Artificial Intelligence Simulation of Ant Colony and Decision Tree in Terms Sustainability

Complain AI with disease diagnosis holds huge potential to improve the sustainability of healthcare systems by improving efficiency, optimizing resources, and developing in-person and remote care initiatives. In this research, artificial intelligence simulation of ant colony optimization was used to achieve the advantage of community communication in ants. In addition, the ant colony algorithm (ACO) was compared with the decision tree algorithm (DT), the logistic model, and neural networks. The study was applied to thalassemia, which is one of the diseases widely spread around the world, which causes the breakdown of red blood cells in the body. Therefore, the aim of this research is to classify the incidence of this disease or not, taking into account the effect of some variables on the probability of infection, in order to reduce deaths due to this disease and achieve one of the goals of sustainable development, which is reaching the standard of good health. The research results indicate that the ant colony artificial intelligence algorithm is superior in classification operations compared to classical methods such as logistic regression and neural networks. The decision tree also concluded that the genetic factor had the greatest influence on the probability of contracting the disease among the rest of the factors included in the study, which were gender, blood type, genetic factor, and place of residence.