Neural network model for classifying renal failure.

Venkatesan, P.; Suresh, M.L.

Book published by Allied Publishers P Ltd. on Mathematics, Computing and Modeling. Ed. P. Balasubramaniam and R. Uthayakumar. 2007;155-160.

Abstract: Artificial Neural Networks (ANNs) are designed to simulate the behavior of biological neural networks for several purposes. They have remarkable ability to derive the meaning from complicated or imprecise data by extracting patterns and detecting trends that are too complex. One of the major problems in medical diagnosis is the subjectivity involved in classification especially in rare diseases like renal failure. This paper discusses the usefulness of Multilayer Feed Forward Neural Network to classify the renal failure into three groups: acute, chronic and diabetic. The novelty of this approach is the use of covariates to obtain accurate classification. A database containing 1200 cases are used in this work and the network model resulted in about 85% correct classification. This work contributes a new methodology and algorithm for renal failure classification problem.

Keywords: Artificial Neural Network, Multilayer Feed Forward Network, diabetes renal failure, logistic model.


Back to List of publications / Home