In the paper we show information theory tools for extracting relevant information for decision support systems from medical databases. Each proposed algorithm for selecting a set of relevant features has a specific score function defined by means of information-theoretical characteristics. Then algorithms are classified according to the primary criterion, that can lead to influence-preferring algorithms or weight-preferring algorithms. Other type of classification can be based on the way of selecting of features as forward, backward or combined algorithms. The software package called CORE (COnstitution and REduction) that supports the process of selection of features relevant for a decision making problem is described. Application on data about 1417 middle age men collected in the twenty years lasting interventional study of cardiovascular risk factors in middle aged men and for decision support in primary care are shown. However, the methodology presented is applicable for any decision making problem where extracting relevant information from data is required.

European Center for Medical Informatics Statistics and Epidemiology of Charles University Prague Czech Republic