Classification of resting-state fMRI for olfactory dysfunction in parkinson's disease using evolutionary algorithms

Amir Dehsarvi, Stephen L. Smith

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

Abstract

ccurate early diagnosis and monitoring of neurodegenerative conditions is essential for effective disease management and treatment. This research develops automatic methods for detecting brain imaging preclinical biomarkers for olfactory dysfunction in early stage Parkinson's disease (PD) by considering the novel application of evolutionary algorithms. Classification will be applied to PD patients with severe hyposmia, patients with no/mild hyposmia, and healthy controls. An additional novel element is the use of evolutionary algorithms to map and predict the functional connectivity using rs-fMRI. Cartesian Genetic Programming (CGP) will be used to classify dynamic causal modelling (DCM) data as well as timeseries data. The findings will be validated using two other commonly used classification methods (ANN and SVM) and by employing k-fold cross-validation. Developing methods for identifying early stage PD patients with hyposmia is relevant since current methods of diagnosing early stage PD have low reliability and accuracy. Furthermore, exploring the performance of CGP relative to other methods is crucial given the additional benefits it provides regarding easy classifier decoding. Hence, this research underscores the potential relevance of DCM analyses for classification and CGP as a novel classification tool for brain imaging data with medical implications for disease diagnosis, particularly in early stages.
Original languageEnglish
Title of host publicationProceedings of the Genetic and Evolutionary Computation Conference Companion on - GECCO '18
Place of PublicationNew York
PublisherAssociation for Computing Machinery
Pages264-265
Number of pages2
ISBN (Print)9781450357647
DOIs
Publication statusPublished - 31 Jul 2018
EventThe Genetic and Evolutionary Computation Conference - Kyoto, Japan
Duration: 15 Apr 201819 Apr 2018
http://gecco-2018.sigevo.org/index.html/tiki-index.html

Conference

ConferenceThe Genetic and Evolutionary Computation Conference
Abbreviated titleGECCO '18
CountryJapan
CityKyoto
Period15/04/1819/04/18
Internet address

Keywords

  • Evolutionary Algorithms
  • Cartesian Genetic Programming
  • Classification
  • Parkinson’s Disease
  • Olfactory Dysfunction
  • Resting-State fMRI
  • Dynamic Causal Modeling

Fingerprint Dive into the research topics of 'Classification of resting-state fMRI for olfactory dysfunction in parkinson's disease using evolutionary algorithms'. Together they form a unique fingerprint.

  • Cite this

    Dehsarvi, A., & Smith, S. L. (2018). Classification of resting-state fMRI for olfactory dysfunction in parkinson's disease using evolutionary algorithms. In Proceedings of the Genetic and Evolutionary Computation Conference Companion on - GECCO '18 (pp. 264-265). Association for Computing Machinery. https://doi.org/10.1145/3205651.3205681