Selected techniques for data mining in medicine

Widespread use of medical information systems and explosive growth of medic al databases require traditional manual data analysis to be coupled with me thods for efficient computer-assisted analysis. This paper presents selecte d data mining techniques that can be applied in medicine, and in particular some machine learning techniques including the mechanisms that make them b etter suited for the analysis of medical databases (derivation of symbolic rules, use of background knowledge, sensitivity and specificity of induced descriptions). The importance of the interpretability of results of data an alysis is discussed and illustrated on selected medical applications. (C) 1 999 Elsevier Science B.V. All rights reserved.