Directed Chebyshev Spectral Graph Neural Networks: Continuous MoCA Prediction from EEG in Parkinson’s Disease

Volume 12 ,Issue 3 ,August 2026 ,Pages 153-188

Authors

Ahmed Najat Ahmed Afandy 1 ; Amin Salih Mohammed Kakshar 1 ; Moayad Potrus 1

1 Department of Software and Informatics Engineering, College of Engineering, Salahaddin University-Erbil, Kurdistan Region, Iraq

DOI logo 10.17656/sjes.10222

Keywords

Abstract

Cognitive impairment is a significant and debilitating feature of Parkinson’s disease (PD) among its non-motor symptoms. However, the current clinical tools for assessing cognitive impairment, such as the Montreal Cognitive Assessment (MoCA) test, are subject to several limitations. To address these issues, we developed a deep learning model for predicting the cognitive status of patients with Parkinson’s disease objectively and continuously from their resting-state electroencephalography (EEG) signals. We model the EEG signals as directed brain networks in the frequency domain using Partial Directed Coherence (PDC) and then process these network representations using a graph neural network with Chebyshev spectral convolutions and a self-attention mechanism. We rigorously tested our model using a dataset from 83 patients with Parkinson’s disease and compared its performance with the state-of-the-art deep learning models. Our model outperformed the state-of-the-art models by reaching the highest performance in the Theta (4-8 Hz) and Alpha (8-12 Hz) bands. At the subject level, the model achieved a mean absolute error (MAE) of 0.34 points (0-30 MoCA) and R² of 0.98. These results suggest that the directed network topology of the EEG signals is a sensitive and physiologically meaningful feature for the prediction of cognitive impairment in Parkinson’s disease.

