An entropy-based method for ischemia diagnosis using ECG signal in wavelet domain

Ischemia means lack of oxygen due to insufficient blood circulation. Cardiac ischemia disease, which is one of the common fatal diseases in advanced countries, is a condition due to imbalance between supply and demand of oxygen. In this study the existence of ischemia is considered using entropy measure. Since signal perturbation in healthy people is less than signal perturbation in patients, generally it is observed that there is higher entropy in patients and lower entropy in healthy ones. In this base, 4 methods (in spatial and wavelet domains) are proposed for comparing entropy of processed electrocardiogram (ECG) signal of healthy and patient people. Our simulations on 20 recorded ECG signal from 10 healthy and 10 patient people show that proposed technique in wavelet domain results in highest discrepancy between healthy and patient subjects in comparison to other methods and specificity and sensitivity of this method are 88.8% and 90% respectively.