Eye-Tracking and Machine Learning Significance in Parkinson’s Disease Symptoms Prediction

  • Artur ChudzikEmail author
  • Artur Szymański
  • Jerzy Paweł Nowacki
  • Andrzej W. Przybyszewski
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 12034)


Parkinson’s disease (PD) is a progressive, neurodegenerative disorder characterized by resting tremor, rigidity, bradykinesia, and postural instability. The standard measure of the PD progression is Unified Parkinson’s Disease Rating (UPDRS). Our goal was to predict patients’ UPDRS development based on the various groups of patients in the different stages of the disease. We used standard neurological and neuropsychological tests, aligned with eye movements on a dedicated computer system. For predictions, we have applied various machine learning models with different parameters embedded in our dedicated data science framework written in Python and based on the Scikit Learn and Pandas libraries. Models proposed by us reached 75% and 70% of accuracy while predicting subclasses of UPDRS for patients in advanced stages of the disease who respond to treatment, with a global 57% accuracy score for all classes. We have demonstrated that it is possible to use eye movements as a biomarker for the assessment of symptom progression in PD.


Eye-tracking Saccades Parkinson’s Disease Machine learning 


  1. 1.
    Connolly, B.S., Lang, A.E.: Pharmacological treatment of Parkinson disease: a review. JAMA 311(16), 1670–1683 (2014)CrossRefGoogle Scholar
  2. 2.
    Goldenberg, M.M.: Medical management of Parkinson’s disease. Pharm. Therapeutics 33(10), 590 (2008)Google Scholar
  3. 3.
    Thanvi, B.R., Lo, T.C.N.: Long term motor complications of levodopa: clinical features, mechanisms, and management strategies. Postgrad. Med. J. 80(946), 452–458 (2004)CrossRefGoogle Scholar
  4. 4.
    Benabid, A.L., et al.: Deep brain stimulation of the subthalamic nucleus for the treatment of Parkinson’s disease. Lancet Neurol. 8(1), 67–81 (2009)CrossRefGoogle Scholar
  5. 5.
    Ramaker, C., et al.: Systematic evaluation of rating scales for impairment and disability in Parkinson’s disease. Mov. Disord. Off. J. Mov. Disord. Soc. 17(5), 867–876 (2002)CrossRefGoogle Scholar
  6. 6.
    Henik, A., et al.: Disinhibition of automatic word reading in Parkinson’s disease. Cortex 29(4), 589–599 (1993)CrossRefGoogle Scholar
  7. 7.
    Jones, G.M., DeJong, J.D.: Dynamic characteristics of saccadic eye movements in Parkinson’s disease. Exp. Neurol. 31(1), 17–31 (1971)CrossRefGoogle Scholar
  8. 8.
    White, O.B., et al.: Ocular motor deficits in Parkinson’s disease: II. Control of the saccadic and smooth pursuit systems. Brain 106(3), 571–587 (1983)CrossRefGoogle Scholar
  9. 9.
    Chan, F., et al.: Deficits in saccadic eye-movement control in Parkinson’s disease. Neuropsychologia 43(5), 784–796 (2005)CrossRefGoogle Scholar
  10. 10.
    Przybyszewski, A., et al.: Multimodal learning and intelligent prediction of symptom development in individual Parkinson’s patients. Sensors 16(9), 1498 (2016)CrossRefGoogle Scholar
  11. 11.
    Pedregosa, F., et al.: Scikit-learn: machine learning in Python. J. Mach. Learn. Res. 12, 2825–2830 (2011)MathSciNetzbMATHGoogle Scholar
  12. 12.
    Nij Bijvank, J.A., et al.: A standardized protocol for quantification of saccadic eye movements: DEMoNS. PLoS ONE 13(7), e0200695 (2018)CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  1. 1.Polish-Japanese Academy of Information TechnologyWarsawPoland
  2. 2.Department of NeurologyUniversity of Massachusetts Medical SchoolWorcesterUSA

Personalised recommendations