A novel method for medical disease diagnosis using artificial neural networks based on backpropagation algorithm

In recent year´s artificial neural network has found its application in diagnosing the disease, based upon prediction from previously collected dataset. In this paper, two different artificial neural networks are proposed for disease diagnosis, which uses Scaled Conjugate gradient backpropagation and Levenberg-Marquardt backpropagation algorithm for training the neural networks. The proposed model has been tested on a dataset about Thyroid disease collected from a local hospital. These samples are first trained using Levenberg-Marquardt propagation and outcomes are measured, then the same samples are trained by means of Scaled Conjugate gradient backpropagation algorithm and results are noted. The algorithm used is capable of distinguishing amongst infected person or non-infected person. The results from the two models are compared and analyzed to show the efficiency of prediction by ANNs in medical diagnosis.