A fuzzy model for supporting the diagnosis of lumbar disc herniation

Abstract

This paper describes the application of adaptive neuro-fuzzy inference architecture for supporting the diagnosis of lumbar disc herniation. The fuzzy system has been trained with the backpropagation gradient descent method in combination with the least squares method. A total of 38 patients have been divided into training and testing data sets. The performance of the fuzzy model has been evaluated in terms of classification accuracies and the results of the simulation confirmed that the proposed fuzzy approach has potential in supporting the diagnosis of lumbar disc herniation.