{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,23]],"date-time":"2026-08-23T14:50:46Z","timestamp":1787496646761,"version":"build-2736575974"},"reference-count":72,"publisher":"Ubiquity Press, Ltd.","issue":"1","license":[{"start":{"date-parts":[[2026,1,16]],"date-time":"2026-01-16T00:00:00Z","timestamp":1768521600000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"Brain and Behavior Research Foundation (NARSAD, PI: BZ)","award":["R01MH116038"],"award-info":[{"award-number":["R01MH116038"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["CPSY"],"abstract":"<jats:p>Objective: Identifying obsessive-compulsive disorder (OCD) using brain data remains challenging. Resting-state electroencephalography (EEG) offers an affordable and noninvasive approach, but identifying predictive signals in EEG data has met with little success, even with the application of traditional machine learning methods. We explored whether convolutional neural networks (CNNs) applied to EEG time-frequency representations can distinguish individuals with OCD from healthy controls.\nMethod: We collected resting-state EEG data from 20 unmedicated participants (10 with OCD, 10 healthy controls). Four-second EEG segments were transformed into time-frequency representations. We then trained a 2D CNN using a leave-one-subject-out cross-validation framework to perform subject-level classification and compared its performance to a more traditional support vector machine (SVM) approach. Next, using multimodal fusion, we examined whether adding clinical and demographic information improved classification.\nResults: The CNN classifier achieved high subject-level performance, distinguishing individuals with an accuracy of 85.0% and an area under the curve (AUC) of 0.88. This significantly outperformed the SVM baseline, which performed no better than chance (45.0% accuracy, AUC: 0.47). A subsequent multimodal analysis revealed that clinical and demographic variables did not contribute any additional independent information.\nConclusion: CNNs applied to resting-state EEG show promise for identifying OCD, outperforming traditional machine learning methods. These findings highlight the potential of deep learning to uncover complex, diagnostically relevant patterns in neural data. While limited by sample size, this work supports further investigation into multimodal models for psychiatric classification, warranting replication in larger, more diverse samples.<\/jats:p>","DOI":"10.5334\/cpsy.149","type":"journal-article","created":{"date-parts":[[2026,1,16]],"date-time":"2026-01-16T09:42:47Z","timestamp":1768556567000},"page":"1-17","source":"Crossref","is-referenced-by-count":2,"title":["Classifying Obsessive-Compulsive Disorder from Resting-State EEG Using Convolutional Neural Networks: A Pilot Study"],"prefix":"10.5334","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4567-8694","authenticated-orcid":false,"given":"Brian","family":"Zaboski","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6024-6721","authenticated-orcid":false,"given":"Sarah","family":"Fineberg","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6093-2625","authenticated-orcid":false,"given":"Patrick","family":"Skosnik","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Stephen","family":"Kichuk","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-9357-9918","authenticated-orcid":false,"given":"Madison","family":"Fitzpatrick","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2117-9321","authenticated-orcid":false,"given":"Christopher","family":"Pittenger","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"3285","published-online":{"date-parts":[[2026,1,16]]},"reference":[{"key":"key20260116094240_B1","unstructured":"Abadi, M., Agarwal, A., Barham, P., Brevdo, E., Chen, Z., Citro, C., Corrado, G. S., Davis, A., Dean, J., Devin, M., Ghemawat, S., Goodfellow, I., Harp, A., Irving, G., Isard, M., Jia, Y., Jozefowicz, R., Kaiser, L., Kudlur, M., \u2026 Zheng, X. (2015). TensorFlow: Large-scale machine learning on heterogeneous systems [White paper]. Google Research. https:\/\/download.tensorflow.org\/paper\/whitepaper2015.pdf"},{"issue":"15","key":"key20260116094240_B2","doi-asserted-by":"crossref","first-page":"4040","DOI":"10.1109\/TSP.2018.2844203","article-title":"Faster independent component analysis by preconditioning with Hessian approximations","volume":"66","year":"2018","journal-title":"IEEE Transactions on Signal Processing"},{"issue":"8","key":"key20260116094240_B3","doi-asserted-by":"crossref","first-page":"1016","DOI":"10.1016\/j.janxdis.2006.03.001","article-title":"Psychometric properties and construct validity of the