Use of some variants of Graph Neural Networks for the classification of Electroencephalograms of schizophrenia
Keywords:
Graph Neural Network, Classification, Electroencephalogram, SchizophreniaAbstract
Graph Neural Networks (GNN) are a form of neural network that have shown their added
value on non-Euclidean data such as electroencephalograms (EEG). The aim of this work was to evaluate
some GNN variants for the classification of schizophrenia EEGs; namely Graph Convolution Network
(GCN) and Graph of Attention (GAT). For this purpose, the Pycaret tool and a Convolutional Neural
Network (CNN) were used for the classification of the obtained graphs. This made it possible to compare
GCN and GAT associated with Pycaret on the one hand, and GCN and GCN coupled with a Convolutional
Neural Network (CNN) for classification on the other. It was found that GCN and GAT offer accuracy
of 85% and 80% respectively. GCN coupled with a CNN offers 80% accuracy. However, despite the fact
that GAT is resource intensive, its confusion matrix shows that it offers better sensitivity and specificity
than the other methods. In other words, the error rate is 5%.
References
I’MTech, “Ces technologies qui décryptent le fonctionnement du cerveau,” Feb. 2019. [Online]. Available: https://imtech.imt.fr/2019/02/04/technologies-decrypter-cerveau/
“Introduction to Non-Euclidean Geometry - EscherMath.” [Online]. Available: https://mathstat.slu.edu/escher/index.php/Introduction_to_Non-Euclidean_Geometry
“Maths - Non-Euclidean Spaces - Martin Baker.” [Online]. Available: https://www.euclideanspace.com/maths/geometry/space/nonEuclid/index.htm
D. Ahmedt-Aristizabal, M. A. Armin, S. Denman, C. Fookes, and L. Petersson, “A Survey on Graph-Based Deep Learning for Computational Histopathology,” 2021, publisher: arXiv Version Number: 2. [Online]. Available: https://arxiv.org/abs/2107.00272
D. Ahmedt-Aristizabal, M. A. Armin, S. Denman, C. Fookes, and L. Petersson, “Graph-Based Deep Learning for Medical Diagnosis and Analysis: Past, Present and Future,” Sensors, vol. 21, no. 14, p. 4758, Jul. 2021. [Online]. Available: https://www.mdpi.com/1424-8220/21/14/4758
A. Demir, T. Koike-Akino, Y. Wang, and D. Erdogmu¸s, “EEG-GAT: Graph Attention Networks for Classification of Electroencephalogram (EEG) Signals,” 2022, publisher: Unpublished. [Online]. Available: https://rgdoi.net/10.13140/RG.2.2.19854.23365
M. Kule and M. M. Kaggwa, “Adherence to Typical Antipsychotics among Patients with Schizophrenia in Uganda: A Cross-Sectional Study,” Schizophrenia Research and Treatment, vol. 2023, pp. 1–12, Feb. 2023. [Online]. Available: https://www.hindawi.com/journals/schizort/2023/7035893/
C. Nauck, M. Lindner, K. Schürholt, and F. Hellmann, “Towards Dynamic Stability Assessment of Power Grid Topologies using Graph Neural Networks,” 2022, publisher: arXiv Version Number: 3. [Online]. Available: https://arxiv.org/abs/2206.06369
J. Zhou, G. Cui, S. Hu, Z. Zhang, C. Yang, Z. Liu, L. Wang, C. Li, and M. Sun, “Graph neural networks: A review of methods and applications,” AI Open, vol. 1, pp. 57–81, 2020. [Online]. Available: https://linkinghub.elsevier.com/retrieve/pii/S2666651021000012
B. Mahmud, S. Mahi, M. Shuvo, S. Islam, and M. K. Morol, A comparative analysis of Graph Neural Networks and commonly used machine learning algorithms on fake news detection, Mar. 2022.
