Abstract
Generative Adversarial Networks, a popular deep learning method, have achieved excellent performance in both classification and prediction tasks. However, there have been relatively few applications of generative adversarial networks to EEG data. To study the effect of high-order brain functional networks on schizophrenia patients, a high-order graph attention generative adversarial network prediction model is proposed, and the generator of the model utilizes graph attention networks and long short-term memory networks to capture the high-order topological features of persistence images for early diagnosis and prediction of schizophrenia patients. The research results on the five frequency bands of schizophrenia show that the proposed prediction model performs best in the Theta frequency band, with AUC and MAP values reaching 93.5% and 93.0%, respectively, and an average accuracy of 91.5%, both of which are superior to the selected comparison methods. Moreover, the image quality coefficient is used to quantify the realism and clarity of the images generated by the model. the image quality coefficients of schizophrenia patients were significantly correlated with the PANSS total scores in the Gamma and Theta bands, which provided a new idea for generative adversarial networks in the prediction of schizophrenia high-order topological features.
Data availability
The hospital data used has only the right to use it, and is owned by the hospital. We will communicate with the hospital and share the data subject to all regulations and protocols. Data on the results of this study are available upon reasonable request from the corresponding author.
References
Canady, V. A. Schizophrenia drug poised to become first-in-class treatment. Ment. Heal. Wkly. 34, 3–4 (2024).
McCutcheon, R. A., Marques, T. R. & Howes, O. D. Schizophrenia—an overview. JAMA Psychiat. 77(2), 201–210 (2020).
Mucci, A. et al. Factors associated with real-life functioning in persons with schizophrenia in a 4-year follow-up study of the Italian network for research on psychoses. JAMA Psychiat. 78, 550–559 (2021).
De Miras, J. R., Ibáñez-Molina, A. J., Soriano, M. F. & Iglesias-Parro, S. Schizophrenia classification using machine learning on resting state EEG signal. Biomed. Signal Process. Control 79, 104233 (2023).
Shalbaf, A., Bagherzadeh, S. & Maghsoudi, A. Transfer learning with deep convolutional neural network for automated detection of schizophrenia from EEG signals. Phys. Eng. Sci. Med. 43, 1229–1239 (2020).
Yi, X., Walia, E. & Babyn, P. Generative adversarial network in medical imaging: A review. Med. Image Anal. 58, 101552 (2019).
Wang, Z., She, Q. & Ward, T. E. Generative adversarial networks in computer vision: A survey and taxonomy. ACM Comput. Surv. 54, 1–38 (2021).
Osuala, R. et al. Data synthesis and adversarial networks: A review and meta-analysis in cancer imaging. Med. Image Anal. 84, 102704 (2023).
Som, A. et al. Pi-net: A deep learning approach to extract topological persistence images. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops. 834–835 (2020).
Chepushtanova, S. et al. Persistence images: An alternative persistent homology representation. arXiv preprint arXiv:06217. 7 (2015).
Yu, H. et al. Extracting and predicting taxi hotspots in spatiotemporal dimensions using conditional generative adversarial neural networks. IEEE Trans. Veh. Technol. 69, 3680–3692 (2020).
Lei, K. et al. GCN-GAN: A non-linear temporal link prediction model for weighted dynamic networks. In IEEE INFOCOM 2019-IEEE Conference on Computer Communications 388–396 (2019).
Vuletić, M., Prenzel, F. & Cucuringu, M. Fin-gan: Forecasting and classifying financial time series via generative adversarial networks. Quant. Financ. 24, 175–199 (2024).
Yang, T. et al. HGAT: Heterogeneous graph attention networks for semi-supervised short text classification. ACM Trans. Inf. Syst. 39, 1–29 (2021).
Bhatti, U. A. et al. MFFCG–Multi feature fusion for hyperspectral image classification using graph attention network. Expert Syst. Appl. 229, 120496 (2023).
Zhao, K. et al. A dynamic graph convolutional neural network framework reveals new insights into connectome dysfunctions in ADHD. Neuroimage 246, 118774 (2022).
Xu, H., Zhang, S., Jiang, B. & Tang, J. Graph context-attention network via low and high order aggregation. Neurocomputing 536, 152–163 (2023).
He, L. et al. High-order graph attention network. Inf. Sci. 630, 222–234 (2023).
Guan, X., Xing, W., Li, J. & Wu, H. HGAT-VCA: Integrating high-order graph attention network with vector cellular automata for urban growth simulation. Comput. Environ. Urban Syst. 99, 101900 (2023).
Adams, H. et al. Persistence images: A stable vector representation of persistent homology. J. Mach. Learn. Res. 18, 1–35 (2017).
Yan, Y. et al. Topological EEG nonlinear dynamics analysis for emotion recognition. IEEE Trans. Cognit. Dev. Syst. 15, 625–638 (2022).