Obsessive\u2013Compulsive Inventory\u2014Revised: Replication and extension with a clinical sample","volume":"20","year":"2006","journal-title":"Journal of Anxiety Disorders"},{"issue":"1","key":"key20260116094240_B4","doi-asserted-by":"crossref","first-page":"180","DOI":"10.1037\/a0018260","article-title":"Assessment of obsessive-compulsive symptom dimensions: Development and evaluation of the Dimensional Obsessive-Compulsive Scale","volume":"22","year":"2010","journal-title":"Psychological Assessment"},{"issue":"2","key":"key20260116094240_B5","doi-asserted-by":"crossref","first-page":"423","DOI":"10.1109\/TPAMI.2018.2798607","article-title":"Multimodal machine learning: A survey and taxonomy","volume":"41","year":"2019","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"3","key":"key20260116094240_B6","doi-asserted-by":"crossref","first-page":"356","DOI":"10.1002\/jcad.12090","article-title":"Psychometric meta-analysis of the English version of the Beck Anxiety Inventory","volume":"94","year":"2016","journal-title":"Journal of Counseling & Development"},{"issue":"6","key":"key20260116094240_B7","doi-asserted-by":"crossref","first-page":"893","DOI":"10.1037\/0022-006X.56.6.893","article-title":"An inventory for measuring clinical anxiety: Psychometric properties","volume":"56","year":"1988","journal-title":"Journal of Consulting and Clinical Psychology"},{"key":"key20260116094240_B8","volume-title":"Beck Anxiety Inventory","year":"2012"},{"key":"key20260116094240_B9","volume-title":"Beck Depression Inventory\u2013II","year":"1996"},{"issue":"6","key":"key20260116094240_B10","doi-asserted-by":"crossref","first-page":"561","DOI":"10.1001\/archpsyc.1961.01710120031004","article-title":"An inventory for measuring depression","volume":"4","year":"1961","journal-title":"Archives of General Psychiatry"},{"issue":"6","key":"key20260116094240_B11","doi-asserted-by":"crossref","first-page":"1129","DOI":"10.1162\/neco.1995.7.6.1129","article-title":"An information-maximization approach to blind separation and blind deconvolution","volume":"7","year":"1995","journal-title":"Neural Computation"},{"issue":"6","key":"key20260116094240_B12","article-title":"A comparative study of machine learning and deep learning models for automatic Parkinson\u2019s disease detection from electroencephalogram signals","volume":"15","year":"2025","journal-title":"Diagnostics"},{"issue":"1","key":"key20260116094240_B13","doi-asserted-by":"crossref","first-page":"49","DOI":"10.1023\/A:1018046112532","article-title":"Stacked regressions","volume":"24","year":"1996","journal-title":"Machine Learning"},{"issue":"10","key":"key20260116094240_B14","doi-asserted-by":"crossref","first-page":"4307","DOI":"10.1038\/s41380-023-02077-0","article-title":"The functional connectome in obsessive-compulsive disorder: Resting-state mega-analysis and machine learning classification for the ENIGMA-OCD consortium","volume":"28","year":"2023","journal-title":"Molecular Psychiatry"},{"issue":"2","key":"key20260116094240_B15","doi-asserted-by":"crossref","first-page":"187","DOI":"10.1037\/0022-006X.50.2.187","article-title":"Reliabilities and intercorrelations of eight measures of proneness to psychosis","volume":"50","year":"1982","journal-title":"Journal of Consulting and Clinical Psychology"},{"key":"key20260116094240_B16","unstructured":"Chollet, F. (2015). Keras [Computer software]. https:\/\/keras.io"},{"key":"key20260116094240_B17","year":"2020","journal-title":"Comparison of attention-based deep learning models for EEG classification"},{"key":"key20260116094240_B18","first-page":"471","volume-title":"Functional neuroradiology","year":"2023"},{"key":"key20260116094240_B19","article-title":"Towards best practice of interpreting deep learning models for EEG-based brain computer interfaces","volume":"17","year":"2023","journal-title":"Frontiers in Computational Neuroscience"},{"issue":"2","key":"key20260116094240_B20","doi-asserted-by":"crossref","first-page":"215","DOI":"10.1037\/0022-006X.51.2.215","article-title":"Magical ideation as an indicator of schizotypy","volume":"51","year":"1983","journal-title":"Journal of Consulting and Clinical Psychology"},{"key":"key20260116094240_B21","doi-asserted-by":"crossref","first-page":"220","DOI":"10.1016\/j.neucom.2015.02.039","article-title":"A hybrid artificial intelligence method to classify trichotillomania and obsessive compulsive disorder","volume":"161","year":"2015","journal-title":"Neurocomputing"},{"issue":"5","key":"key20260116094240_B22","doi-asserted-by":"crossref","first-page":"543","DOI":"10.1177\/15500594231222980","article-title":"Application of hybrid deep learning architectures