New Detection Method based on ECG Signal Features To Determine Localisation and Extent of Myocardio Infarction using Body Surface Potential Map Data
Cardiovascular diseases lead to death in the world, and Myocardial Infarction (MI) is very dangerous one among those diseases. Patient monitoring for an early detection of MI is most important to alert medical assistance and increase the vital prognostic of patients. In this paper, PhysioNet challenge 2007 Database the Body surface potential map database which consists of ECG of normal and myocardial infarcted patients is used. Since the data available is less, Bilinear Interpolation is used to generate data from the existing. PhysioNet challenge 2007 database has BSPM data. Data is all about four patients with MI, where two patient’s data are used as training set to determine rules, and two other patients for testing set. Three features T-wave amplitude, R-wave amplitude and integration of T-wave are extracted from the ECG signals.The Myocardial Infarction is detected using rule and threshold values using Artificial Neural Network. The accuracy obtained is 96% when 39signals are used for training and 27 signals used for testing.
Keywords - Myocardial Infarction (MI), Body Surface Potential Map (BSPM), Left Ventricle (LV), Right Ventricle (RL).1