FUZZY MODELING OF THE EXPERTS KNOWLEDGE IN EGG-BASED ISCHEMIA DETECTION

We concentrate on computational implementations of the detection of is chaemic episodes in order to allow continuous monitoring of patients i nterned in Coronary Care Units (CCU). The consideration of several alt ernatives led us to choosing an implementation based on the expert's k nowledge as the most adequate. In order to solve the problem of transf orming the imprecise knowledge provided by the expert into computable structures we have decided to make use of a fuzzy implementation. We i llustrate and comment the operation of our solution over some records of the European ST-T Database, which is an electrocardiographic databa se specifically aimed at the validation of algorithms whose objective is the detection of ischaemic episodes. This work can be included in t he more general problem of the design, physical implementation and val idation of an electronic-computational system (SUTIL), which by means of the simultaneous, integrated and intelligent evaluation of a large amount of information extracted from real time processing of haemodyna mic and electrocardiographic signals, performs an intensive and exhaus tive follow up of patients with ischaemic cardiopathies interned in CC Us.