Predicting Sex From EEG: Validity and Generalizability of Deep-Learning-Based Interpretable Classifier

0533609 - ÚI 2021 RIV CH eng J - Journal Article
Bučková, Barbora - Brunovský, M. - Bareš, M. - Hlinka, Jaroslav
Predicting Sex From EEG: Validity and Generalizability of Deep-Learning-Based Interpretable Classifier.
Frontiers in Neuroscience. Roč. 14, 27 October (2020), č. článku 589303. E-ISSN 1662-453X
R&D Projects: GA MZd(CZ) NV17-28427A
Grant - others:GA MŠk(CZ) LO1611
Institutional support: RVO:67985807
Keywords : explainable artificial intelligence * EEG * sexual dimorsphism * classification * machine learning * major depressive disorder * biomarkers
OECD category: Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Impact factor: 4.677, year: 2020
Method of publishing: Open access

Explainable artificial intelligence holds a great promise for neuroscience and plays an important role in the hypothesis generation process. We follow-up a recent machine learning-oriented study that constructed a deep convolutional neural network to automatically identify biological sex from EEG recordings in healthy individuals and highlighted the discriminative role of beta-band power. If generalizing, this finding would be relevant not only theoretically by pointing to some specific neurobiological sexual dimorphisms, but potentially also as a relevant confound in quantitative EEG diagnostic practice. To put this finding to test, we assess whether the automatic identification of biological sex generalizes to another dataset, particularly in the presence of a psychiatric disease, by testing the hypothesis of higher beta power in women compared to men on 134 patients suffering from Major Depressive Disorder. Moreover, we construct ROC curves and compare the performance of the classifiers in determining sex both before and after the antidepressant treatment. We replicate the observation of a significant difference in beta-band power between men and women, providing classification accuracy of nearly 77%. The difference was consistent across the majority of electrodes, however multivariate classification models did not generally improve the performance. Similar results were observed also after the antidepressant treatment (classification accuracy above 70%), further supporting the robustness of the initial finding.
Permanent Link: http://hdl.handle.net/11104/0311949