Fuzzy Rule-Base Expert System for Evaluation Possibility of Fatal Asthma

Abstract

Asthma, a chronic lung disease, has increasing rate in developing countries. Fatal asthma as a sudden exacerbation of asthma threatens the life of asthmatic patients, even patients with a condition of good-controlled asthma. So prediction the risk of fatal asthma is a great contribution decreasing the possibility of asthma mortality and morbidity. In this paper a fuzzy expert system is developed for prediction of fatal asthma. Fuzzy-rules, modular representation of variables in regard to patients’ perception of the disease, and minimizing the need for laboratory data are the most important features of this system. Main variables of viral infection, Exposure to irritants/allergens, Duration of asthma, Response to treatment, Instability of asthma, Degree of nocturnal symptoms, Intensity of current treatment, Peripheral blood eosinophilia, and Intensity of exacerbation make antecedents of the rules. Output of this system is possibility of fatal asthma determined in the interval (0-10). Evaluating the performance of this system at asthma, allergy, immunology research center of Emam Khomeini hospital reinforces the good efficiency of this fuzzy expert system for prediction of possibility of fatal asthma.