Framework for Designing a Disease Information System using Soft Computing Technique

Abstract

Disease Information Systems (DIS) have become critical tools in modern healthcare, facilitating accurate disease diagnosis, treatment, and management. This paper explores the use of soft computing techniques, specifically artificial neural networks (ANNs) and genetic algorithms (GAs), in the development of DIS. We propose a hybrid system that leverages the feature selection capabilities of GAs and the pattern recognition abilities of ANNs. The hybrid system was tested using four distinct datasets of Diabetes. The performance of the proposed system was compared with nine state-of-the-art swarm intelligence algorithms, including Ant Colony Optimization (ACO), Particle Swarm Optimization (PSO), and Grey Wolf Optimization (GWO). The results demonstrate that the hybrid GA-NN system outperforms these algorithms in terms of accuracy, sensitivity, and specificity. The proposed system achieved maximum average accuracies on the datasets, illustrating its potential for effective disease diagnosis and management.