A hybrid neuro-fuzzy system for ECG classification of myocardial infarction

We present an approach to the automated ECG classification based on a hybrid neuro-fuzzy model. The classification power of the connectionist paradigm has been coupled with the ability of the fuzzy set formalism to treat in a quantitative way natural language. This allows us to build up a system capable of both a good classification accuracy and to give meaningful explanations of the proposed diagnoses, in the form of symbolic IF-THEN rules.