Classification of patients on the basis of otoneurological data by using Kohonen networks

Machine learning methods such as neural networks, decision trees and geneti c algorithms can be useful to aid in the classification of patients. We tes ted Kohonen artificial neural networks, which are known to be effective for classification tasks. Our sample included patients with six different dise ases. The Kohonen network algorithm recognized the four largest groups reli ably, but the two smallest groups were too small for the method. Neural net works seem to be promising for the computer-aided classification of otoneur ological patients provided that the number of patients used is sufficiently large.