Comparison of four computer-aided diagnosis schemes for automated discrimination of myocardial heart disease

The aim of this paper is to compare the performance of four different methods, i.e., neural network (NN) with backpropagation learning, NN with genetic-algorithm-based (GA-based) learning, fuzzy reasoning, and the GA-based fuzzy logic approach, for automated discrimination of myocardial heart disease. In our experiments, a total of 90 samples of echocardiographic images from 45 subjects were used. Our results showed that the GA-based fuzzy logic approach is superior to the other three methods. This method enables the classification to achieve a 95.9% of accuracy.