A Neuro-Physiological Diffusion Model for Accurate EEG-Based Psychiatric Disorder Classification

Gowri Thumbur; Pradeep  Gopal; Abbinayaa M; S Subashini; Mathivanan Nagaraj; N Nasiya Niwaz Banu Banu

doi:10.35882/jeeemi.v8i1.1131

Gowri Thumbur Department of Electronics and Communication Engineering, GITAM School of Technology, GITAM University, Visakhapatnam, India. https://orcid.org/0000-0002-2584-1397
Pradeep Gopal Department of Computer Science and Engineering, KGISL Institute of Technology, Coimbatore, India. https://orcid.org/0009-0000-5185-0206
Abbinayaa M Department of Computer Science and Engineering, Dr.N.G.P. Institute of Technology, Coimbatore, India. https://orcid.org/0009-0004-1904-967X
S Subashini Department of Computer Science and Engineering (Internet of Things), Nandha Engineering College, Erode -Perundurai main road, Erode - 638052, Tamil Nadu, India.
Mathivanan Nagaraj Department of Artificial Intelligence and Data Science, Karpagam Academy of Higher Education, Coimbatore, Tamil Nadu, India. https://orcid.org/0009-0007-2090-0486
N Nasiya Niwaz Banu Banu Department of Computer Science and Engineering, Nehru Institute of Technology, Jawahar Gardens, Kaliapuram, Thirumalayampalayam, Coimbatore, 641105, Tamil Nadu, India. https://orcid.org/0009-0001-5950-4970

DOI: https://doi.org/10.35882/jeeemi.v8i1.1131

Keywords: EEG-based Mental Disorder Classification, Diffusion Model with Physiological Constraints, Synthetic EEG Signal Generation, Multi-task Transformer Classifier, Neurophysiological Feature Augmentation

Abstract

Identification of psychiatric conditions such as depression, schizophrenia, anxiety, and obsessive-compulsive disorder (OCD) from Electroencephalography (EEG) data remains a significant challenge due to the complexity of neurophysiological patterns. While Generative Adversarial Networks (GANs) have been explored to augment EEG datasets and enhance classifier performance, they often suffer from limitations including training instability, mode collapse, and the generation of physiologically implausible EEG samples. These shortcomings hinder their applicability in high-stakes clinical decision-making, where reliability and physiological coherence are critical. This study aims to address the above-mentioned challenges by proposing a novel Neuro-Physiologically Constrained Diffusion Framework (NPC-DiffEEG). This framework leverages the strengths of conditional diffusion models while integrating domain-specific neurophysiological constraints, ensuring that generated EEG signals preserve key properties, such as frequency band structures and inter-channel connectivity patterns, both of which are essential for accurate mental disorder classification. The NPC-DiffEEG-generated data is combined with real EEG features and processed using a multi-task attention-based transformer, enabling the model to learn robust, cross-disorder representations. Extensive experiments conducted on a publicly available multi-disorder EEG dataset demonstrate that NPC-DiffEEG significantly outperforms traditional GAN-based augmentation approaches. The model achieves an impressive average classification accuracy of 96.8%, along with superior F1-scores and AUC values across all disorder categories. Furthermore, integrating attention-based disorder attribution not only enhances interpretability but also reduces overfitting, thereby improving generalizability to unseen subjects. This innovative approach marks a substantial advancement in EEG-based classification of psychiatric disorders, bridging the gap between synthetic data generation and clinically reliable decision-support systems.

Downloads

Download data is not yet available.

References

Abir, S. I., Shoha, S., Hossain, M. M., Sultana, N., Saha, T. R., Sarwer, M. H., ... & Hasan, M. (2025). Machine learning and deep learning techniques for EEG-based prediction of psychiatric disorders. Journal of Computer Science and Technology Studies, 7(1), 46-63.

Karimian, M. (2025). A Short Review on Diagnosing and Predicting Mental Disorders with Machine Learning. International Journal of Applied Data Science in Engineering and Health, 1(1), 20-27.

Balakrishnan, S., Murugesan, R. K., Lim, E. L., Faisal, A., & Ashraf, H. (2025). Survey of Deep Learning and Machine Learning Approaches for Major Depressive Disorder Detection Using EEG Data. Journal of Electrical and Computer Engineering, 2025(1), 6277690.

Li, W., Zhao, P., Xu, C., Hou, Y., Jiang, W., & Song, A. (2025). Deep Learning for EEG-Based Visual Classification and Reconstruction: Panorama, Trends, Challenges and Opportunities. IEEE Transactions on Biomedical Engineering.

