Aphasia Classification Using Neural Networks

H. Axer, Jan Jantzen, G. Berks, Diedrich Graf von Keyserlingk

    Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearch


    A web-based software model (http://fuzzy.iau.dtu.dk/aphasia.nsf) was developed as an example for classification of aphasia using neural networks. Two multilayer perceptrons were used to classify the type of aphasia (Broca, Wernicke, anomic, global) according to the results in some subtests of the Aachen Aphasia Test (AAT). First a coarse classification was achieved by using an assessment of spontaneous speech of the patient. This classifier produced correct results in 87% of the test cases. For a second test, data analysis tools were used to select four features out of the 30 available test features to yield a more accurate diagnosis. This second classifier produced correct results in 92% of the test cases. This test requires four AAT scores as input for the multilayer perceptron. In practice, the second test requires hours of work on behalf of the clinician, whereas the first test can be done in about half an hour in a free interview. The results of the classifiers were analyzed regarding their accuracy dependent on the diagnosis.
    Original languageEnglish
    Title of host publicationAphasia Classification Using Neural Networks
    Publication date2000
    Publication statusPublished - 2000
    EventEuropean Symposium on Intelligent Techniques - Aachen, Germany
    Duration: 14 Sept 200015 Sept 2000


    ConferenceEuropean Symposium on Intelligent Techniques

    Cite this