Prediction of Myocardial Ischaemia Based on Spectral Analysis of ECG

Disease and death due to myocardial ischemia affect human health and longevity. The electrocardiogram is the cheapest and most readily available diagnostic method for myocardial ischemia. Intelligent diagnosis based on ECG is interesting to study. In this paper, spectral analysis of ECG is performed, from which spectral features related to myocardial ischemia are extracted and a decision tree classifier is constructed to identify the risk of myocardial ischemia. The performance of the model is evaluated based on the predictions on the test set with an accuracy of 94.2%, positive predictive value of 92.7%, sensitivity of 97.9% and specificity of 88.7%.