References

  1. Pigott, J. S., Davies, N., Chesterman, E., Read, J., Nimmons, D., Walters, K., ... & Schrag, A. (2023). Delivering optimal care to people with cognitive impairment in Parkinson’s disease: a qualitative study of patient, caregiver, and professional perspectives. Parkinson’s Disease, 2023(1), 9732217.
  2. Aarsland, D., Batzu, L., Halliday, G. M., Geurtsen, G. J., Ballard, C., Ray Chaudhuri, K., & Weintraub, D. (2021). Parkinson disease-associated cognitive impairment. Nature reviews Disease primers, 7(1), 47.
  3. Jellinger, K. A. (2024). Mild cognitive impairment in Parkinson's disease: current view. Frontiers in Cognition, 3, 1369538.
  4. Tröster, A. I. (2023). Parkinson's disease and parkinsonism.
  5. Anjum, M. F., Espinoza, A. I., Cole, R. C., Singh, A., May, P., Uc, E. Y., ... & Narayanan, N. S. (2024). Resting-state EEG measures cognitive impairment in Parkinson’s disease. npj Parkinson's Disease, 10(1), 6.
  6. Ghasemi, M., Boostani, R., & Lak, A. J. (2024, November). A Brief Review on EEG-Based Diagnosis of Parkinson's Disease Using Deep Learning Models. In 2024 E-Health and Bioengineering Conference (EHB) (pp. 1-4). IEEE.
  7. Spoa, M., Monti, S., Bjekić, J., Guerra, A., Fiorenzato, E., Cauzzo, S., ... & Antonini, A. (2025). Resting-state EEG changes associated with cognitive decline in Parkinson’s disease: a systematic review. Journal of Neural Transmission, 1-35.
  8. Noce, G., Percio, C. D., Piervincenzi, C., Carducci, F., Lizio, R., Onorati, P., ... & Babiloni, C. (2023). Brain white matter and resting state eeg markers are abnormal in HIV subjects with relatively good cognitive status. Alzheimer's & Dementia, 19, e063615.
  9. Wang, J., Yue, K., & Duan, L. (2023). Models and techniques for domain relation extraction: a survey. Journal of Data Science and Intelligent Systems, 1(2), 65-82.
  10. Graña, M., & Morais-Quilez, I. (2023). A review of Graph Neural Networks for Electroencephalography data analysis. Neurocomputing, 562, 126901.
  11. Zafeiropoulos, N., Bitilis, P., Tsekouras, G. E., & Kotis, K. (2023). Graph neural networks for parkinson’s disease monitoring and alerting. Sensors, 23(21), 8936.
  12. Lak, A. J., Boostani, R., Alenizi, F. A., Mohammed, A. S., & Fakhrahmad, S. M. (2024). RoBERTa, ResNeXt and BiLSTM with self-attention: The ultimate trio for customer sentiment analysis. Applied Soft Computing, 164, 112018.
  13. Swarnalatha, R., & Salunkhe, S. (2023). EEG-Centered Parkinson's Disease Prediction System Using Gaussian Kernel Discrete Wavelet Transform and Leaky Single Peak Triangle Context Convolutional Neural Network Deep Learning Technique. Medical Research Archives, 11(5).
  14. Desai, K. (2023). Parkinsons Disease Detection via Resting-State Electroencephalography Using Signal Processing and Machine Learning Techniques. arXiv preprint arXiv:2304.01214.
  15. Motin, M. A., Mahmud, M., & Brown, D. J. (2022, October). Detecting Parkinson’s disease from electroencephalogram signals: an explainable machine learning approach. In 2022 IEEE 16th International Conference on Application of Information and Communication Technologies (AICT) (pp. 1-6). IEEE.
  16. Oh, S. L., Hagiwara, Y., Raghavendra, U., Yuvaraj, R., Arunkumar, N., Murugappan, M., & Acharya, U. R. (2020). A deep learning approach for Parkinson’s disease diagnosis from EEG signals. Neural Computing and Applications, 32, 10927-10933.
  17. Loh, H. W., Ooi, C. P., Palmer, E., Barua, P. D., Dogan, S., Tuncer, T., ... & Acharya, U. R. (2021). GaborPDNet: Gabor transformation and deep neural network for Parkinson’s disease detection using EEG signals. Electronics, 10(14), 1740.
  18. Wang, S., Wang, G., Pei, G., & Yan, T. (2022, April). An eeg-based approach for parkinson’s disease diagnosis using capsule network. In 2022 7th International Conference on Intelligent Computing and Signal Processing (ICSP) (pp. 1641-1645).
  19. Li, K., Ao, B., Wu, X., Wen, Q., Ul Haq, E., & Yin, J. (2023). Parkinson’s disease detection and classification using EEG based on deep CNN-LSTM model. Biotechnology and Genetic Engineering Reviews, 1-20.
