Classification of types of dementia using a neural network model

D. L. Hudson, M. E. Cohen, M. Kramer, A. Szeri, F. L. Chang

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

2 Scopus citations

Abstract

Both diagnosis of dementia and differentiation among dementia caused by different disorders continue to be a challenge with the only definitive diagnosis available from autopsy results. The diagnosis relies on the combination of factors from a number of sources. Due to the number of factors involved, the problem is suitable for a neural network solution in which all parameters can be included along with a weighting factor for each that indicates its degree of relevance to the diagnosis. The Hypernet neural network developed by Cohen and Hudson is used to combine diverse parameters including measures derived from a new method for electroencephalogram (EEG) analysis.

Original languageEnglish (US)
Title of host publication20th International Conference on Computers and Their Applications 2005, CATA 2005
Pages208-213
Number of pages6
StatePublished - Dec 1 2005
Event20th International Conference on Computers and Their Applications 2005, CATA 2005 - New Orleans, LA, United States
Duration: Mar 16 2005Mar 18 2005

Publication series

Name20th International Conference on Computers and Their Applications 2005, CATA 2005

Other

Other20th International Conference on Computers and Their Applications 2005, CATA 2005
CountryUnited States
CityNew Orleans, LA
Period3/16/053/18/05

    Fingerprint

Keywords

  • Biomedical engineering
  • Computer modeling
  • Knowledge discovery
  • Neural networks
  • Pattern recognition

ASJC Scopus subject areas

  • Computer Science Applications

Cite this

Hudson, D. L., Cohen, M. E., Kramer, M., Szeri, A., & Chang, F. L. (2005). Classification of types of dementia using a neural network model. In 20th International Conference on Computers and Their Applications 2005, CATA 2005 (pp. 208-213). (20th International Conference on Computers and Their Applications 2005, CATA 2005).