Parkinson’s Disease Detection from Handwriting Using VGG-16 and Random Forest
DOI:
https://doi.org/10.30871/jaic.v10i2.12428Keywords:
Early Detection, Parkinson's Disease, Random Forest, VGG-16Abstract
Parkinson’s disease is one of the most common neurodegenerative diseases in Indonesia and remains incurable. However, early recognition of Parkinson’s disease makes it possible for timely intervention to be conducted. Unfortunately, Parkinson’s disease detection process can sometimes take a long time. This study proposes a system for early Parkinson’s disease using offline handwriting images and machine learning techniques. The system employs VGG-16 for feature extraction and Random Forest classifier for prediction to recognize early signs of Parkinson’s disease through three handwriting tasks, namely spirals, meander and circle using publicly available NewHandPD dataset containing 594 samples across all tasks. The model will be trained using original data as well as images processed with three preprocessing techniques, namely grayscale, grayscale with CLAHE and grayscale with CLAHE and Otsu thresholding. In the final testing phase using a held-out test set, the model trained on the original data achieved the best performance, achieving average accuracy of 94%. The best performing model will be hosted in a cloud-based environment and accessed by a developed software application through an API. A questionnaire was conducted using the USE Questionnaire, resulting in average score of 90,97%. Indicating a high level of user satisfaction for the application developed in this study.
Downloads
References
[1] D. M. Wilson, M. R. Cookson, L. Van Den Bosch, H. Zetterberg, D. M. Holtzman, and I. Dewachter, “Hallmarks of neurodegenerative diseases,” Cell, vol. 186, no. 4, pp. 693–714, Feb. 2023, doi: 10.1016/j.cell.2022.12.032.
[2] I. Karlina et al., “Gambaran penyakit neurodegeneratif: Huntington, Alzheimer, dan Parkinson: Sebuah tinjauan,” Jurnal Biomedika dan Kesehatan, vol. 7, no. 1, pp. 113–123, Mar. 2024, doi: 10.18051/JBiomedKes.2024.v7.113-123.
[3] World Health Organization, Parkinson disease: A public health approach. Technical brief. World Health Organization, 2022. [Online]. Available: https://books.google.co.id/books?id=CngOEQAAQBAJ
[4] N. Raisa, A. F. Insanitaqwa, and M. Rahayu, “The depiction of general physician’s knowledge level of Parkinson’s disease in Indonesia,” MNJ (Malang Neurology Journal), vol. 9, no. 2, pp. 129–133, Jul. 2023, doi: 10.21776/ub.mnj.2023.009.02.10.
[5] R. B. Postuma and D. Berg, “Advances in markers of prodromal Parkinson disease,” Nat. Rev. Neurol., vol. 12, no. 11, pp. 622–634, Nov. 2016, doi: 10.1038/nrneurol.2016.152.
[6] J. Zhang, “Mining imaging and clinical data with machine learning approaches for the diagnosis and early detection of Parkinson’s disease,” NPJ Parkinsons Dis., vol. 8, no. 1, p. 13, Jan. 2022, doi: 10.1038/s41531-021-00266-8.
[7] Z. Wang et al., “A minimally invasive biomarker for sensitive and accurate diagnosis of Parkinson’s disease,” Acta Neuropathol. Commun., vol. 12, no. 1, p. 167, Oct. 2024, doi: 10.1186/s40478-024-01873-1.
[8] S. Ali, A. Hashmi, A. Hamza, U. Hayat, and H. Younis, “Dynamic and static handwriting assessment in Parkinson’s disease: A synergistic approach with C-Bi-GRU and VGG19,” Journal of Computing Theories and Applications, vol. 1, no. 2, pp. 151–162, Dec. 2023, doi: 10.33633/jcta. v1i2.9469.
