Medical Optimal Decision Making under Uncertainty without Assuming Independence of Symptoms

Efficiency and accuracy are imperative aspects in the world of medical diagnosis, for this reason, we have developed a medical diagnosis system based onholonic multi agent system. Holonic multi agent medical diagnosis system combines the advantages of the holonic paradigm, multi agent system technology, and swarm intelligence in order to realize a highly reliable, adaptive, scalable, flexible, and robust Internet- based diagnosis system for diseases. This paper also handles an important assumption inBaye´s theorem. Clustering and discriminating provide method for solving dependence in symptoms problem. It builds on degree of dependency between symptoms with consequence of raising the efficiency and accuracy of the diagnosis. The idea is to transform raw symptoms of each disease into independent groups. Furthermore, decision making under uncertainty is the aim of our system that is able to achieve optimal medical diagnosis together with swarm technique and holonic paradigm without assuming independence of symptoms; whereas, independence of symptoms is the central and critical assumption in Bayes´ theorem. Additional factors that play an important role are the required time for the decision process and the reduced costs.