Diagnosic system for predicting bladder cancer recurrence using association rules

In this work we present a method based on association rules for the prediction of bladder cancer recurrence. Our objective is to provide a system which is on one hand comprehensible and on the other hand with a high sensitivity. Since data are not equitably distributed among the classes and since errors costs are asymmetric, we propose to handle separately the cases of recurrence and those of no-recurrence. Association rules are generated from each training set, using CBA algorithm, an associative classification approach. To represent the rules uncertainty, each rule is accompanied by a confidence degree estimated during the generation phase. Several symptoms of low intensity can be complementary and mutually reinforcing. This phenomenon is taken into account thanks to aggregate functions which strengthen the confidence degrees of the fired rules. The experimental results are very satisfactory and the sensibility rates are improved in comparison with some other approaches. In addition, interesting extracted knowledge was provided to oncologists.