Neural network diagnosis of heart disease

Mortality rate increases all over the world on a daily basis. The reason for this could be largely adduced to the increase in the number of patients with cardiovascular diseases. To worsen the case, many physicians have been known for misdiagnosis of patients reporting heart related ailment. In this paper, an intelligent system has been design which will help in effective diagnosis of the patient to avoid misdiagnosis. The dataset of UCI statlog heart disease has been used in this experiment. The dataset is comprises thirteen features which are vital in diagnosis of heart diseases. The system is model on a multilayer neural network trained with backpropagation and simulated on feedforward neural network. The recognition of 85% was obtained from testing of the network.