[9] E. V. Altay and B. Alatas, “Association analysis of Parkinson disease with vocal change characteristics using multi-objective metaheuristic optimization,” Med. Hypotheses, vol. 141, p. 109722, Aug. 2020, doi: 10.1016/j.mehy.2020.109722.
[10] M. Diaz, M. Moetesum, I. Siddiqi, and G. Vessio, “Sequence-based dynamic handwriting analysis for Parkinson’s disease detection with one-dimensional convolutions and BiGRUs,” Expert Syst. Appl., vol. 168, p. 114405, Apr. 2021, doi: 10.1016/j.eswa.2020.114405.
[11] A. Ammour, I. Aouraghe, G. Khaissidi, M. Mrabti, G. Aboulem, and F. Belahsen, “A new semi-supervised approach for characterizing the Arabic on-line handwriting of Parkinson’s disease patients,” Comput. Methods Programs Biomed., vol. 183, p. 104979, Jan. 2020, doi: 10.1016/j.cmpb.2019.07.007.
[12] J. Mei, C. Desrosiers, and J. Frasnelli, “Machine learning for the diagnosis of Parkinson’s disease: A review of literature,” Front. Aging Neurosci., vol. 13, May 2021, doi: 10.3389/fnagi.2021.633752.
[13] N. M. Ranjan, G. Mate, and M. Bembde, “Detection of Parkinson’s disease using machine learning algorithms and handwriting analysis,” Journal of Data Mining and Management, vol. 8, no. 1, pp. 21–29, Mar. 2023, doi: 10.46610/JoDMM.2023.v08i01.004.
[14] M. Gazda, M. Hires, and P. Drotar, “Multiple-fine-tuned convolutional neural networks for Parkinson’s disease diagnosis from offline handwriting,” IEEE Trans. Syst. Man Cybern. Syst., vol. 52, no. 1, pp. 78–89, Jan. 2022, doi: 10.1109/TSMC.2020.3048892.
[15] A. Das, H. S. Das, A. Neog, R. B. Bharat, A. Choudhury, and M. Swargiary, “Detection of Parkinson’s disease from hand-drawn images using machine learning algorithms,” in Soft Computing and Signal Processing, V. K. and W. J. and R. K. T. V Reddy V. Sivakumar and Prasad, Ed., Singapore: Springer Singapore, 2021, pp. 241–252.
[16] C. R. Pereira, S. A. T. Weber, C. Hook, G. H. Rosa, and J. P. Papa, “Deep learning-aided Parkinson’s disease diagnosis from handwritten dynamics,” in 2016 29th SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI), IEEE, Oct. 2016, pp. 340–346. doi: 10.1109/SIBGRAPI.2016.054.
[17] K. Kusnadi and D. A. S. P. Atmaja, “Implementation of grayscale image transformation and histogram equalization methods in digital image processing,” Krisnadana Journal, vol. 4, no. 2, pp. 111–121, 2025.
[18] M. Hayati et al., “Impact of CLAHE-based image enhancement for diabetic retinopathy classification through deep learning,” Procedia Comput. Sci., vol. 216, pp. 57–66, 2023, doi: 10.1016/j.procs.2022.12.111.
[19] A. Riadi and R. Sulaehani, “Analisis implementasi preprocessing dengan Otsu-Gaussian pada pengenalan wajah,” ILKOM Jurnal Ilmiah, vol. 11, no. 3, pp. 200–205, Dec. 2019, doi: 10.33096/ilkom.v11i3.457.200-205.
[20] V. Jackins, S. Vimal, M. Kaliappan, and M. Y. Lee, “AI-based smart prediction of clinical disease using random forest classifier and Naive Bayes,” J. Supercomput., vol. 77, no. 5, pp. 5198–5219, May 2021, doi: 10.1007/s11227-020-03481-x.
[21] A. Parmar, R. Katariya, and V. Patel, “A review on random forest: An ensemble classifier,” International Conference on Intelligent Data Communication Technologies and Internet of Things, pp. 758–763, 2019, doi: 10.1007/978-3-030-03146-6_86.
