Diagnosis of Atopic dermatitis Using Artificial Neural Network

Abstract

Atopic dermatitis is a chronic inflammatory skin disease. It most commonly occurs in children under 5 years. The exact cause of atopic dermatitis has not yet been determined. Today, in order to facilitate the diagnosis, artificial intelligence methods are increasingly used. For the development of the expert system a feedforward Artificial Neural Network is chosen. The network has 9 inputs (age, gender, the presence of asthma, skin pH, filaggrin (FLG), IgE, IL-4, IL-16, IL-31) and 1 output parameter. The performance of the obtained ANN is satisfactory with an accuracy of 94.44% and a sensitivity of 95.62%. This study has been shown to be successful in distinguishing atopic dermatitis from other skin diseases. Therefore, studies of this type with a larger number of respondents, should be developed.