Classifying Obsessive-Compulsive Disorder from Resting-State EEG using Convolutional Neural Networks: A Pilot Study

Objective: Classifying obsessive-compulsive disorder (OCD) using brain data remains challenging. Resting-state electroencephalography (EEG) offers an affordable and noninvasive approach, but traditional machine learning methods have limited its predictive capability. We explored whether convolutional neural networks (CNNs) applied to minimally processed EEG time-frequency representations could offer a solution, effectively distinguishing individuals with OCD from healthy controls. Method: We collected resting-state EEG data from 20 unmedicated participants (10 OCD, 10 healthy controls). Clean, 4-second EEG segments were transformed into time-frequency representations using Morlet wavelets. In a two-step evaluation, we first used a 2D CNN classifier using leave-one-subject-out cross-validation and compared it to a traditional support vector machine (SVM) trained on spectral band power features. Second, using multimodal fusion, we examined whether adding clinical and demographic information improved classification. Results: The CNN achieved strong classification accuracy (82.0%, AUC: 0.86), significantly outperforming the chance-level SVM baseline (49.0%, AUC: 0.45). Most clinical variables did not improve performance beyond the EEG data alone (subject-level accuracy: 80.0%). However, incorporating education level boosted performance notably (accuracy: 85.0%, AUC: 0.89). Conclusion: CNNs applied to resting-state EEG show promise for diagnosing OCD, outperforming traditional machine learning methods. Despite sample size limitations, these findings highlight deep learning’s potential in psychiatric applications. Education level emerged as a potentially complementary feature, warranting further investigation in larger, more diverse samples.