for identification of individuals with obsessive compulsive disorder based on EEG data","volume":"55","year":"2024","journal-title":"Clinical EEG and Neuroscience"},{"issue":"2","key":"key20260116094240_B23","first-page":"319","article-title":"Psychometric properties of the Perceptual Aberration Scale and the Magical Ideation Scale in Spanish college students","volume":"9","year":"2009","journal-title":"International Journal of Clinical and Health Psychology"},{"issue":"11","key":"key20260116094240_B24","doi-asserted-by":"crossref","first-page":"1006","DOI":"10.1001\/archpsyc.1989.01810110048007","article-title":"The Yale-Brown Obsessive Compulsive Scale: I. Development, use, and reliability","volume":"46","year":"1989","journal-title":"Archives of General Psychiatry"},{"key":"key20260116094240_B25","article-title":"MEG and EEG data analysis with MNE-Python","volume":"7","year":"2013","journal-title":"Frontiers in Neuroscience"},{"key":"key20260116094240_B26","doi-asserted-by":"crossref","first-page":"446","DOI":"10.1016\/j.neuroimage.2013.10.027","article-title":"MNE software for processing MEG and EEG data","volume":"86","year":"2014","journal-title":"NeuroImage"},{"issue":"7825","key":"key20260116094240_B27","doi-asserted-by":"crossref","first-page":"357","DOI":"10.1038\/s41586-020-2649-2","article-title":"Array programming with NumPy","volume":"585","year":"2020","journal-title":"Nature"},{"key":"key20260116094240_B28","article-title":"The REDCap consortium: Building an international community of software platform partners","volume":"95","year":"2019","journal-title":"Journal of Biomedical Informatics"},{"issue":"2","key":"key20260116094240_B29","doi-asserted-by":"crossref","first-page":"377","DOI":"10.1016\/j.jbi.2008.08.010","article-title":"Research electronic data capture (REDCap)\u2014A metadata-driven methodology and workflow process for providing translational research informatics support","volume":"42","year":"2009","journal-title":"Journal of Biomedical Informatics"},{"issue":"3","key":"key20260116094240_B30","doi-asserted-by":"crossref","first-page":"90","DOI":"10.1109\/MCSE.2007.55","article-title":"Matplotlib: A 2D graphics environment","volume":"9","year":"2007","journal-title":"Computing in Science & Engineering"},{"issue":"3","key":"key20260116094240_B31","doi-asserted-by":"crossref","first-page":"626","DOI":"10.1109\/72.761722","article-title":"Fast and robust fixed-point algorithms for independent component analysis","volume":"10","year":"1999","journal-title":"IEEE Transactions on Neural Networks"},{"key":"key20260116094240_B32","year":"2024","journal-title":"A generic review of integrating artificial intelligence in cognitive behavioral therapy"},{"issue":"3","key":"key20260116094240_B33","doi-asserted-by":"crossref","first-page":"169","DOI":"10.1002\/mpr.1359","article-title":"Twelve-month and lifetime prevalence and lifetime morbid risk of anxiety and mood disorders in the United States","volume":"21","year":"2012","journal-title":"International Journal of Methods in Psychiatric Research"},{"issue":"1","key":"key20260116094240_B34","doi-asserted-by":"crossref","first-page":"39","DOI":"10.1017\/S1352465811000245","article-title":"The Illusory Beliefs Inventory: A new measure of magical thinking and its relationship with obsessive compulsive disorder","volume":"40","year":"2012","journal-title":"Behavioural and Cognitive Psychotherapy"},{"key":"key20260116094240_B35","year":"2014","journal-title":"Adam: A method for stochastic optimization"},{"key":"key20260116094240_B36","doi-asserted-by":"crossref","first-page":"493","DOI":"10.1109\/TNSRE.2024.3355750","article-title":"Graph neural network-based EEG classification: A survey","volume":"32","year":"2024","journal-title":"IEEE Transactions on Neural Systems and Rehabilitation Engineering"},{"key":"key20260116094240_B37","article-title":"ImageNet classification with deep convolutional neural networks","volume":"25","year":"2012","journal-title":"Advances in Neural Information Processing Systems"},{"key":"key20260116094240_B38","article-title":"Extracting the auditory attention in a dual-speaker scenario from EEG using a joint CNN-LSTM model","volume":"12","year":"2021","journal-title":"Frontiers in Physiology"},{"issue":"3","key":"key20260116094240_B39","doi-asserted-by":"crossref","first-page":"491","DOI":"10.1037\/0021-843X.106.3.491","article-title":"Magical ideation and social anhedonia as predictors of psychosis proneness: A partial replication","volume":"106","year":"1997","journal-title":"Journal of Abnormal Psychology"},{"key":"key20260116094240_B40","doi-asserted-by":"crossref","first-page":"1167","DOI":"10.2147\/PRBM.S211117","article-title":"Exposure