analysed and published with univariate methods.
Our findings proved the usefulness of the MKL method in detecting changes in the power of various frequency bands during a given task and selecting automatically the most contributory signal in the most contributory site(s) of recording.
With a single computation, the contribution of each frequency band in each recording site in the estimated multivariate model can be highlighted, which then allows formulation of hypotheses that can be tested a posteriori with univariate methods if needed.