Key result
EEG beta-band power classifies biological sex in MDD with ~77% accuracy.
Why the study?
The generalizability of deep-learning-based automatic identification of biological sex from EEG recordings, especially in the presence of psychiatric disease, was uncertain.
Can a deep-learning-based classifier accurately predict biological sex from EEG recordings in patients with Major Depressive Disorder?
Cross-Sectional (n=134)
Can a deep-learning-based classifier accurately predict biological sex from EEG recordings in patients with Major Depressive Disorder?
Effect estimate: AUC 0.7246
p-value: p=<0.001
Deep learning classifiers can accurately identify biological sex from EEG beta-band power in patients with Major Depressive Disorder, highlighting a robust neurobiological sexual dimorphism.
Sex-specific EEG beta-band differences in MDD support biomarker exploration; hypothesis-generating and requires validation before any clinical use.
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.
No takes yet. Share an insight, caveat, or question.
Bučková et al. (2020) conducted a cross-sectional in Major Depressive Disorder (n=134). Relative beta-band power in EEG vs. Men vs Women was evaluated on Classification accuracy of biological sex using mean relative beta-band power (AUC 0.7246, p=<0.001). Mean relative beta-band power in EEG significantly differed between men and women with Major Depressive Disorder, providing a biological sex classification accuracy of 76.87% (AUC 0.7246).
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: