C. Decaestecker et al., DECISION TREE INDUCTION - A USEFUL TOOL FOR ASSISTED DIAGNOSIS AND PROGNOSIS IN TUMOR PATHOLOGY, Laboratory investigation, 76(6), 1997, pp. 799-808
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.