A comparison of neural network and Bayes recognition approaches in the evaluation of the brainstem trigeminal evoked potentials in multiple sclerosis

Hugo Guterman, Youval Nehmadi, Andrei Chistyakov, Jean F. Soustiel, Moshe Feinsod

Research output: Contribution to journalArticlepeer-review

11 Scopus citations

Abstract

This article describes the application of Multi-Layer Perceptron (MLP), Probabilistic Neural Network and Kohonen's Learning Vector Quantization to the problem of diagnosing Multiple Sclerosis. The classification information is obtained from brainstem trigeminal evoked potential. The performance of the neural networks based classifiers is compared with that of the human experts and the Bates classifier. The ability of the MLP classifier to generalize is far better than that of the Bayes classifier. The efficiency of the neural network based classifiers in conjunction with several types of well-known evoked potential features, such as Fourier transform space, latency and temporal wave, is examined. Although a large clinical database would be necessary before this approach can be fully validated, the initial results are promising.

Original languageEnglish
Pages (from-to)203-213
Number of pages11
JournalInternational Journal of Bio-Medical Computing
Volume43
Issue number3
DOIs
StatePublished - 1 Dec 1996

Keywords

  • Bayes
  • Brainstem
  • Evoked potentials
  • Multiple sclerosis
  • Neural networks
  • Pattern recognition

Fingerprint

Dive into the research topics of 'A comparison of neural network and Bayes recognition approaches in the evaluation of the brainstem trigeminal evoked potentials in multiple sclerosis'. Together they form a unique fingerprint.

Cite this