Application of a genetic programming based rule discovery system to recurring miscarriage data

摘要

This paper introduces a rule inference system based on the paradigm of genetic programming. Rules are deduced from a medical data set related to recurring miscarriage. A rule consists of an IF-part (antecedent) and a THEN-part (consequent). The system has to be supplied with the consequent and works out antecedents. An antecedent classifies the predictive class which is represented by the supplied consequent. The antecedents produced take the form of a tree, where Boolean operations such as AND, OR and NOT represent nodes, and Boolean expressions represent the leaves. Boolean expressions can be built from nominal and numeric attribute values, which makes the system very versatile.