Classification of otoneurological cases according to Bayesian probabilistic models

We show that Bayesian methods can be efficiently applied to the classification of otoneurological diseases and to assess attribute dependencies. A set of 38 otoneurological attributes was employed in order to use a naive Bayesian probabilistic model and Bayesian networks with different scoring functions for the classification of cases from six otoneurological diseases. Tests were executed on the basis of tenfold crossvalidation. We obtained average sensitivities of 90%, positive predictive values of 92% and accuracies as high as 97%, which is better than our earlier tests with neural networks. Our assessments indicated that Bayesian methods have good power and potential to classify otoneurological patient cases correctly even if this is often a complicated task for the best specialists. Bayesian methods classified the current medical data and knowledge well.