Diagnosis of heart diseases using nonlinear ARX model

This paper proposed the heart disease diagnosis system using nonlinear ARX (NARX) model. The system uses neural network for model estimation and classification of Normal and several heart diseases based on heart sounds. In classification, a spectrogram was applied to the modeled heart sounds for features extraction and selection. The features were fed to the FFNN and trained using Resilient Backpropagation (RPROP) algorithm. With optimized learning parameter of 0.07, the network gave best performance at 32-220-6. The accuracy of the network when validated with the diagnostic test was above 97% which suggests that the network performed well and was doing as gold standard. The classification of heart diseases was further improved to 100% when overall testing was performed.