Risk assessment for acute myocardial infarction patients using artificial neural networks

The purpose of the study was to develop a clinical score for risk assessment to determine the profile of every patient with acute myocardial infarction (MI). A cohort of 1,318 consecutive patients with a first MI admitted to four referral teaching hospitals (one with tertiary facilities) were followed up for 6 months after admission. To classify patients an artificial neural network (ANN), called a multilayer perceptron was used with the backpropagation learning algorithm. This method is used to analyse a collection of simple clinical markers. The model has achieved high values of sensitivity and specificity in the classification of the patients, training both in the training cohort (91.58% sensitivity, 79.37% specificity), and the validation cohort (88.46% sensitivity, 78.09% specificity). The use of simple clinical variables allows ANNs to give a reliable prediction of risk for in-hospital and 6 month mortality.