Elnaggar, K., El-Gayar, M. M., & Elmogy, M. (2025). Depression detection and diagnosis based on electroencephalogram (EEG) analysis: A systematic review. Diagnostics, 15(2), 210.

Uyanik, H., Sengur, A., Salvi, M., Tan, R. S., Tan, J. H., & Acharya, U. R. (2025). Automated Detection of Neurological and Mental Health Disorders Using EEG Signals and Artificial Intelligence: A Systematic Review. Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery, 15(1), e70002.

Yadulla, A. R., Sajja, G. S., Addula, S. R., Maturi, M. H., Nadella, G. S., De La Cruz, E., ... & Gonaygunta, H. (2025). A Systematic Review of Mental Health Monitoring and Intervention Using Unsupervised Deep Learning on EEG Data. Psychology International, 7(3), 61.

Rehman, H., Khan, D. M., Amanullah, H., Kamran, L., Rehman, O. U., Siddiqui, S. T., & Masroor, K. (2025). Advances in EEG-based detection of Major Depressive Disorder using shallow and deep learning techniques: A systematic review. Computers in Biology and Medicine, 192, 110154.

Dhekane, S., & Khandare, A. (2025). Applied Machine Learning in EEG data Classification to Classify Major Depressive Disorder by Critical Channels. Journal of Electronics, Electromedical Engineering, and Medical Informatics, 7(3), 581-596.

Ko, D. W., & Yang, J. J. (2022). EEG-Based schizophrenia diagnosis through time series image conversion and deep learning. Electronics, 11(14), 2265.

Siddiqui, S. T., Syed, Z., Hashmi, S. G., Ahmad, J., Singha, A. K., & Qidwai, K. A. (2025, April). A Wearable EEG-Based Hybrid CNN-RNN Framework for Psychiatric Disorder Diagnosis: Leveraging XAI for Enhanced Clinical Insights. In 2025 Devices for Integrated Circuit (DevIC) (pp. 743-748). IEEE.

Khalfallah, S., Peuch, W., Tlija, M., & Bouallegue, K. (2025). Exploring the effectiveness of machine learning and deep learning techniques for EEG signal classification in neurological disorders. IEEE Access.

Mota, M. B., de Oliveira, A. B., Bof, P., & Barone, D. A. C. (2025, June). Neuropsychiatric Disorders Classification using EEG Signal and Deep Neural Networks. In Simpósio Brasileiro de Computação Aplicada à Saúde (SBCAS) (pp. 287-292). SBC.

Bashir, N., Narejo, S., Naz, B., Ismail, F., Anjum, M. R., Butt, A., ... & Prasad, R. (2025). A machine learning framework for major depressive disorder (MDD) detection using non-invasive EEG signals. Wireless personal communications, 140(1), 39-61.

Khan, S., Noorani, S. H., Frnda, J., Rauf, U., Arsalan, A., & Saeed, S. M. U. (2025). A Transfer Learning-based Framework for Enhanced Classification of Perceived Mental Stress using EEG Spectrograms. IEEE Access.

Sammany, M., Haggag, A. E. S. E. S., & Nassef, T. M. (2025). Electrochemical-Based Eeg Brain Signal Recognition Using Deep Neural Networks. Egyptian Journal of Chemistry, 68(2), 333-347.

Ngo, L., Le, A., Ho, K., Le, T., Nguyen, N., Nguyen, S., ... & Ha, H. (2025). Electroencephalogram (EEG) based automated detection of mental disorders using artificial intelligence processing pipelines. Neuroscience Research Notes, 8(2), 404-1.

Sarwer, M. H., Saha, T. R., Abir, S. I., Shoha, S., Hossain, M. M., Sultana, N., ... & Al Shiam, S. A. (2025). EEG Functional Connectivity and Deep Learning for Automated Diagnosis of Alzheimer's disease and Schizophrenia. Journal of Computer Science and Technology Studies, 7(1), 82-99.

Shukla, P. K. (2025). Advanced Diagnosis of Psychological Illnesses Through Quantum Deep Learning and EEG Methods: The Case of the DEAP Dataset. In Harnessing AI and Machine Learning for Precision Wellness (pp. 341-382). IGI Global Scientific Publishing.

Kumar, L., Kaustubh, K., Rajkhowa, T., & Mattur, S. A. (2025, March). EEG-ViLSTM: A Deep Learning Approach for Depression Detection Using EEG Signals. In 2025 National Conference on Communications (NCC) (pp. 1-6). IEEE.

Senthil Kumar, S., Venmathi, A. R., Thangavel, Y., & Raja, L. (2025). ResDense Fusion: enhancing schizophrenia disorder detection in EEG data through ensemble fusion of deep learning models. Neural Computing and Applications, 37(4), 2411-2433.

