A software system for giving clues of medical diagnosis to clinician

Abstract

The importance of developing a support system for medical decision-making in the clinical field has been pointed out for improving the accuracy and objectivity of the judgment of clinicians, and for early detection of disease. In this paper, we notice that signs, symptoms and clinical laboratory data are essential information which show the functional depression and failure of the ecosystem, and a practical software system is presented that provides physicians with clues to clinical diagnosis. First, by analysing the medical task and the structuralization of patient information, a medical modelling method is provided, where diagnosis can be considered as the identification of a patient who corresponds to the controlled object. Secondly, by using the concept of a patient model and a disease model, a system identification algorithm is proposed, and an actual system constructed for medical diagnosis is described in order to confirm the usefulness of the proposed method.