Predicting the long-term outcome of preschool children with asthma symptoms

The long-term solution to the asthma epidemic is thought to be prevention, and not treatment of the established disease. The most cases of asthma begin during the first years of life, thus the early identification of young children at high risk of developing persistent symptoms of the disease throughout childhood is an important public health priority. Artificial Neural Networks have been proposed to improve the performance of physicians in clinical decision-making. In this study, a new computational intelligence technique for the prediction of persistent asthma in children is presented. The presented method is based on Multi-Layer Perceptron neural networks and Probabilistic Neural Networks architectures. Through a feature reduction, 8 prognostic factors correlated to the persistent asthma are utilized. Various network topologies have been investigated in order to obtain the best prediction accuracy. The proposed Artificial Neural Network can be used in asthma outcome prediction with 100% success according to the experimental results.