| Abstract: | The differential diagnosis of erythemato-squamous diseases is a major challenge in dermatology. This group consists of six different categories: psoriasis, seboreic dermatitis, lichen planus, pityriasis rosea, chronic dermatitis and pityriasis rubra pilaris. They all share the clinical features of erythema and scaling with very little differences. This paper investigates three different data mining methods; multilayer perceptron neural network, C5.0 decision tree and linear discriminate analysis in order to build an ensemble model to the problem of differential diagnosis of these erythemato-squamous diseases. The dermatology dataset investigated in this study is taken from the UCI (from University of California, Department of Information and Computer Science) machine learning database. Given a training set of such instances, the individual model learned how to differentiate a new case in the domain. The proposed ensemble combined the models using a confidence-weighted voting scheme. The classification performance of the proposed system is presented using statistical accuracy, specificity and sensitivity.
|