Can myocardial infarction be predicted in cardiac emergencies?

Myocardial infarction (MI) is a cardiological emergency whose diagnosis in the emergency department remains a clinical problem. In this book an artificial neural network (ANN) was used and compared to logistic regression in the prediction of MI in patients consulting the emergency department for chest pain. Patient data were randomized into training and test series. Neural network and logistic regression models were built on the basis of the training data and tested on observations from the test group. The models were compared by analyzing their ROC (Receiver Operating Curve) curves.