Deep Transfer Learning Based Parkinson’s Disease Detection Using Optimized Feature Selection

Authors

  • Muppana Greeshmanth Mallesh
  • B Venkateswarlu

Keywords:

“INDEX TERMS Parkinsons disease, neurological disorder, handwritten records, transfer learning, deep learning

Abstract

Parkinson’s disease (PD) diagnosis remains challenging due to the absence of definitive clinical tests, particularly in its early stages. This study addresses the critical need for an effective and non-invasive methodology for early PD detection by leveraging deep learning, specifically Convolutional Neural Networks (CNNs), to analyze handwriting patterns. Various models including ResNet50, VGG19, InceptionV3, and Xception are employed for feature extraction, with K-Nearest Neighbors (KNN), Random Forest (RF), Support Vector Machine (SVM), and Decision Tree used for classification. The proposed ensemble method combines predictions from multiple models, enhancing accuracy. In the base model, ResNet50 + VGG19 + InceptionV3 with KNN achieved 95% accuracy. As an extension, further exploration of ensemble techniques, including Voting Classifier, is conducted, aiming for 98% accuracy or higher. Additionally, a front end using Flask framework is developed for user testing, incorporating user authentication. This research contributes to advancing early PD detection, crucial for prescribing timely treatment and improving patients' quality of life

Downloads

Download data is not yet available.

References

B. R. Bloem, M. S. Okun, and C. Klein, Parkinsons disease, Lancet, vol. 397, no. 10291, pp. 22842303, 2021.

H. Li, C.-M. Pun, F. Xu, L. Pan, R. Zong, H. Gao, and H. Lu, A hybrid feature selection algorithm based on a discrete arti cial bee colony for Parkinsons diagnosis, ACM Trans. Internet Technol., vol. 21, no. 3, pp. 122, Aug. 2021.

M. Kim, J. Yun, Y. Cho, K. Shin, R. Jang, H. J. Bae, and N. Kim, Deep learning in medical imaging, Neurospine, vol. 16, no. 4, p. 657, 2019.

M. Bakator and D. Radosav, Deep learning and medical diagnosis: Areview of literature, Multimodal Technol. Interact., vol. 2, no. 3, p. 47, Aug. 2018.

Z. Fang, Improved KNN algorithm with information entropy for the diagnosis of Parkinsons disease, in Proc. Int. Conf. Mach. Learn. Knowl. Eng. (MLKE), Feb. 2022, pp. 98101.

E. Kaplan, E. Altunisik, Y. E. Firat, P. D. Barua, S. Dogan, M. Baygin, F. B. Demir, T. Tuncer, E. Palmer, R.-S. Tan, P. Yu, J. Soar, H. Fujita, and U. R. Acharya, Novel nested patch-based feature extraction model for automated Parkinsons disease symptom classi cation using MRI images, Comput. Methods Programs Biomed., vol. 224, Sep. 2022, Art. no. 107030.

M. Gazda, M. Hires, and P. Drotar, Ensemble of convolutional neural networks for Parkinsons disease diagnosis from of ine handwriting, Dept. Comput. Inform., Intell. Inf. Syst. Lab, Tech. Univ. Kosice, Koice, Slovakia, Tech. Rep. 9, 2022.

M. Mohaghegh and J. Gascon, Identifying Parkinsons disease using multimodal approach and deep learning, in Proc. 6th Int. Conf. Innov. Technol. Intell. Syst. Ind. Appl. (CITISIA), Nov. 2021, pp. 16.

M.Fratello, F. Cordella, G. Albani, G. Veneziano, G. Marano, A. Paf , and A. Pallotti, Classi cation-based screening of Parkinsons disease patients through graph and handwriting signals, Eng. Proc., vol. 11, no. 1, p. 49, 2021.

A. Gold, Understanding the mann-whitney test, J. Property Tax Assessment Admin., vol. 4, no. 3, pp. 5557, 2007.

H. W. Loh, C. P. Ooi, E. Palmer, P. D. Barua, S. Dogan, T. Tuncer, M. Baygin, and U. R. Acharya, GaborPDNet: Gabor transformation and deep neural network for Parkinsons disease detection using EEG signals, Electronics, vol. 10, no. 14, p. 1740, Jul. 2021.

S. Chakraborty, S. Aich, J. Seong-Sim, E. Han, J. Park, and H.-C. Kim, Parkinsons disease detection from spiral and wave drawings using convolutional neural networks: A multistage classi er approach, in Proc. 22nd Int. Conf. Adv. Commun. Technol. (ICACT), Feb. 2020, pp. 298303.

S. Nõmm, S. Zarembo, K. Medijainen, P. Taba, and A. Toomela, Deep CNNbasedclassi cation of the archimedes spiral drawing tests to support diagnostics of the Parkinsons disease, IFAC-PapersOnLine, vol. 53, no. 5, pp. 260264, 2020.

T. Tuncer, S. Dogan, and U. R. Acharya, Automated detection of Parkinsons disease using minimum average maximum tree and singular value decomposition method with vowels, Biocybernetics Biomed. Eng., vol. 40, no. 1, pp. 211220, Jan. 2020.

