Signal and Visual Approaches for Parkinson's Disease Detection from Spiral Drawings

Authors

  • Manuel Gil-Martín Universidad Politécnica de Madrid
  • Cristina Luna-Jiménez Universidad Politécnica de Madrid
  • Fernando Fernández-Martínez Universidad Politécnica de Madrid
  • Rubén San-Segundo Universidad Politécnica de Madrid

DOI:

https://doi.org/10.7557/18.6809

Keywords:

Parkinson's detection, deep learning, visual transformer, Fast Fourier Transform, signal

Abstract

The development of medical decision-support technologies that provide accurate biomarkers to physicians is an important research area. For example, in the case of Parkinson's Disease (PD), the current supervisions of patients become intrusive, occasional, and subjective. However, new technologies such as wearable devices, signal processing, computer vision, and deep learning could offer a non-intrusive, continuous, and objective solution to help physicians with patient monitoring. The Parkinson's Disease Spiral Drawings public dataset was selected to face PD detection in this work by comparing four representation methods of the X, Y, and the pressure time series: signal, visual, hand-crafted, and fusion. The signal approach uses the Fast Fourier Transform of recording windows and a Convolutional Neural Network for modeling; the visual strategy employs visual transformer features from gray-scale images; the hand-crafted technique utilizes statistics calculated from temporal signals, and the fusion combines the information from the previous approaches. In these procedures, a Random Forest classifier was used for PD detection using the attributes extracted from each type of representation. The best results showed an F1 score of 93.33% and 93.06% at the user level using a signal approach with the three signals for the Static Spiral Task and an image-based proposal with X and Y coordinates for the Dynamic Spiral Task, respectively.

References

E. Ammenwerth, P. Nykänen, M. Rigby, and N. de Keizer. Clinical decision support systems: Need for evidence, need for evaluation. Artificial Intelligence in Medicine, 59(1):1–3, Sept. 2013. doi: 10.1016/j.artmed.2013.05.001. URL https://doi.org/10.1016/j.artmed.2013.05.001

A. Das, H. S. Das, A. Neog, B. Bharat Reddy, A. Choudhury, and M. Swargiary. Detection of parkinson’s disease from hand-drawn images using machine learning algorithms. In V. S. Reddy, V. K. Prasad, J. Wang, and K. T. V. Reddy, editors, Soft Computing and Signal Processing, pages 241–252, Singapore, 2021. Springer Singapore. ISBN 978-981-33-6912-2

C. Gallicchio, A. Micheli, and L. Pedrelli. Deep echo state networks for diagnosis of parkinson's disease, 2018. URL https://arxiv.org/abs/1802.06708

M. Gil-Martín, J. M. Montero, and R. San-Segundo. Parkinson's disease detection from drawing movements using convolutional neural networks. Electronics, 8(8):907, Aug. 2019. doi: 10.3390/electronics8080907. URL https://doi.org/10.3390/electronics8080907.

M. Gil-Martín, R. San-Segundo, R. de Córdoba, and J. M. Pardo. Robust biometrics from motion wearable sensors using a d-vector approach. Neural Processing Letters, 52(3):2109–2125, Sept. 2020. doi: 10.1007/s11063-020-10339-z. URL https://doi.org/10.1007/s11063-020-10339-z.

M. Gil-Martín, R. San-Segundo, A. Mateos, and J. Ferreiros-Lopez. Human stress detection with wearable sensors using convolutional neural networks. IEEE Aerospace and Electronic Systems Magazine, 37(1):60–70, 2022. doi: 10.1109/MAES.2021.3115198.

U. Hahne, J. Schild, S. Elstner, and M. Alexa. Multi-touch focus+context sketch-based interaction. In Proceedings of the 6th Eurographics Symposium on Sketch-Based Interfaces and Modeling, SBIM '09, page 77–83, New York, NY, USA, 2009. Association for Computing Machinery. ISBN 9781605586021. doi: 10.1145/1572741.1572755. URL https://doi.org/10.1145/1572741.1572755.

M. E. Isenkul, B. E. Sakar, and O. Kursun. Improved spiral test using digitized graphics tablet for monitoring parkinson's disease. In The 2nd International Conference on e-Health and Telemedicine (ICEHTM-2014), 2014.

J. Jankovic. Parkinson's disease: clinical features and diagnosis. Journal of Neurology, Neurosurgery & Psychiatry, 79(4):368–376, Apr. 2008. doi: 10.1136/jnnp.2007.131045. URL https://doi.org/10.1136/jnnp.2007.131045.

P. Khatamino, I. Cantürk, and L. Özyilmaz. A deep learning-CNN based system for medical diagnosis: An application on parkinson's disease handwriting drawings. In 2018 6th International Conference on Control Engineering & Information Technology (CEIT). IEEE, Oct. 2018. doi: 10.1109/ceit.2018.8751879. URL https://doi.org/10.1109/ceit.2018.8751879.

C. Luna-Jiménez, J. Cristóbal-Martín, R. Kleinlein, M. Gil-Martín, J. M. Moya, and F. Fernández-Martínez. Guided spatial transformers for facial expression recognition. Applied Sciences, 11(16), 2021. ISSN 2076-3417. doi: 10.3390/app11167217. URL https://www.mdpi.com/2076-3417/11/16/7217.

B. E. Sakar, M. E. Isenkul, C. O. Sakar, A. Sertbas, F. Gurgen, S. Delil, H. Apaydin, and O. Kursun. Collection and analysis of a parkinson speech dataset with multiple types of sound recordings. IEEE Journal of Biomedical and Health Informatics, 17(4): 828–834, July 2013. doi: 10.1109/jbhi.2013.2245674. URL https://doi.org/10.1109/jbhi.2013.2245674.

R. San-Segundo, M. Gil-Martín, L. F. D'Haro-Enríquez, and J. M. Pardo. Classification of epileptic eeg recordings using signal transforms and convolutional neural networks. Computers in Biology and Medicine, 109:148–158, 2019. ISSN 0010-4825. doi: https://doi.org/10.1016/j.compbiomed.2019.04.031. URL https://www.sciencedirect.com/science/article/pii/S0010482519301398.

R. Saunders-Pullman, C. Derby, K. Stanley, A. Floyd, S. Bressman, R. B. Lipton, A. Deligtisch, L. Severt, Q. Yu, M. Kurtis, and S. L. Pullman. Validity of spiral analysis in early parkinson's disease. Movement Disorders, 23(4):531–537, 2008. doi: 10.1002/mds.21874. URL https://doi.org/10.1002/mds.21874.

Downloads

Published

2023-01-23