AUTHOR=Ellis Charles A. , Sendi Mohammad S. E. , Zhang Rongen , Carbajal Darwin A. , Wang May D. , Miller Robyn L. , Calhoun Vince D. TITLE=Novel methods for elucidating modality importance in multimodal electrophysiology classifiers JOURNAL=Frontiers in Neuroinformatics VOLUME=17 YEAR=2023 URL=https://www.frontiersin.org/journals/neuroinformatics/articles/10.3389/fninf.2023.1123376 DOI=10.3389/fninf.2023.1123376 ISSN=1662-5196 ABSTRACT=Introduction

Multimodal classification is increasingly common in electrophysiology studies. Many studies use deep learning classifiers with raw time-series data, which makes explainability difficult, and has resulted in relatively few studies applying explainability methods. This is concerning because explainability is vital to the development and implementation of clinical classifiers. As such, new multimodal explainability methods are needed.

Methods

In this study, we train a convolutional neural network for automated sleep stage classification with electroencephalogram (EEG), electrooculogram, and electromyogram data. We then present a global explainability approach that is uniquely adapted for electrophysiology analysis and compare it to an existing approach. We present the first two local multimodal explainability approaches. We look for subject-level differences in the local explanations that are obscured by global methods and look for relationships between the explanations and clinical and demographic variables in a novel analysis.

Results

We find a high level of agreement between methods. We find that EEG is globally the most important modality for most sleep stages and that subject-level differences in importance arise in local explanations that are not captured in global explanations. We further show that sex, followed by medication and age, had significant effects upon the patterns learned by the classifier.

Discussion

Our novel methods enhance explainability for the growing field of multimodal electrophysiology classification, provide avenues for the advancement of personalized medicine, yield unique insights into the effects of demographic and clinical variables upon classifiers, and help pave the way for the implementation of multimodal electrophysiology clinical classifiers.