and response prevention in the treatment of obsessive-compulsive disorder: Current perspectives","volume":"12","year":"2019","journal-title":"Psychology Research and Behavior Management"},{"issue":"2","key":"key20260116094240_B41","doi-asserted-by":"crossref","first-page":"417","DOI":"10.1162\/089976699300016719","article-title":"Independent component analysis using an extended infomax algorithm for mixed subgaussian and supergaussian sources","volume":"11","year":"1999","journal-title":"Neural Computation"},{"key":"key20260116094240_B42","article-title":"Using CNN saliency maps and EEG modulation spectra for improved and more interpretable machine learning-based Alzheimer\u2019s disease diagnosis","volume":"2023","year":"2023","journal-title":"Computational Intelligence and Neuroscience"},{"issue":"1\u20132","key":"key20260116094240_B43","first-page":"94","article-title":"Differential associations between schizotypy facets and emotion traits","volume":"187","year":"2011","journal-title":"Psychiatry Research"},{"issue":"2","key":"key20260116094240_B44","doi-asserted-by":"crossref","first-page":"259","DOI":"10.1016\/j.cbpra.2022.09.002","article-title":"Suicidal obsessions or suicidal ideation? A case report and practical guide for differential assessment","volume":"31","year":"2024","journal-title":"Cognitive and Behavioral Practice"},{"key":"key20260116094240_B45","first-page":"51","article-title":"Data structures for statistical computing in Python","year":"2010"},{"issue":"6","key":"key20260116094240_B46","first-page":"1142","article-title":"Validation of ICA as a tool to remove eye movement artifacts from EEG\/ERP","volume":"47","year":"2010","journal-title":"Psychophysiology"},{"issue":"4","key":"key20260116094240_B47","first-page":"246","article-title":"Use of EEG for predicting treatment response to transcranial magnetic stimulation in obsessive compulsive disorder","volume":"51","year":"2019","journal-title":"Clinical EEG and Neuroscience"},{"issue":"3","key":"key20260116094240_B48","article-title":"Real-time classification of anxiety in virtual reality therapy using biosensors and a convolutional neural network","volume":"14","year":"2024","journal-title":"Biosensors"},{"key":"key20260116094240_B49","first-page":"15","volume-title":"Artificial intelligence application in networks and systems","year":"2023"},{"key":"key20260116094240_B50","unstructured":"Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Prettenhofer, P., Weiss, R., Dubourg, V., Vanderplas, J., Passos, A., Cournapeau, D., Brucher, M., Perrot, M., & Duchesnay, E. (2011). Scikit-learn: Machine learning in Python. Journal of Machine Learning Research, 12, 2825\u20132830. http:\/\/www.jmlr.org\/papers\/v12\/pedregosa11a.html"},{"key":"key20260116094240_B51","volume-title":"Obsessive-compulsive disorder: Phenomenology, pathophysiology, and treatment","year":"2017"},{"key":"key20260116094240_B52","article-title":"A systematic review of EEG based automated schizophrenia classification through machine learning and deep learning","volume":"18","year":"2024","journal-title":"Frontiers in Human Neuroscience"},{"key":"key20260116094240_B53","article-title":"Neurofeedback for obsessive compulsive disorder: A randomized, double-blind trial","volume":"328","year":"2023","journal-title":"Psychiatry Research"},{"key":"key20260116094240_B54","article-title":"A deep neural network and transfer learning combined method for cross-task classification of error-related potentials","volume":"18","year":"2024","journal-title":"Frontiers in Human Neuroscience"},{"issue":"1","key":"key20260116094240_B55","doi-asserted-by":"crossref","first-page":"53","DOI":"10.1038\/mp.2008.94","article-title":"The epidemiology of obsessive-compulsive disorder in the National Comorbidity Survey Replication","volume":"15","year":"2010","journal-title":"Molecular Psychiatry"},{"issue":"4","key":"key20260116094240_B56","doi-asserted-by":"crossref","first-page":"343","DOI":"10.1097\/JCP.0b013e3181aba68f","article-title":"Artificial neural network model for the prediction of obsessive-compulsive disorder treatment response","volume":"29","year":"2009","journal-title":"Journal of Clinical Psychopharmacology"},{"issue":"11","key":"key20260116094240_B57","doi-asserted-by":"crossref","first-page":"5391","DOI":"10.1002\/hbm.23730","article-title":"Deep learning with convolutional neural networks for EEG decoding and visualization","volume":"38","year":"2017","journal-title":"Human Brain Mapping"},{"issue":"Suppl. 