Using multiobjective evolutionary algorithms to understand Parkinson's disease

Marta Vallejo, Jeremy Cosgrove, Jane E. Alty, Stephen L. Smith, David W. Corne, Michael A. Lones

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

The incidence of neurodegenerative diseases such as Parkinson's is increasing rapidly around the world, yet the symptoms and pathology of these diseases remain incompletely understood. As a consequence, it is challenging for clinicians to provide patients with accurate diagnoses or prognoses. In this work, we use multi-objective evolutionary algorithms to explore recordings of patients drawing neurological assessment figures, with the aim of identifying patterns of cognitive and motor signals that discriminate different disease states. As a proof of principle, we demonstrate how this approach can be used to explore the trade-off between predicting clinical measures of motor and cognitive deficit.

Original languageEnglish
Title of host publicationGECCO 2016 Companion
Subtitle of host publicationProceedings of the 2016 Genetic and Evolutionary Computation Conference
PublisherAssociation for Computing Machinery
Pages13-14
Number of pages2
ISBN (Electronic)9781450343237
DOIs
Publication statusPublished - 2016
EventGenetic and Evolutionary Computation Conference 2016 - Denver, United States
Duration: 20 Jul 201624 Jul 2016

Conference

ConferenceGenetic and Evolutionary Computation Conference 2016
Abbreviated titleGECCO 2016
CountryUnited States
CityDenver
Period20/07/1624/07/16

Keywords

  • Multi-objective evolutionary algorithms
  • Parkinson's disease
  • Polynomial regression
  • Predictive modelling

ASJC Scopus subject areas

  • Software
  • Computer Science Applications
  • Computational Theory and Mathematics

Fingerprint Dive into the research topics of 'Using multiobjective evolutionary algorithms to understand Parkinson's disease'. Together they form a unique fingerprint.

Cite this