Childhood leukaemia relapse risk factors. A rough sets approach

Abstract

A rough sets approach was applied to a data set consisting of clinical and laboratory examinations (condition attributes) of children with acute lymphoblastic leukaemia to generate a set of rules for the prediction of disease relapse (conclusion attributes). The information system is presented as a table composed of 69 rows corresponding to the patients and 16 columns corresponding to the attributes. Using manipulation based on rough set theory the information system is reduced to get a subset of a minimum number of attributes ensuring an acceptable quality of classification. Then the conclusion algorithm derived from the reduced system is presented as a conclusion table. The relationship between condition and conclusion attributes is being shown. The research leads to the conclusion that intensive, high dose central nervous system prophylactic irradiation seems to be a better prevention against CNS relapse. Rough set theory is a useful and still complementary tool of medical (biological) data analysis.

The rough set theory and applications

“…Podraza and Podraza (1999) proposed a prediction method for a data set consisting of clinical and laboratory examinations (condition attributes) of children with acute lymphoblastic leukaemia to generate a set of rules for the prediction of disease relapse (conclusion attributes). An information system is constructed as a table composing of 69 rows corresponding to the patients and 26 columns corresponding to the attributes.…”