Mining Temporal Medical Data Using Adaptive Fuzzy Cognitive Maps

In this paper, we present our research on mining temporal medical data. In particular, we investigate the possibility of applying fuzzy cognitive maps (FCMs) to discover temporal dependencies between medical concepts. We consider two types of simple concepts, i.e., medical interventions (such as prescribing drugs) and health effects expressed by changes of patients' conditions. The long-term goal of the research is the application of the discovered FCM to medical decision support and planning the therapy of patients. Finally, we present the results of experiments performed on temporal diabetes data.