Combined neural networks for diagnosis of erythemato-squamous diseases

Abstract

This paper illustrates the use of combined neural networks (CNNs) model to guide model selection for diagnosis of the erythemato-squamous diseases. The multilayer perceptron neural networks (MLPNNs) were also tested and benchmarked for their performance on the diagnosis of the erythemato-squamous diseases. The domain contained records of patients with known diagnosis. Given a training set of such records, the classifiers learned how to differentiate a new case in the domain. The first level networks were used to detect the six erythemato-squamous diseases when 34 features defining six disease indications were used as inputs. To improve diagnostic accuracy, the second level networks were trained using the outputs of the first level networks as input data. The CNN model achieved accuracy rates which were higher than that of the stand-alone neural network model (MLPNN).