Genetic Programming and Evolvable Machines

, Volume 8, Issue 4, pp 433–447

Diagnosis of Parkinson’s disease using evolutionary algorithms

  • Stephen L. Smith
  • Patrick Gaughan
  • David M. Halliday
  • Quan Ju
  • Nabil M. Aly
  • Jeremy R. Playfer
Original Paper

DOI: 10.1007/s10710-007-9043-9

Cite this article as:
Smith, S.L., Gaughan, P., Halliday, D.M. et al. Genet Program Evolvable Mach (2007) 8: 433. doi:10.1007/s10710-007-9043-9

Abstract

This paper describes the novel application of an evolutionary algorithm to discriminate Parkinson’s patients from age-matched controls in their response to simple figure-copying tasks. The reliable diagnosis of Parkinson’s disease is notoriously difficult to achieve with misdiagnosis reported to be as high as 25% of cases. The approach described in this paper aims to distinguish between the velocity profiles of pen movements of patients and controls to identify distinguishing artifacts that may be indicative of the Parkinson’s symptom bradykinesia. Results are presented for 12 patients with Parkinson’s disease and 10 age-match controls. An algorithm was evolved using half the patient and age-matched control responses, which was then successfully used to correctly classify the remaining responses. A more rigorous “leave one out” strategy was also applied to the test data with encouraging results.

Keywords

Parkinson’s disease Evolutionary algorithms Cartesian genetic programing 

Copyright information

© Springer Science+Business Media, LLC 2007

Authors and Affiliations

  • Stephen L. Smith
    • 1
  • Patrick Gaughan
    • 1
  • David M. Halliday
    • 1
  • Quan Ju
    • 1
  • Nabil M. Aly
    • 2
  • Jeremy R. Playfer
    • 3
  1. 1.Department of ElectronicsThe University of YorkHeslington, YorkUK
  2. 2.University Hospital AintreeLiverpoolUK
  3. 3.Royal Liverpool and Broadgreen University HospitalsLiverpoolUK