Identification of Myocardial Infarction from Multi-Lead ECG signal

Electrocardiogram (ECG) is the cheap and noninvasive method of depicting the heart activity and abnormalities. It provides information about the functionality of the heart. It is the record of variation of bioelectric potential with respect to time as the human heart beats. The classification of ECG signals is an important application since the early detection of heart diseases/abnormalities can prolong life and enhance the quality of living through appropriate treatment. Since the ECG signals, while recording are contaminated by several noises it is necessary to preprocess the signals prior to classification. Digital filters are used to remove noise from the signal. Principal component analysis is applied on the 12 lead signal to extract various features. The present paper shows the unique feature, point score calculated on the basis of the features extracted from the ECG signal. The point score calculation is tested for 40 myocardial infarction ECG signals and 25 Normal ECG signals from the PTB Diagnostic database with 94% sensitivity.