Suganyadevi, S., & Seethalakshmi, V. “CVD-HNet: Classifying Pneumonia and COVID-19 in Chest X-ray Images Using Deep Network”. Wireless Personal Communications, Vol.126, no. 4, pp.3279–3303, 2022, doi: 10.1007/s11277-022-09864-y

Balasamy, K., & Suganyadevi, S. “Multi-dimensional fuzzy based diabetic retinopathy detection in retinal images through deep CNN method”. Multimedia Tools and Applications, Vol 83, no. 5, pp.1–23. 2024, doi: 10.1007/s11042-024-19798-1

Shamia, D., Balasamy, K., and Suganyadevi, S. “A secure framework for medical image by integrating watermarking and encryption through fuzzy based roi selection”, Journal of Intelligent & Fuzzy systems, 2023, Vol. 44, no.5, pp.7449-7457, doi: 10.3233/JIFS-222618.

Balasamy, K., Seethalakshmi, V. & Suganyadevi, S. Medical Image Analysis Through Deep Learning Techniques: A Comprehensive Survey. Wireless Pers Commun 137, 1685–1714 (2024). https://doi.org/10.1007/s11277-024-11428-1.

Suganyadevi, S., Seethalakshmi, V. Deep recurrent learning based qualified sequence segment analytical model (QS2AM) for infectious disease detection using CT images. Evolving Systems 15, 505–521 (2024). https://doi.org/10.1007/s12530-023-09554-5.

] Cirillo D, Valencia A. Big data analytics for personalized medicine. Curr Opin Biotechnol 2019;58:161–7.

Harris AD, Amiri H, Bento M, et al. Harmonization of multi-scanner in vivo magnetic resonance spectroscopy: ENIGMA consortium task group considerations. Front Neurol 2023;13:1045678.

Smit DJA, Andreassen OA, Boomsma DI, et al. Large-scale collaboration in ENIGMA-EEG: A perspective on the meta-analytic approach to link neurological and psychiatric liability genes to electrophysiological brain activity. Brain Behav 2021;11:e02188.

Grasby KL, Jahanshad N, Painter JN, et al. The genetic architecture of the human cerebral cortex. Science 2020;367:eaay6690.

Jia T, Chu C, Liu Y, et al. Epigenome-wide meta-analysis of blood DNA methylation and its association with subcortical volumes: Findings from the ENIGMA epigenetics working group. Mol Psychiatry 2021;26:3884–95.

Larivière S, Paquola C, Park B-Y, et al. The ENIGMA toolbox: Multiscale neural contextualization of multisite neuroimaging datasets. Nat Methods 2021;18:698–700.

Jo T, Nho K, Saykin AJ. Deep learning in alzheimer’s disease: Diagnostic classification and prognostic prediction using neuroimaging data. Front Aging Neurosci 2019;11:220.

Ebrahimighahnavieh MA, Luo S, Chiong R. Deep learning to detect Alzheimer’s disease from neuroimaging: A systematic literature review. Comput Methods Programs Biomed 2020;187:105242.

Rathore S, Habes M, Iftikhar MA, et al. A review on neuroimaging-based classification studies and associated feature extraction methods for Alzheimer’s disease and its prodromal stages. Neuroimage 2017;155:530–48.

Ellis KA, Bush AI, Darby D, et al. The australian imaging, biomarkers and lifestyle (AIBL) study of aging: Methodology and baseline characteristics of 1112 individuals recruited for a longitudinal study of Alzheimer’s disease. Int Psychogeriatr 2009;21:672–87.

K. Balasamy, V. Seethalakshmi, “HCO-RLF: Hybrid classification optimization using recurrent learning and fuzzy for COVID-19 detection on CT images”, Biomedical Signal Processing and Control,

Volume 100, Part A, 2025, 106951, https://doi.org/10.1016/j.bspc.2024.106951.

Wang L, Alpert KI, Calhoun VD, et al. SchizConnect: Mediating neuroimaging databases on schizophrenia and related disorders for large-scale integration. Neuroimage 2016;124:1155–67.

Chen X, Lu B, Li H-X, et al. The DIRECT consortium and the REST-meta-MDD project: Towards neuroimaging biomarkers of major depressive disorder. Psychoradiology 2022;2:32–42.

Alotaibi NM, Alhothali AM, Ali MS. Multi-atlas ensemble graph neural network model for major depressive disorder detection using functional MRI data. Front Comput Neurosci. 2025 Jun 9;19:1537284. doi: 10.3389/fncom.2025.1537284. PMID: 40552311; PMCID: PMC12183270.