A fuzzy cognitive map based tool for prediction of infectious diseases

The prediction of pulmonary infections in intensive care unit is a complex medical task where a large number of parameters, tests, clinical symptoms and laboratory results are present. The knowledge of physicians according to the physical examination and clinical measurements are the main point to succeed a diagnosis and monitoring patient status. This paper presents the results of our investigation of the problem of representing knowledge for medical diagnosis systems concentrated on the pulmonary infections. The main topic of the presented effort is the representation of the cause-effect relationships within medical data by the application of the soft computing technique of fuzzy cognitive maps. The fuzzy cognitive map is a knowledge based technique for modeling and representing experts´ knowledge. It can handle efficiently with complex modeling problems to assess medical decision making tasks. Due to its easy graphical representation the proposed FCM can be used to make the medical knowledge widely available through computer consultation systems.