Automatic Detection and Localization of Myocardial Infarction Using Back Propagation Neural Networks

This paper presents automatic detection and localization of myocardial infarction (MI) using back propagation neural networks (BPNN) classifier with features extracted from 12 lead ECG. Detection of MI aims to classify healthy and subjects having MI. Localization is the task of specifying the infarcted region of the heart. The electrocardiogram (ECG) source used is the PTB database available on Physio-bank. Time domain features of each beat in the ECG signal such as T wave amplitude, Q wave and ST level deviation, which are indicative of MI, are extracted. For localization, lead-wise principal components analysis (PCA) is done on the data extracted from ST-T region and Q wave region of each beat. The resulting principal components are used as features for localization of seven types of myocardial infarction. For detection, it is found that the sensitivity and specificity of BPNN for beat classification is 97.5 % and 99.1% respectively. For localization, PCA based features using back propagation neural network classifier resulted in a beat classification accuracy of 93.7%. The proposed method due to its simplicity and high accuracy over the PTB database can be very helpful in correct diagnosis of MI in a practical scenario.