Proposal of Medical KDD Support User Interface Utilizing Rule Interestingness Measures

This paper discusses the utilization of rule interestingness measures in medical KDD. The authors selected various interestingness measures and conducted experiments using clinical datasets to examine how they can estimate real human interest. The results indicate that some of them have a stable, reasonable estimation performance and the combinational use of interestingness measures will contribute to medical KDD. We then developed a prototype of medical KDD support user interface based on the experimental outcomes. We conducted a case study in which a medical expert tried to discover medical knowledge with the prototype. Some interesting rules were actually obtained and that indicates the potential of the user interface