Evaluation of Artificial Neural Networks in Prediction of Essential Hypertension

This paper investigates the ability of variously designed & trained Artificial Neural Network (ANN) to predict the probability of occurrence of Hypertension (HT) in a mixed (healthy + hypertensive, both sexes) patient population. To do this a multi layer feed-forward neural network with 13 inputs and 1 output was created with multiple hidden layers. Network parameters such as count of hidden layers, count of neurons in the hidden layers, percentage of testing samples and percentage of samples used for validation were varied so as to deliver the maximum prediction accuracy of the ANN network. The training algorithm used for ANN is LevenbergMarquardt back propagation algorithm. A large database, comprising healthy and hypertensive patients from a university hospital was used for training the ANN and prediction. The maximum accuracy marked by this approach was 92.85%, considered quite satisfactory by medical experts. Thus the best network parameter choice best for ANNs approached empirically. General Terms ANN Classification, Diagnosis