[22] T. F. Basar, D. E. Ratnawati, and I. Arwani, “Analisis sentimen pengguna Twitter terhadap pembayaran cashless menggunakan ShopeePay dengan algoritma random forest,” Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer, vol. 6, no. 3, pp. 1426–1433, Feb. 2022, [Online]. Available: https://j-ptiik.ub.ac.id/index.php/j-ptiik/article/view/10830
[23] K. Kamal and H. Ez-Zahraouy, “A comparison between the VGG16, VGG19 and ResNet50 architecture frameworks for classification of normal and CLAHE processed medical images,” Apr. 28, 2023. doi: 10.21203/rs.3.rs-2863523/v1.
[24] S. Tammina, “Transfer learning using VGG-16 with deep convolutional neural network for classifying images,” International Journal of Scientific and Research Publications (IJSRP), vol. 9, no. 10, p. p9420, Oct. 2019, doi: 10.29322/IJSRP.9.10.2019.p9420.
[25] A. P. Siregar, D. P. Purba, J. P. Pasaribu, and K. R. Bakara, “Implementasi algoritma random forest dalam klasifikasi diagnosis penyakit stroke,” Jurnal Penelitian Rumpun Ilmu Teknik, vol. 2, no. 4, pp. 155–164, Nov. 2023, doi: 10.55606/juprit.v2i4.3039.
[26] D. Theckedath and R. R. Sedamkar, “Detecting affect states using VGG16, ResNet50 and SE-ResNet50 networks,” SN Comput. Sci., vol. 1, no. 2, p. 79, Mar. 2020, doi: 10.1007/s42979-020-0114-9.
[27] E. Bolin and W. Lam, “A review of sensitivity, specificity, and likelihood ratios: Evaluating the utility of the electrocardiogram as a screening tool in hypertrophic cardiomyopathy,” Congenit. Heart Dis., vol. 8, no. 5, pp. 406–410, Sep. 2013, doi: 10.1111/chd.12083.
[28] E. Richardson, R. Trevizani, J. A. Greenbaum, H. Carter, M. Nielsen, and B. Peters, “The receiver operating characteristic curve accurately assesses imbalanced datasets,” Patterns, vol. 5, no. 6, Jun. 2024, doi: 10.1016/j.patter.2024.100994.
[29] K. Kristiawan and A. Widjaja, “Perbandingan algoritma machine learning dalam menilai sebuah lokasi toko ritel,” Jurnal Teknik Informatika dan Sistem Informasi, vol. 7, no. 1, pp. 35–46, Apr. 2021, doi: 10.28932/jutisi.v7i1.3182.
[30] W. A. Kusuma, V. Noviasari, and G. I. Marthasari, “Analisis usability dalam user experience pada sistem KRS online UMM menggunakan USE questionnaire,” Jurnal Nasional Teknik Elektro dan Teknologi Informasi, vol. 5, no. 4, pp. 294–301, Nov. 2016.
[31] Y. Huang, K. Chaturvedi, A.-A. Nayan, M. H. Hesamian, A. Braytee, and M. Prasad, “Early Parkinson’s disease diagnosis through hand-drawn spiral and wave analysis using deep learning techniques,” Information, vol. 15, no. 4, p. 220, Apr. 2024, doi: 10.3390/info15040220.
[32] S. Sumartini, K. S. Harahap, and S. Sthevany, “Kajian Pengendalian Mutu Produk Tuna Loin Precooked Frozen Menggunakan Metode Skala Likert di Perusahaan Pembekuan Tuna,” Aurelia Journal, vol. 2, no. 1, p. 29, Nov. 2020, doi: 10.15578/aj.v2i1.9392.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Billy Franko, Derry Alamsyah
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
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 (Attribution-ShareAlike 4.0 International (CC BY-SA 4.0) ) 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 (See The Effect of Open Access).