A. Das, H. S. Das, A. Choudhury, A. Neog, and S. Mazumdar, Detection of Parkinsons disease from hand-drawn images using deep transfer learning, in Proc. Congr. Intell. Syst. Singapore: Springer, Sep. 2020, pp. 6784.

L. S. Bernardo, A. Quezada, R. Munoz, F. M. Maia, C. R. Pereira, W. Wu, and V. H. C. De Albuquerque, Handwritten pattern recognition for early Parkinsons disease diagnosis, Pattern Recognit. Lett., vol. 125, pp. 7884, Jul. 2019.

A. Johri and A. Tripathi, Parkinson disease detection using deep neural networks, in Proc. 12th Int. Conf. Contemp. Comput. (IC), Aug. 2019, pp. 14.

T. Tuncer and S. Dogan, A novel octopus based Parkinsons disease and gender recognition method using vowels, Appl. Acoust., vol. 155, pp. 7583, Dec. 2019.

P. Khatamino, I. Canturk, and L. Ozyilmaz, A deep learning-CNN based system for medical diagnosis: An application on Parkinsons disease handwriting drawings, in Proc. 6th Int. Conf. Control Eng. Inf. Technol. (CEIT), Oct. 2018, pp. 16.

[C.-L. Liu, C.-H. Lee, and P.-M. Lin, A fall detection system using K-nearest neighbor classi er, Exp. Syst. Appl., vol. 37, no. 10, pp. 71747181, Oct. 2010.

S. Katoch, S. S. Chauhan, and V. Kumar, A review on genetic algorithm: Past, present, and future, Multimedia Tools Appl., vol. 80, no. 5, pp. 80918126, 2021.

C. R. Pereira, S. A. Weber, C. Hook, G. H. Rosa, and J. P. Papa, Deep learning-aided Parkinsons disease diagnosis from handwritten dynamics, in Proc. 29th Conf. Graph., Patterns Images (SIBGRAPI), Oct. 2016, pp. 340346.

C. R. Pereira, D. R. Pereira, F. A. Silva, J. P. Masieiro, S. A. Weber, C. Hook,andJ.P.Papa, Anewcomputervision-basedapproachtoaidthe diagnosis of Parkinsons disease, Comput. Methods Programs Biomed., vol. 136, pp. 7988, Nov. 2016.

R. Ribani and M. Marengoni, A survey of transfer learning for convolutional neural networks, in Proc. 32nd SIBGRAPI Conf. Graph., Patterns Images Tuts. (SIBGRAPI-T), 2019, pp. 4757.

S. Xu and Z. Pan, A novel ensemble of random forest for assisting diagnosis of Parkinsons disease on small handwritten dynamics dataset, Int. J. Med. Informat., vol. 144, Dec. 2020, Art. no. 104283.

M. Moetesum, I. Siddiqi, N. Vincent, and F. Cloppet, Assessing visual attributes of handwriting for prediction of neurological disorders A case study onParkinsons disease, Pattern Recognit. Lett., vol. 121, pp. 1927, Apr. 2019.

A.Parziale, C. A. Della, R. Senatore, and A. Marcelli, A decision tree for automatic diagnosis of Parkinsons disease from of ine drawing samples: Experimentsandndings,inProc.Int.Conf.ImageAnal.Process.Cham, Switzerland: Springer, 2019, pp. 196206.

J. P. Folador, M. C. S. Santos, L. M. D. Luiz, L. A. P. De Souza, M. F. Vieira, A. A. Pereira, and A. De Oliveira Andrade, On the use of histograms of oriented gradients for tremor detection from sinusoidal and spiral handwritten drawings of people with Parkinsons disease, Med. Biol. Eng. Comput., vol. 59, no. 1, pp. 195214, Jan. 2021.

L. Parisi, D. Neagu, R. Ma, and F. Campean, Quantum ReLU activation for convolutional neural networks to improve diagnosis of Parkinsons disease and COVID-19, Exp. Syst. Appl., vol. 187, Jan. 2022, Art. no. 115892.

Datasetlink: https://www.kaggle.com/datasets/banilkumar20phd7071/handwritten-parkinsons-disease-augmented-data

.

Downloads

Published

2025-05-20

How to Cite

1.
Mallesh MG, Venkateswarlu B. Deep Transfer Learning Based Parkinson’s Disease Detection Using Optimized Feature Selection. J Neonatal Surg [Internet]. 2025May20 [cited 2025Sep.24];14(25S):548-56. Available from: https://www.jneonatalsurg.com/index.php/jns/article/view/6164

Issue

Vol. 14 No. 25S (2025): Journal of Neonatal Surgery

Section

Original Article

License

Creative Commons License

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

You are free to:

  • Adapt — remix, transform, and build upon the material for any purpose, even commercially.

Terms:

  • Attribution — You must give appropriate credit, provide a link to the license, and indicate if changes were made. You may do so in any reasonable manner, but not in any way that suggests the licensor endorses you or your use.
  • No additional restrictions — You may not apply legal terms or technological measures that legally restrict others from doing anything the license permits.