Levy, W. J. Effect of epoch length on power spectrum analysis of the EEG. Anesthesiology 66, 489–495 (1987).
Hagerty, M. R. et al. Case study of ecstatic meditation: fMRI and EEG evidence of self-stimulating a reward system. Neural Plast. 2013, 653572 (2013).
Hernandez, J. et al. EEG rhythmic and arrhythmic spectral components and functional connectivity at resting state may predict the development of synucleinopathies in idiopathic REM sleep behavior disorder. Sleep. zsae074 (2024).
Vaswani, A. et al. Attention is all you need. Adv. Neural Inf. Process. Syst. 30 (2017).
Velickovic, P. et al. Graph attention networks. Stat. 1050, 10–48550 (2017).
Yang, G., Liu, S., Li, Y. & He, L. Short-term prediction method of blood glucose based on temporal multi-head attention mechanism for diabetic patients. Biomed. Signal Process. Control. 82, 104552 (2023).
Nguyen, M. et al. Predicting Alzheimer’s disease progression using deep recurrent neural networks. Neuroimage 222, 117203 (2020).
Jung, W., Jun, E., Suk, H-I., & Initiative AsDN. Deep recurrent model for individualized prediction of Alzheimer’s disease progression. NeuroImage. 237, 118143 (2021).
Koppe, G., Guloksuz, S., Reininghaus, U. & Durstewitz, D. Recurrent neural networks in mobile sampling and intervention. Schizophr. Bull. 45, 272–276 (2019).
Van Houdt, G., Mosquera, C. & Nápoles, G. A review on the long short-term memory model. Artif. Intell. Rev. 53, 5929–5955 (2020).
Yin, G. et al. Automatic recognition of schizophrenia from brain-network features using graph convolutional neural network. Asian J. Psychiatr. 87, 103687 (2023).
Hyvärinen, A. & Oja, E. Independent component analysis: algorithms and applications. Neural Netw. 13, 411–430 (2000).
Chen, J. et al. FEM: Feature extraction and mapping for radio modulation classification. Phys. Commun. 45, 101279 (2021).
Kim, M. J. et al. Deep learning-based EEG analysis to classify normal, mild cognitive impairment, and dementia: Algorithms and dataset. Neuroimage 272, 120054 (2023).
De Crop, A. et al. Correlation of contrast-detail analysis and clinical image quality assessment in chest radiography with a human cadaver study. Radiology 262, 298–304 (2012).
Acknowledgements
Appreciation is owed to the patients, clinical psychiatrists, and nursing staff in Beijing Huilongguan Hospital for their participation and collaboration. We also thank the Shanxi Provincial Key Laboratory of “Intelligent Optimization Computing and Blockchain Technology” for its support.
Funding
This research was granted by Beijing High-Level Public Health Technical Talent Development Project (Discipline Leader − 02–03, Academic Backbones-02-09), Beijing Natural Science Foundation Grant (No. 7202072), Beijing Municipal Science & Technology Commission Grant (Z191100006619104), and Beijing Hospitals Authority’ Ascent Plan (DFL20192001). This research was also granted by the National Natural Science Foundation of Shanxi Province (No. 202303021221172).
Author information
Authors and Affiliations
Contributions
G.Y. and M.Y. conceived this project. S.T. and Y.Z. collected data from patients with schizophrenia and processed experimental data. G.G. and X.M. wrote data processing codes. J.H., L.W., P.Z., D.S., and B.W. helped with data interpretation. The manuscript was completed under the direction of G.Y. by M.Y., L.W., X.M., and D.S. All the authors contributed to this work through useful discussion and/or comments on the manuscript.
Corresponding author
Ethics declarations
Competing interests
The authors declare no competing interests.
Ethical approval
All experimental protocols were approved by a named institutional and/or licensing committee.
Consent to participate
All authors are contributing and accepting to submit the current work.
Informed consent
All participants provided informed consent. The research process strictly adhered to the ethical principles outlined in the Declaration of Helsinki (1964) and its subsequent revisions. It was also approved by the Research Ethics Committee of Beijing Huilongguan Hospital. Even if the dataset in is a balanced set of healthy subjects, matched by sex, age, and education, there may be other unrecognized biases. All experimental protocols were approved by a named institutional and/or licensing committee.
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Supplementary Information
Below is the link to the electronic supplementary material.
Rights and permissions
Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/.
About this article
Cite this article
Yin, G., Yin, M., Guo, G. et al. Analysis and prediction of schizophrenia patients based on high-order graph attention generative adversarial networks. Sci Rep (2026). https://doi.org/10.1038/s41598-025-15602-8
Received:
Accepted:
Published:
DOI: https://doi.org/10.1038/s41598-025-15602-8