Y.-C. Huang, “Condition assessment of power transformers using geneticbased neural networks,” IEE Proceedings - Science, Measurement and Technology, vol. 150, no. 1, p. 19, 2003. [Online]. Available: https://digital-library.theiet.org/content/journals/10.1049/ip-smt_20020638
Z. Chen, P. P. Kulkarni, I. R. Galatzer-Levy, B. Bigio, C. Nasca, and Y. Zhang, “Modern Views of Machine Learning for Precision Psychiatry,” preprint, Apr. 2022. [Online]. Available: https://www.techrxiv.org/articles/preprint/Modern_Views_of_Machine_Learning_for_Precision_Psychiatry/19502131/1
T. Pélagie Flore, J. Kuate Fotso, B. Isaoura, and P. Ele, “Intelligent system for early diagnosis of paediatric cerebral malaria from an electroencephalogram,” Current Medicine Research and Practice, vol. 10, no. 5, p. 210, 2020. [Online]. Available: http://www.cmrpjournal.org/text. asp?2020/10/5/210/299514
P. F. Temgoua Nanfack and A. M. M. Junior, “Study of Metrics that Could be Considered as Inputs to an Intelligent System for Diagnosing Schizophrenia based on an Electroencephalogram (EEG),” European Journal of Engineering and Technology Research, vol. 5, no. 3, pp. 292–296, Mar. 2020. [Online]. Available: https://www.ej-eng.org/index.php/ejeng/article/view/1811
S. L. Oh, J. Vicnesh, E. J. Ciaccio, R. Yuvaraj, and U. R. Acharya, “Deep Convolutional Neural Network Model for Automated
Diagnosis of Schizophrenia Using EEG Signals,” Applied Sciences, vol. 9, no. 14, p. 2870, Jul. 2019. [Online]. Available: https://www.mdpi.com/2076-3417/9/14/2870
A. Shalbaf, S. Bagherzadeh, and A. Maghsoudi, “Transfer learning with deep convolutional neural network for automated detection of schizophrenia from EEG signals,” Physical and Engineering Sciences in Medicine, vol. 43, no. 4, pp. 1229–1239, Dec. 2020. [Online]. Available: https://link.springer.com/10.1007/s13246-020-00925-9
C.-R. Phang, C.-M. Ting, S. B. Samdin, and H. Ombao, “Classification of EEG-based Effective Brain Connectivity in Schizophrenia using Deep Neural Networks,” in 2019 9th International IEEE/EMBS Conference on Neural Engineering (NER). San Francisco, CA, USA: IEEE, Mar. 2019, pp. 401–406. [Online]. Available: https://ieeexplore.ieee.org/document/8717087/
C.-R. Phang, F. Noman, H. Hussain, C.-M. Ting, and H. Ombao, “A Multi-Domain Connectome Convolutional Neural Network for Identifying Schizophrenia From EEG Connectivity Patterns,” IEEE Journal of Biomedical and Health Informatics, vol. 24, no. 5, pp. 1333–1343, May 2020. [Online]. Available: https://ieeexplore.ieee.org/document/8836535/
K. Singh, S. Singh, and J. Malhotra, “Spectral features based convolutional neural network for accurate and prompt identification of schizophrenic patients,” Proceedings of the Institution of Mechanical Engineers, Part H: Journal of Engineering in Medicine, vol. 235, no. 2, pp. 167–184, Feb. 2021. [Online]. Available: http://journals.sagepub.com/doi/10.1177/0954411920966937
M. Hussain, N. A. Alsalooli, N. Almaghrabi, and E.-u.-H. Qazi, “Schizophrenia Detection on EEG Signals Using an Ensemble of a Lightweight Convolutional Neural Network,” Applied Sciences, vol. 14, no. 12, p. 5048, Jun. 2024. [Online]. Available: https://www.mdpi.com/2076-3417/14/12/5048
J. Rahul, D. Sharma, L. D. Sharma, U. Nanda, and A. K. Sarkar, “A systematic review of EEG based automated schizophrenia classification through machine learning and deep learning,” Frontiers in Human Neuroscience, vol. 18, p. 1347082, Feb. 2024. [Online]. Available: https://www.frontiersin.org/articles/10.3389/fnhum.2024.1347082/full
“How AWS uses graph neural networks to meet customer needs,” Mar. 2022. [Online]. Available: https://www.amazon.science/blog/how-aws-uses-graph-neural-networks-to-meet-customer-needs
A. Demir, T. Koike-Akino, Y. Wang, M. Haruna, and D. Erdogmus, EEGGNN: Graph Neural Networks for Classification of Electroencephalogram (EEG) Signals, Jun. 2021.
