3066-280XISSN (Online)
Volume 4 , Issue 2 , PP: 42-52, 2025 | Cite this article as | XML | Html | PDF | Full Length Article
Wei Hong Lim 1 *
Doi: https://doi.org/10.54216/MOR.040205
In this case, the diagnostic and statistical manual for mental disorders has experienced increased advancements in deep generative models (DGMs) that incorporate deep learning in analyzing neuroimaging information. The following review looks at different approaches that have been used in the classification of mental disorders and the specific performance of DGMs like GANs and VAEs. In classifying psychiatric symptoms, it remains challenging to represent the inherent intricacy of data by conventional methods. Thus, techniques that are more accurate are needed to identify complex patterns in extensive data. The newer studies also suggest that DGMs yield higher accuracy than traditional machine learning approaches because the most important features can be identified without requiring significant feature engineering. For example, using GANs to distinguish between major depressive disorder and healthy controls surpasses traditional classifier accuracy by remarkable margins. Moreover, this review contrasts the DGM architectures and their implementations in various psychiatric disorders that can improve diagnostic accuracy and pathophysiological features of diseases. Altogether, the results of the present study emphasize the possibilities of DGMs’ contribution to the field of psychiatry and open possibilities for further studies to deliver more precise diagnostic classifications and enhance the efficacy of treatment by employing the perspective of personalized medicine.
Deep Generative Models , Neuroimaging , Mental Health Diagnostics , Data Augmentation , Personalized Medicine
[1] H. Yamaguchi, G. Sugihara, M. Shimizu, and Y. Yamashita, “Generative artificial intelligence model for simulating structural brain changes in schizophrenia,” Frontiers in Psychiatry, vol. 15, p. 1437075, Oct. 2024, doi: 10.3389/FPSYT.2024.1437075.
[2] Z. Elyoseph and I. Levkovich, “Comparing the Perspectives of Generative AI, Mental Health Ex-perts, and the General Public on Schizophrenia Recovery: Case Vignette Study,” JMIR Mental Health, vol. 11, no. 1, p. e53043, Mar. 2024, doi: 10.2196/53043.
[3] M. Squires et al., “Deep learning and machine learning in psychiatry: a survey of current progress in depression detection, diagnosis and treatment,” Brain Informatics, vol. 10, no. 1, pp. 1–19, Apr. 2023, doi: 10.1186/S40708-023-00188-6.
[4] B. Gao, J. Zhou, Y. Yang, J. Chi, and Q. Yuan, “Generative adversarial network and convolutional neural network-based EEG imbalanced classification model for seizure detection,” Biocybernetics and Biomedical Engineering, vol. 42, no. 1, pp. 1–15, Jan. 2022, doi: 10.1016/J.BBE.2021.11.002.
[5] Q. Yao and H. Lu, “Brain functional connectivity augmentation method for mental disease clas-sification with generative adversarial network,” in Lecture Notes in Computer Science, vol. 11857, pp. 444–455, 2019, doi: 10.1007/978-3-030-31654-9_38/TABLES/4.
[6] W. Ko, W. Jung, E. Jeon, and H. Il Suk, “A Deep Generative-Discriminative Learning for Multi-modal Representation in Imaging Genetics,” IEEE Transactions on Medical Imaging, vol. 41, no. 9, pp. 2348–2359, Sep. 2022, doi: 10.1109/TMI.2022.3162870.
[7] S. Harne et al., “CASE: Efficient Curricular Data Pre-training for Building Assistive Psychology Expert Models,” Jun. 2024. [Online]. Available: https://arxiv.org/abs/2406.00314v3.
[8] Z. Wang, L. Chen, L. Wang, and G. Diao, “Recognition of Audio Depression Based on Convolu-tional Neural Network and Generative Antagonism Network Model,” IEEE Access, vol. 8, pp. 101181–101191, 2020, doi: 10.1109/ACCESS.2020.2998532.
[9] M. Karimi, A. Hasanzadeh, and Y. Shen, “Network-principled deep generative models for design-ing drug combinations as graph sets,” Bioinformatics, vol. 36, no. Supplement_1, pp. i445–i454, Jul. 2020, doi: 10.1093/BIOINFORMATICS/BTAA317.
