NOVEL APPROACH EXPLAINS SPATIO-SPECTRAL INTERACTIONS IN RAW ELECTROENCEPHALOGRAM DEEP LEARNING CLASSIFIERS

The application of deep learning classifiers to resting-state electroencephalography (rs-EEG) data has become increasingly common. However, relative to studies using traditional machine learning methods and extracted features, deep learning methods are less explainable. A growing number of studies have presented explainability approaches for rs-EEG deep learning classifiers. However, to our knowledge, no approaches give insight into spatio-spectral interactions (i.e., how spectral activity in one channel may interact with activity in other channels). In this study, we combine gradient and perturbation-based explainability approaches to give insight into spatio-spectral interactions in rs-EEG deep learning classifiers for the first time. We present the approach within the context of major depressive disorder (MDD) diagnosis identifying differences in frontal δ activity and reduced interactions between frontal electrodes and other electrodes. Our approach provides novel insights and represents a significant step forward for the field of explainable EEG classification.