D. Klepl, F. He, M. Wu, D. J. Blackburn, and P. G. Sarrigiannis, “EEGbased Graph Neural Network Classification of Alzheimer’s Disease: An Empirical Evaluation of Functional Connectivity Methods,” Neuroscience, preprint, Jun. 2022. [Online]. Available: http://biorxiv.org/lookup/doi/10.1101/2022.06.14.496080
A. Rahmani, A. Venkitaraman, and P. Frossard, “A Meta-GNN approach to personalized seizure detection and classification,” 2022, publisher: arXiv Version Number: 1. [Online]. Available: https://arxiv.org/abs/2211.02642
X. Lun, S. Jia, Y. Hou, Y. Shi, Y. Li, H. Yang, S. Zhang, and J. Lv, GCNsNet: A Graph Convolutional Neural Network Approach for Decoding Time-resolved EEG Motor Imagery Signals, Sep. 2022, vol. PP, journal Abbreviation: IEEE Transactions on Neural Networks and Learning Systems Publication Title: IEEE Transactions on Neural Networks and Learning Systems.
N. Wagh and Y. Varatharajah, EEG-GCNN: Augmenting Electroencephalogram-based Neurological Disease Diagnosis using a Domain-guided Graph Convolutional Neural Network, Nov. 2020.
D. Lei, K. Qin, W. H. L. Pinaya, J. Young, T. Van Amelsvoort, M. Marcelis, G. Donohoe, D. O. Mothersill, A. Corvin, S. Vieira, S. Lui, C. Scarpazza, C. Arango, E. Bullmore, Q. Gong, P. McGuire, and A. Mechelli, “Graph Convolutional Networks Reveal NetworkLevel Functional Dysconnectivity in Schizophrenia,” Schizophrenia Bulletin, vol. 48, no. 4, pp. 881–892, Jun. 2022. [Online]. Available: https://academic.oup.com/schizophreniabulletin/article/48/4/881/6586020
S. Ghosh, E. Bhargava, C.-T. Lin, and S. S. Nagarajan, “Graph Convolutional Learning of Multimodal Brain Connectome Data for Schizophrenia Classification,” Bioengineering, preprint, Jan. 2023. [Online]. Available: http://biorxiv.org/lookup/doi/10.1101/2023.01.05.522960
D. Klepl, M. Wu, and F. He, “Graph Neural Network-based EEG Classification: A Survey,” 2023, publisher: [object Object] Version Number: 2. [Online]. Available: https://arxiv.org/abs/2310.02152
E. Olejarczyk and W. Jernajczyk, “Graph-based analysis of brain connectivity in schizophrenia,” PLOS ONE, vol. 12, no. 11, p. e0188629, Nov. 2017. [Online]. Available: https://dx.plos.org/10.1371/journal.pone.0188629
E. Olejarczyk and W. Jernajczyk, “EEG in schizophrenia,” Sep. 2017, publisher: RepOD. [Online]. Available: https://repod.icm.edu.pl/dataset.xhtml?persistentId=
MNE, “MNE — MNE 1.1.1 documentation,” Sep. 2022. [Online]. Available: https://mne.tools/stable/index.html
PyCaret, “Home - PyCaret,” 2022. [Online]. Available: https://pycaret.org/
A. Munjal, R. Khandia, and B. Gautam, “A MACHINE LEARNING APPROACH FOR SELECTION OF POLYCYSTIC OVARIAN SYNDROME (PCOS) ATTRIBUTES AND COMPARING DIFFERENT CLASSIFIER PERFORMANCE WITH THE HELP OF WEKAAND PYCARET,” INTERNATIONAL JOURNAL OF SCIENTIFIC RESEARCH, pp. 59–63, Dec. 2020. [Online]. Available: https://www.worldwidejournals.com/international-journal-of-scientific-research-(IJSR)/recent_issues_pdf/2020/December/a-machine-learning-approach-for-selection-of-polycystic-ovarian-syDecember_2020_6430160911_5416514.pdf
“NN Modules (Tensorflow) — DGL 0.4.3post2 documentation.” [Online]. Available: https://docs.dgl.ai/en/0.4.x/api/python/nn.tensorflow.html#graphconv
J. Lee, J. W. Choi, and S. Jo, “Subject-Independent Motor Imagery EEG Classification Based on Graph Convolutional Network,” in Pattern Recognition, C. Wallraven, Q. Liu, and H. Nagahara, Eds. Cham: Springer International Publishing, 2022, vol. 13189, pp. 268–281, series Title: Lecture Notes in Computer Science. [Online]. Available: https://link.springer.com/10.1007/978-3-031-02444-3_20