  20. Xu, S., Wang, Z., Sun, J., Zhang, Z., Wu, Z., Yang, T., ... & Cheng, C. (2020). Using a deep recurrent neural network with EEG signal to detect Parkinson’s disease. Annals of translational medicine, 8(14).
  21. Lee, S., Hussein, R., & McKeown, M. J. (2019, November). A deep convolutional-recurrent neural network architecture for Parkinson’s disease EEG classification. In 2019 IEEE global conference on signal and information processing (GlobalSIP) (pp. 1-4). IEEE.
  22. Shi, X., Wang, T., Wang, L., Liu, H., & Yan, N. (2019, November). Hybrid convolutional recurrent neural networks outperform CNN and RNN in task-state EEG detection for Parkinson's disease. In 2019 Asia-Pacific signal and information processing association annual summit and conference (APSIPA ASC) (pp. 939-944). IEEE.
  23. Parajuli, M., Amara, A. W., & Shaban, M. (2023). Deep-learning detection of mild cognitive impairment from sleep electroencephalography for patients with Parkinson’s disease. Plos one, 18(8), e0286506.
  24. Chu, C., Zhang, Z., Song, Z., Xu, Z., Wang, J., Wang, F., ... & Loparo, K. A. (2022). An enhanced EEG microstate recognition framework based on deep neural networks: an application to Parkinson's disease. IEEE Journal of Biomedical and Health Informatics, 27(3), 1307-1318.
  25. De Oliveira, A. P. S., De Santana, M. A., Andrade, M. K. S., Gomes, J. C., Rodrigues, M. C., & dos Santos, W. P. (2020). Early diagnosis of Parkinson’s disease using EEG, machine learning and partial directed coherence. Research on Biomedical Engineering, 36, 311-331.
  26. Khare, S. K., Bajaj, V., & Acharya, U. R. (2021). PDCNNet: An automatic framework for the detection of Parkinson’s disease using EEG signals. IEEE Sensors Journal, 21(15), 17017-17024.
  27. Maitín, A. M., García-Tejedor, A. J., & Muñoz, J. P. R. (2020). Machine learning approaches for detecting Parkinson’s disease from EEG analysis: a systematic review. Applied Sciences, 10(23), 8662.
  28. Maitin, A. M., Romero Muñoz, J. P., & García-Tejedor, Á. J. (2022). Survey of machine learning techniques in the analysis of EEG signals for Parkinson’s disease: A systematic review. Applied Sciences, 12(14), 6967.
  29. Loh, H. W., Hong, W., Ooi, C. P., Chakraborty, S., Barua, P. D., Deo, R. C., ... & Acharya, U. R. (2021). Application of deep learning models for automated identification of Parkinson’s disease: A review (2011–2021). Sensors, 21(21), 7034.
  30. Shaban, M. (2023). Deep learning for Parkinson’s disease diagnosis: a short survey. Computers, 12(3), 58.
  31. Kurbatskaya, A., Jaramillo-Jimenez, A., Ochoa-Gomez, J. F., Brønnick, K., & Fernandez-Quilez, A. (2023, July). Machine learning-based detection of Parkinson’s disease from resting-state EEG: A multi-center study. In 2023 45th Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC) (pp. 1-4). IEEE.
  32. Sugden, R. J., & Diamandis, P. (2023). Generalizable electroencephalographic classification of Parkinson's disease using deep learning. Informatics in Medicine Unlocked, 42, 101352.
  33. Shaban, M. (2021, May). Automated screening of Parkinson's disease using deep learning-based electroencephalography. In 2021 10th international IEEE/EMBS conference on neural engineering (NER) (pp. 158-161). IEEE.
  34. Suuronen, I., Airola, A., Pahikkala, T., Murtojärvi, M., Kaasinen, V., & Railo, H. (2023). Budget-based classification of Parkinson's disease from resting state EEG. IEEE Journal of Biomedical and Health Informatics, 27(8), 3740-3747.
  35. Bera, S., Geem, Z. W., Cho, Y. I., & Singh, P. K. (2025). A comparative study of machine learning and deep learning models for automatic Parkinson’s disease detection from electroencephalogram signals. Diagnostics, 15(6), 773.
  36. Aljalal, M., Aldosari, S. A., Molinas, M., AlSharabi, K., & Alturki, F. A. (2022). Detection of Parkinson’s disease from EEG signals using discrete wavelet transform, different entropy measures, and machine learning techniques. Scientific Reports, 12(1), 22547.
