In this paper, attempt has been made to make use of Artificial Neural network in Disease Diagnosis with high accuracy. Heart disease is the case we diagnose here. Classification is an important tool in medical diagnosis. Feed-forward back propagation neural network is used as a classifier to distinguish between absence and presence of disease. It consists of input layer with 13 neuron, a hidden layer with 20 neuron and an output layer with just 1 neuron. An Activation function and the number of neurons in the hidden layer is selected using test and error method. The data were obtained from UCI machine learning repository in order to diagnose the disease. The data is separated into input and target. The targets for the neural network will be classified with 0’s as absence disease and with 1’s as presence disease. The result shows that the network is able to classify 88% of the cases in the testing set.
展开▼