20","key":"key20260116094240_B58","first-page":"22","article-title":"The Mini-International Neuropsychiatric Interview (M.I.N.I.): The development and validation of a structured diagnostic psychiatric interview for DSM-IV and ICD-10","volume":"59","year":"1998","journal-title":"The Journal of Clinical Psychiatry"},{"key":"key20260116094240_B59","article-title":"Obsessive\u2013compulsive disorder","volume":"5","year":"2019","journal-title":"Nature Reviews Disease Primers"},{"key":"key20260116094240_B60","article-title":"Is brain dynamics preserved in the EEG after automated artifact removal? A validation of the fingerprint method and the automatic removal of cardiac interference approach based on microstate analysis","volume":"14","year":"2021","journal-title":"Frontiers in Neuroscience"},{"issue":"1","key":"key20260116094240_B61","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1177\/1073191116638410","article-title":"Psychometric properties of a structured diagnostic interview for DSM-5 anxiety, mood, and obsessive-compulsive and related disorders","volume":"25","year":"2018","journal-title":"Assessment"},{"issue":"3","key":"key20260116094240_B62","doi-asserted-by":"crossref","first-page":"333","DOI":"10.1016\/j.biopsycho.2005.11.012","article-title":"Interpreting event-related brain potential (ERP) distributions: Implications of baseline potentials and variability with application to amplitude normalization by vector scaling","volume":"72","year":"2006","journal-title":"Biological Psychology"},{"key":"key20260116094240_B63","volume-title":"Python 2.6 reference manual","year":"2009"},{"issue":"4","key":"key20260116094240_B64","doi-asserted-by":"crossref","first-page":"416","DOI":"10.1590\/1516-4446-2012-1048","article-title":"Psychometric properties of the Beck Depression Inventory-II: A comprehensive review","volume":"35","year":"2013","journal-title":"Brazilian Journal of Psychiatry"},{"issue":"60","key":"key20260116094240_B65","article-title":"seaborn: Statistical data visualization","volume":"6","year":"2021","journal-title":"Journal of Open Source Software"},{"issue":"2","key":"key20260116094240_B66","doi-asserted-by":"crossref","first-page":"241","DOI":"10.1016\/S0893-6080(05)80023-1","article-title":"Stacked generalization","volume":"5","year":"1992","journal-title":"Neural Networks"},{"key":"key20260116094240_B67","first-page":"6084","article-title":"Wavelet transform time-frequency image and convolutional network-based motor imagery EEG classification","volume":"7","year":"2018","journal-title":"IEEE Access"},{"issue":"3","key":"key20260116094240_B68","article-title":"Emotion classification based on Transformer and CNN for EEG spatial\u2013temporal feature learning","volume":"14","year":"2024","journal-title":"Brain Sciences"},{"issue":"7","key":"key20260116094240_B69","article-title":"Precision psychiatry for obsessive-compulsive disorder: Clinical applications of deep learning architectures","volume":"14","year":"2025","journal-title":"Journal of Clinical Medicine"},{"key":"key20260116094240_B70","article-title":"Deep learning in obsessive-compulsive disorder: A narrative review","volume":"16","year":"2025","journal-title":"Frontiers in Psychiatry"},{"key":"key20260116094240_B71","article-title":"Electroencephalographic correlates and predictors of treatment outcome in OCD: A brief narrative review","volume":"12","year":"2021","journal-title":"Frontiers in Psychiatry"},{"key":"key20260116094240_B72","article-title":"Predicting OCD severity from religiosity and personality: A machine learning and neural network approach","volume":"8","year":"2024","journal-title":"Journal of Mood & Anxiety Disorders"}],"container-title":["Computational Psychiatry"],"original-title":[],"link":[{"URL":"https:\/\/account.cpsyjournal.org\/index.php\/up-j-cp\/article\/download\/149\/233","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/account.cpsyjournal.org\/index.php\/up-j-cp\/article\/download\/149\/234","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/account.cpsyjournal.org\/index.php\/up-j-cp\/article\/download\/149\/235","content-type":"application\/zip","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/account.cpsyjournal.org\/index.php\/up-j-cp\/article\/download\/149\/233","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T10:52:13Z","timestamp":1782816733000},"score":1,"resource":{"primary":{"URL":"https:\/\/account.cpsyjournal.org\/index.php\/up-j-cp\/article\/view\/149"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,16]]},"references-count":72,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,1,16]]}},"URL":"https:\/\/doi.org\/10.5334\/cpsy.149","relation":{},"ISSN":["2379-6227"],"issn-type":[{"value":"2379-6227","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,16]]}}}