S. Wein, A. Schüller, A. M. Tomé, W. M. Malloni, M. W. Greenlee, and E. W. Lang, “Forecasting brain activity based on models of spatiotemporal brain dynamics: A comparison of graph neural network architectures,” Network Neuroscience, vol. 6, no. 3, pp. 665–701, Jul. 2022. [Online]. Available: https://direct.mit.edu/netn/article/6/3/665/111069/Forecasting-brain-activity-based-on-models-of
T. N. Kipf and M. Welling, “Semi-Supervised Classification with Graph Convolutional Networks,” 2016, publisher: arXiv Version Number: 4. [Online]. Available: https://arxiv.org/abs/1609.02907
“Math Behind Graph Neural Networks,” Mar. 2022. [Online]. Available: https://rish-16.github.io/posts/gnn-math/
J. Lu, Y. Tian, S. Wang, M. Sheng, and X. Zheng, “PearNet: A Pearson Correlation-based Graph Attention Network for Sleep Stage Recognition,” Oct. 2022, arXiv:2209.13645 [cs, eess]. [Online]. Available: http://arxiv.org/abs/2209.13645
P. Velickovi ˇ c, G. Cucurull, A. Casanova, A. Romero, P. Liò, and ´ Y. Bengio, “Graph Attention Networks,” Feb. 2018, arXiv:1710.10903 [cs, stat]. [Online]. Available: http://arxiv.org/abs/1710.10903
B. Sanchez-Lengeling, E. Reif, A. Pearce, and A. Wiltschko, “A Gentle Introduction to Graph Neural Networks,” Distill, vol. 6, no. 8, p. 10.23915/distill.00033, Aug. 2021. [Online]. Available: https://distill.pub/2021/gnn-intro
Z. Xiong, Q. Shen, Y. Xiong, YijieWang, and W. Li, “New Generation Model of Word Vector Representation Based on CBOW or Skip-Gram,” Computers, Materials & Continua, vol. 60, no. 1, pp. 259–273, 2019. [Online]. Available: http://www.techscience.com/cmc/v60n1/28351
A. Celikkanat and F. D. Malliaros, “Exponential Family Graph Embeddings,” Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, no. 04, pp. 3357–3364, Apr. 2020. [Online]. Available: https://ojs.aaai.org/index.php/AAAI/article/view/5737
P. Compagnon and K. Olliver, “Graph embeddings for social network analysis, state of the art,” 2016, publisher: Master’s thesis, INSA Lyon. [Online]. Available: https://www.researchgate.net/profile/Paul-Compagnon/publication/331714802_Graph_Embeddings_for_Social_Network_Analysis_State_of_the_Art/links/5c890149a6fdcc381750fc1a/Graph-Embeddings-for-Social-Network-Analysis-State-of-the-Art.pdf
C. Tremblay, “Sensitivity, Specificity & ROC curve / Sensibilité, Spécificité et courbe ROC,” Nov. 2021. [Online]. Available: https://kobia.fr/classification-metrics-sensitivity-specificity-roc/
B. Wang, B. Cai, J. Sheng, and W. Jiao, “AAGCN: a graph convolutional neural network with adaptive feature and topology learning,” Scientific Reports, vol. 14, no. 1, p. 10134, May 2024. [Online]. Available: https://www.nature.com/articles/s41598-024-60598-2
G. Community, “Implement your own word2vec(skipgram) model in Python,” 2024, section: Python. [Online]. Available: https://www.geeksforgeeks.org/implement-your-own-word2vecskip-gram-model-in-python/
L. Reetha and R. Gnanajeyaraman, “A hybrid CNN-GNN approach for enhanced early detection of schizophrenia using EEG data,” in 2025 3rd International Conference on Intelligent Systems, Advanced Computing and Communication (ISACC). Silchar, India: IEEE, Feb. 2025, pp. 810–816. [Online]. Available: https://ieeexplore.ieee.org/document/10969251/
Downloads
Published
How to Cite
Issue
Section
License
International Journal of Computing is an open access journal. Authors who publish with this journal agree to the following terms:• Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
• Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
• Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work.
