DS-HViT: A Dual-Stream Hierarchical Vision Transformer for Multi-Scale Analysis of Parkinson's Disease Handwriting

Authors

  • Ayoub Louja Hassan First University of Settat, Faculty of Sciences and Technologies, Laboratoire IR2M, Morocco, Settat
  • Yassin Zaiouane Hassan First University of Settat, Faculty of Sciences and Technologies, Laboratoire IR2M, Morocco, Settat
  • Abdellah Jamali Hassan First University of Settat, Faculty of Sciences and Technologies, Laboratoire IR2M, Morocco, Settat
  • Najib Naja National Institute of Posts and Telecommunications, Rabat, Morocco
Volume: 15 | Issue: 5 | Pages: 28157-28164 | October 2025 | https://doi.org/10.48084/etasr.12833

Received: 19 June 2025 | Revised: 9 July 2025, 20 July 2025, and 25 July 2025 | Accepted: 27 July 2025 | Online: 6 October 2025


Corresponding author: Ayoub Louja

Abstract

Early detection of Parkinson's Disease (PD) remains challenging in the medical field due to motor symptoms manifesting across different temporal scales. To address this, we introduce a Dual-Stream Hierarchical Vision Transformer (DS-HViT), a deep learning framework designed to capture the multi-scale temporal dynamics of PD-related Handwriting (HW) impairments. The architecture employs parallel micro- and macro-scale streams: the micro-scale stream models high-frequency tremor signatures, while the macro-scale stream captures gradual motor decline. The model was evaluated on the NewHandPD dataset using 5-fold patient-stratified cross-validation, complemented by bootstrap analysis and McNemar’s test for statistical validation. DS-HViT achieved an accuracy of 98.2 ± 0.8%, with sensitivity of 97.3 ± 1.2% and specificity of 99.0 ± 0.9%, significantly surpassing state-of-the-art methods (p < 0.01). Ablation studies confirmed the synergistic effect of dual-stream processing, while the model demonstrated excellent calibration with an Expected Calibration Error (ECE) of 0.043 and exceptional discriminative ability with a Diagnostic Odds Ratio (DOR) of 486.3.

Keywords:

Parkinson's disease, handwriting analysis, vision transformer, multi-scale analysis, deep learning

Downloads

Download data is not yet available.

References

World Health Organization, Parkinson Disease: a Public Health Approach. Technical Brief, 1st ed. Geneva: World Health Organization, 2022.

A. Ammour, I. Aouraghe, G. Khaissidi, M. Mrabti, G. Aboulem, and F. Belahsen, "Online Arabic and French handwriting of Parkinson’s disease: The impact of segmentation techniques on the classification results," Biomedical Signal Processing and Control, vol. 66, Apr. 2021, Art. no. 102429.

S. Sveinbjornsdottir, "The clinical symptoms of Parkinson’s disease," Journal of Neurochemistry, vol. 139, no. S1, pp. 318–324, Oct. 2016.

M. Thomas, A. Lenka, and P. K. Pal, "Handwriting Analysis in Parkinson’s Disease: Current Status and Future Directions," Movement Disorders Clinical Practice, vol. 4, no. 6, pp. 806–818, Nov. 2017.

K. W. Lange et al., "Brain dopamine and kinematics of graphomotor functions," Human Movement Science, vol. 25, no. 4–5, pp. 492–509, Oct. 2006.

P. Varalakshmi, B. Tharani Priya, B. A. Rithiga, R. Bhuvaneaswari, and R. S. J. Sundar, "Diagnosis of Parkinson’s disease from hand drawing utilizing hybrid models," Parkinsonism & Related Disorders, vol. 105, pp. 24–31, Dec. 2022.

I. Aouraghe, G. Khaissidi, and M. Mrabti, "A literature review of online handwriting analysis to detect Parkinson’s disease at an early stage," Multimedia Tools and Applications, vol. 82, no. 8, pp. 11923–11948, Mar. 2023.

P. Drotar, J. Mekyska, I. Rektorova, L. Masarova, Z. Smekal, and M. Faundez-Zanuy, "Decision Support Framework for Parkinson’s Disease Based on Novel Handwriting Markers," IEEE Transactions on Neural Systems and Rehabilitation Engineering, vol. 23, no. 3, pp. 508–516, May 2015.

C. R. Pereira et al., "Handwritten dynamics assessment through convolutional neural networks: An application to Parkinson’s disease identification," Artificial Intelligence in Medicine, vol. 87, pp. 67–77, May 2018.

I. Kamran, S. Naz, I. Razzak, and M. Imran, "Handwriting dynamics assessment using deep neural network for early identification of Parkinson’s disease," Future Generation Computer Systems, vol. 117, pp. 234–244, Apr. 2021.

E. Y. Özdemir and F. Özyurt, "Elasticnet-Based Vision Transformers for early detection of Parkinson’s disease," Biomedical Signal Processing and Control, vol. 101, Mar. 2025, Art. no. 107198.

X. Jiang, H. Yu, J. Yang, X. Liu, and Z. Li, "A new network structure for Parkinson’s handwriting image recognition," Medical Engineering & Physics, vol. 139, May 2025, Art. no. 104333.