  37. Sahota, A., Roguski, A., Jones, M. W., Abdallah, Z. S., & Santos-Rodriguez, R. (2024, September). Investigating Brain Connectivity and Regional Statistics from EEG for Early Stage Parkinson's Classification. In 2024 IEEE 34th International Workshop on Machine Learning for Signal Processing (MLSP) (pp. 1-6). IEEE.
  38. Odish, O. F., Johnsen, K., van Someren, P., Roos, R. A., & van Dijk, J. G. (2018). EEG may serve as a biomarker in Huntington’s disease using machine learning automatic classification. Scientific Reports, 8(1), 16090.
  39. Singh, A., Cole, R. C., Espinoza, A. I., Evans, A., Cao, S., Cavanagh, J. F., & Narayanan, N. S. (2021). Timing variability and midfrontal~ 4 Hz rhythms correlate with cognition in Parkinson’s disease. npj Parkinson's Disease, 7(1), 14.
  40. Cao, L. X., Kong, W. L., Chan, P., Zhang, W., Morris, M. J., & Huang, Y. (2024). Assessment tools for cognitive performance in Parkinson’s disease and its genetic contributors. Frontiers in Neurology, 15, 1413187.
  41. Kyriaki, K., Koukopoulos, D., & Fidas, C. A. (2024). A comprehensive survey of eeg preprocessing methods for cognitive load assessment. IEEE Access, 12, 23466-23489.
  42. Delorme, A., & Makeig, S. (2004). EEGLAB: an open source toolbox for analysis of single-trial EEG dynamics including independent component analysis. Journal of neuroscience methods, 134(1), 9-21.
  43. Rashmi, C. R., & Shantala, C. P. (2022). EEG artifacts detection and removal techniques for brain computer interface applications: a systematic review. Int. J. Adv. Technol. Eng. Explor, 9(88), 354.
  44. Rahman, S. A., Khalil, M. I., Zhou, H., Guo, Y., Ding, Z., Gao, X., & Zhang, D. (2025). Advancement in Graph Neural Networks for EEG Signal Analysis and Application: A Review. IEEE Access.
  45. Baccalá, L. A., & Sameshima, K. (2001). Partial directed coherence: a new concept in neural structure determination. Biological cybernetics, 84(6), 463-474.
  46. Chiarion, G., Sparacino, L., Antonacci, Y., Faes, L., & Mesin, L. (2023). Connectivity analysis in EEG data: a tutorial review of the state of the art and emerging trends. Bioengineering, 10(3), 372.
  47. Ashrafi, A. F., & Kabir, M. H. (2025, November). Enhanced Graph Convolutional Network with Chebyshev Spectral Graph and Graph Attention for Autism Spectrum Disorder Classification. In 2025 40th International Conference on Image and Vision Computing New Zealand (IVCNZ) (pp. 1-6). IEEE.
  48. Klepl, D., Wu, M., & He, F. (2024). Graph neural network-based eeg classification: A survey. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 32, 493-503.
  49. Defferrard, M., Bresson, X., & Vandergheynst, P. (2016). Convolutional neural networks on graphs with fast localized spectral filtering. Advances in neural information processing systems, 29.
  50. Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., ... & Polosukhin, I. (2017). Attention is all you need. Advances in neural information processing systems, 30.
  51. Veličković, P., Cucurull, G., Casanova, A., Romero, A., Lio, P., & Bengio, Y. (2017). Graph attention networks. arXiv preprint arXiv:1710.10903.
  52. Mienye, I. D., Swart, T. G., & Obaido, G. (2024). Recurrent neural networks: A comprehensive review of architectures, variants, and applications. Information, 15(9), 517.
  53. Paszke, A., Gross, S., Massa, F., Lerer, A., Bradbury, J., Chanan, G., ... & Chintala, S. (2019). Pytorch: An imperative style, high-performance deep learning library. Advances in neural information processing systems, 32.
  54. Fey, M., & Lenssen, J. E. (2019). Fast graph representation learning with PyTorch Geometric. arXiv preprint arXiv:1903.02428.
  55. Kingma, D. P. (2014). Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980.
  56. Pineau, J., Vincent-Lamarre, P., Sinha, K., Larivière, V., Beygelzimer, A., d'Alché-Buc, F., ... & Larochelle, H. (2021). Improving reproducibility in machine learning research (a report from the neurips 2019 reproducibility program). Journal of machine learning research, 22(164), 1-20.
Statistics
  • Article view11
  • Downloads0
  • First online7 July 2026

  • RIS
  • BibTeX
  • EndNote
  • Mendeley
  • APA (7th edition)
  • MLA (9th edition)
  • Chicago
  • Harvard
  • IEEE
  • Vancouver