DECISION TREE INDUCTION - A USEFUL TOOL FOR ASSISTED DIAGNOSIS AND PROGNOSIS IN TUMOR PATHOLOGY

The aim of the present work is to show that decision tree induction al gorithms are a useful tool for extracting reliable information from da ta series, with the objective of assisting pathologists in identifying specific diagnostic and prognostic markers in various types of tumor pathologies. In terms of accuracy, we show that the decision tree tech nique exceeds other more sophisticated techniques, such as multilayer neural networks. Furthermore, because of the ease with which decision tree results can be interpreted (logical classification rules), new me thodologies can be readily developed to further assist in analyzing co mplex data that mix heterogeneous features. In this paper, we illustra te such capabilities in the context of different complex diagnostic an d/or prognostic problems in tumor pathology relating to bladder, astro cytomas, and adipose tissues.