Diagnosis of Parkinson's disease using evolutionary algorithms

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

doi:10.1007/s10710-007-9043-9

Diagnosis of Parkinson's disease using evolutionary algorithms

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

Electronic Engineering

Research output: Contribution to journal › Article › peer-review

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.

Original language	English
Pages (from-to)	433-447
Number of pages	15
Journal	Journal of Genetic Programming and Evolvable Machine
Volume	8
Issue number	4
DOIs	https://doi.org/10.1007/s10710-007-9043-9
Publication status	Published - Dec 2007

Keywords

Parkinson's disease
evolutionary algorithms
cartesian genetic programing
IMPLICIT CONTEXT

Access to Document

10.1007/s10710-007-9043-9

http://link.springer.com/article/10.1007%2Fs10710-007-9043-9

Cite this

@article{b30019cf0d68413cb81fd563466328c2,

title = "Diagnosis of Parkinson's disease using evolutionary algorithms",

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, IMPLICIT CONTEXT",

author = "Smith, {Stephen L.} and Patrick Gaughan and Halliday, {David M.} and Quan Ju and Aly, {Nabil M.} and Playfer, {Jeremy R.}",

year = "2007",

month = dec,

doi = "10.1007/s10710-007-9043-9",

language = "English",

volume = "8",

pages = "433--447",

journal = "Journal of Genetic Programming and Evolvable Machine",

issn = "1389-2576",

publisher = "Springer",

number = "4",

}

TY - JOUR

T1 - Diagnosis of Parkinson's disease using evolutionary algorithms

AU - Smith, Stephen L.

AU - Gaughan, Patrick

AU - Halliday, David M.

AU - Ju, Quan

AU - Aly, Nabil M.

AU - Playfer, Jeremy R.

PY - 2007/12

Y1 - 2007/12

N2 - 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.

AB - 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.

KW - Parkinson's disease

KW - evolutionary algorithms

KW - cartesian genetic programing

KW - IMPLICIT CONTEXT

U2 - 10.1007/s10710-007-9043-9

DO - 10.1007/s10710-007-9043-9

M3 - Article

SN - 1389-2576

VL - 8

SP - 433

EP - 447

JO - Journal of Genetic Programming and Evolvable Machine

JF - Journal of Genetic Programming and Evolvable Machine

IS - 4

ER -