L. Ali, M.-F. Leung, M. A. Khan, R. Nour, Y. Imrana, and A. V. Vasilakos, "ChiGa-Net: A genetically optimized neural network with refined deeply extracted features using χ 2 statistical score for trustworthy Parkinson’s disease detection," Neurocomputing, vol. 624, Apr. 2025, Art. no. 129450.

A. Y. Jaffar, "Combining Local and Global Feature Extraction for Brain Tumor Classification: A Vision Transformer and iResNet Hybrid Model," Engineering, Technology & Applied Science Research, vol. 14, no. 5, pp. 17011–17018, Oct. 2024.

A. Dey and S. Biswas, "Shot-ViT: Cricket Batting Shots Classification with Vision Transformer Network," International Journal of Engineering, vol. 37, no. 12, pp. 2463–2472, 2024.

X. Wang et al., "LSTM-CNN: An efficient diagnostic network for Parkinson’s disease utilizing dynamic handwriting analysis," Computer Methods and Programs in Biomedicine, vol. 247, Apr. 2024, Art. no. 108066.

A. Dosovitskiy et al., "An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale." arXiv, 2020.

F. Shamshad et al., "Transformers in medical imaging: A survey," Medical Image Analysis, vol. 88, Aug. 2023, Art. no. 102802.

A. Hatamizadeh et al., "UNETR: Transformers for 3D Medical Image Segmentation," in 2022 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), Waikoloa, HI, USA, Jan. 2022, pp. 1748–1758.

R. C. Helmich, M. J. R. Janssen, W. J. G. Oyen, B. R. Bloem, and I. Toni, "Pallidal dysfunction drives a cerebellothalamic circuit into Parkinson tremor," Annals of Neurology, vol. 69, no. 2, pp. 269–281, Feb. 2011.

Y. Liu et al., "HiFT: A Hierarchical Full Parameter Fine-Tuning Strategy." arXiv, 2024, https://doi.org/10.48550/ARXIV.2401.15207.

D. Chicco, V. Starovoitov, and G. Jurman, "The Benefits of the Matthews Correlation Coefficient (MCC) Over the Diagnostic Odds Ratio (DOR) in Binary Classification Assessment," IEEE Access, vol. 9, pp. 47112–47124, 2021.

S. A. Alshammari and N. S. Albalawi, "Enhancing Healthcare Monitoring: A Deep Learning Approach to Human Activity Recognition using Wearable Sensors," Engineering, Technology & Applied Science Research, vol. 14, no. 6, pp. 18843–18848, Dec. 2024.

P. Drotár, J. Mekyska, I. Rektorová, L. Masarová, Z. Smékal, and M. Faundez-Zanuy, "Evaluation of handwriting kinematics and pressure for differential diagnosis of Parkinson’s disease," Artificial Intelligence in Medicine, vol. 67, pp. 39–46, Feb. 2016.

A. S. Glas, J. G. Lijmer, M. H. Prins, G. J. Bonsel, and P. M. M. Bossuyt, "The diagnostic odds ratio: a single indicator of test performance," Journal of Clinical Epidemiology, vol. 56, no. 11, pp. 1129–1135, Nov. 2003.

I. Drira et al., "Eye-Rubbing Detection Tool Using Artificial Intelligence on a Smartwatch in the Management of Keratoconus," Translational Vision Science & Technology, vol. 13, no. 12, Dec. 2024, Art. no. 16.

A. Louja, I. Drira, A. Jamali, N. Naja, and L. Sliman, "Wearable sensor-based eye-rubbing monitoring: a hybrid CNN-attentionrub architecture for keratoconus prevention," The Journal of Supercomputing, vol. 81, no. 13, Aug. 2025, Art. no. 1268.

S. Yaqoob et al., "Use of Blockchain in Healthcare: A Systematic Literature Review," International Journal of Advanced Computer Science and Applications, vol. 10, no. 5, 2019.

A. Louja, A. Jamali, and N. Naja, "Blockchain-Powered Artificial Intelligence for Healthcare Systems Data Orchestration," in Proceedings of the Third ICMDS’24: Machine Learning, Inverse Problems and Related Fields, vol. 1466, A. Laghrib and A. Ghazdali, Eds. Cham: Springer Nature Switzerland, 2025, pp. 155–163.

M. Zouidine and M. Khalil, "Large Language Models for Arabic Sentiment Analysis and Machine Translation," Engineering, Technology & Applied Science Research, vol. 15, no. 2, pp. 20737–20742, Apr. 2025.

Downloads

How to Cite

[1]
A. Louja, Y. Zaiouane, A. Jamali, and N. Naja, “DS-HViT: A Dual-Stream Hierarchical Vision Transformer for Multi-Scale Analysis of Parkinson’s Disease Handwriting”, Eng. Technol. Appl. Sci. Res., vol. 15, no. 5, pp. 28157–28164, Oct. 2025.

Metrics

Abstract Views: 31
PDF Downloads: 5

Metrics Information

License

Copyright (c) 2025 Ayoub Louja, Zaiouane Yassin, Abdellah Jamali, Najib Naja

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

Authors who publish with this journal agree to the following terms:

- Authors retain the copyright and grant the journal the 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) after its publication in ETASR with an acknowledgement of its initial publication in this journal.