Personal computer system for ECG recognition in myocardial infarction diagnosing based on an artificial neural network

A personal computer system for electrocardiogram recognition is developed as a medical tool in myocardial infarction (MI) diagnosis. It uses a backpropagation type artificial neural network (ANN) as processing element. A signal preprocessing is made in order to reduce noise in the ECG and to make measurements of the exact incidence in time and amplitudes of the Q, R, S, P and T waves. These measurements plus patient age and sex, form a neural network input vector. The ANN output is associated with a medical diagnostic. Six classes are identified: normal, left ventricular hypertrophy, right ventricular hypertrophy, biventricular hypertrophy, anterior myocardial infarction, inferior myocardial infarction.