[10] M. Kahng, N. Thorat, D. H. P. Chau, F. B. Viégas, and M. Wattenberg, “GAN Lab: Understanding Complex Deep Generative Models using Interactive Visual Experimentation,” IEEE Transactions on Visualization and Computer Graphics, vol. 25, no. 1, pp. 310–320, Jan. 2019, doi: 10.1109/TVCG.2018.2864500.
[11] C. Li, J. Zhu, and B. Zhang, “Max-Margin Deep Generative Models for (Semi-)Supervised Learn-ing,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 40, no. 11, pp. 2762–2775, Nov. 2018, doi: 10.1109/TPAMI.2017.2766142.
[12] T. Fernando, S. Denman, S. Sridharan, and C. Fookes, “Memory augmented deep generative models for forecasting the next shot location in tennis,” IEEE Transactions on Knowledge and Data Engineering, vol. 32, no. 9, pp. 1785–1797, Sep. 2020, doi: 10.1109/TKDE.2019.2911507.
[13] M. Bahrami, M. Maitra, C. Nagy, G. Turecki, H. R. Rabiee, and Y. Li, “Deep feature extraction of single-cell transcriptomes by generative adversarial network,” Bioinformatics, vol. 37, no. 10, pp. 1345–1351, Jun. 2021, doi: 10.1093/BIOINFORMATICS/BTAA976.
[14] A. Sun and Z. Wu, “Early Detection of Mental Disorder Via Social Media Posts Using Deep Learn-ing Models,” in Lecture Notes in Electrical Engineering, vol. 978, pp. 149–158, 2023, doi: 10.1007/978-981-19-7904-0_13/TABLES/4.
[15] J. Ive et al., “Generation and evaluation of artificial mental health records for Natural Language Processing,” npj Digital Medicine, vol. 3, no. 1, pp. 1–9, May 2020, doi: 10.1038/s41746-020-0267-x.
[16] F. Zhu, F. Ye, Y. Fu, Q. Liu, and B. Shen, “Electrocardiogram generation with a bidirectional LSTM-CNN generative adversarial network,” Scientific Reports, vol. 9, no. 1, pp. 1–11, May 2019, doi: 10.1038/s41598-019-42516-z.
[17] K. Saha, A. Yousuf, R. L. Boyd, J. W. Pennebaker, and M. De Choudhury, “Social Media Discus-sions Predict Mental Health Consultations on College Campuses,” Scientific Reports, vol. 12, no. 1, pp. 1–11, Jan. 2022, doi: 10.1038/s41598-021-03423-4.
[18] X. Sun, Y. Song, and M. Wang, “Toward Sensing Emotions with Deep Visual Analysis: A Long-Term Psychological Modeling Approach,” IEEE Multimedia, vol. 27, no. 4, pp. 18–27, Oct. 2020, doi: 10.1109/MMUL.2020.3025161.
[19] A. Salatiello, M. Hovaidi-Ardestani, and M. A. Giese, “A Dynamical Generative Model of Social Interactions,” Frontiers in Neurorobotics, vol. 15, p. 648527, Jun. 2021, doi: 10.3389/FNBOT.2021.648527/BIBTEX.
[20] J. Zhang, E. Larschan, J. Bigness, and R. Singh, “scNODE: generative model for temporal single cell transcriptomic data prediction,” Bioinformatics, vol. 40, no. Supplement_2, pp. ii146–ii154, Sep. 2024, doi: 10.1093/BIOINFORMATICS/BTAE393.
[21] G. E. Hinton, S. Osindero, and Y. W. Teh, “A Fast Learning Algorithm for Deep Belief Nets,” Neu-ral Computation, vol. 18, no. 7, pp. 1527–1554, Jul. 2006, doi: 10.1162/NECO.2006.18.7.1527.
[22] Q. Huang, C. Qiao, K. Jing, X. Zhu, and K. Ren, “Biomarkers identification for Schizophrenia via VAE and GSDAE-based data augmentation,” Computational Biology and Medicine, vol. 146, p. 105603, Jul. 2022, doi: 10.1016/J.COMPBIOMED.2022.105603.
