Evolving Classifiers to Recognise the Movement Characteristics of Parkinson's Disease Patients

Created by W.Langdon from gp-bibliography.bib Revision:1.3949

@Article{Lones:2014:ieeeTEC,
  author =       "Michael Adam Lones and Stephen Leslie Smith and 
                 Jane Elizabeth Alty and Stuart E. Lacy and 
                 Katherine L. Possin and D. R. Stuart Jamieson and Andy M. Tyrrell",
  title =        "Evolving Classifiers to Recognise the Movement
                 Characteristics of Parkinson's Disease Patients",
  journal =      "IEEE Transactions on Evolutionary Computation",
  year =         "2014",
  volume =       "18",
  number =       "4",
  pages =        "559--576",
  month =        aug,
  keywords =     "genetic algorithms, genetic programming, artificial
                 biochemical networks, Automated disease diagnosis, Time
                 series analysis, Classification",
  ISSN =         "1089-778X",
  URL =          "http://www-users.york.ac.uk/~mal503/common/papers/lones-tevc2013-PD.pdf",
  DOI =          "doi:10.1109/TEVC.2013.2281532",
  size =         "18 pages",
  abstract =     "Parkinson's disease is a debilitating neurological
                 condition that affects approximately 1 in 500 people
                 and often leads to severe disability. To improve
                 clinical care, better assessment tools are needed that
                 increase the accuracy of differential diagnosis and
                 disease monitoring. we report how we have used
                 evolutionary algorithms to induce classifiers capable
                 of recognising the movement characteristics of
                 Parkinson's disease patients. These
                 diagnostically-relevant patterns of movement are known
                 to occur over multiple time scales. To capture this, we
                 used two different classifier architectures:
                 sliding-window genetic programming classifiers, which
                 model over-represented local patterns that occur within
                 time series data, and artificial biochemical networks,
                 computational dynamical systems that respond to
                 dynamical patterns occurring over longer time scales.
                 Classifiers were trained and validated using movement
                 recordings of 49 patients and 41 age-matched controls
                 collected during a recent clinical study. By combining
                 classifiers with diverse behaviours, we were able to
                 construct classifier ensembles with diagnostic
                 accuracies in the region of 95percent, comparable to
                 the accuracies achieved by expert clinicians. Further
                 analysis indicated a number of features of diagnostic
                 relevance, including the differential effect of
                 handedness and the over-representation of certain
                 patterns of acceleration.",
  notes =        "Also known as \cite{6600775}",
}

Genetic Programming entries for Michael A Lones Stephen L Smith Jane E Alty Stuart E Lacy Katherine L Possin D R Stuart Jamieson Andrew M Tyrrell

Citations