Expert Fuzzy System Determining Dengue, Zika, Chikungunya and Yellow Fever Infection

Abstract

This article presents a fuzzy system for determining the level of infection of four viral diseases: dengue, zika, chikungunya, and yellow fever. Medical diagnosis is a complicated task because it is full of uncertainty and imprecision, which many times causes a misdiagnosis. However, this problem can be treated through a fuzzy system with the ability to work with uncertainty by providing the opportunity to model conditions that are imprecisely defined. Dengue, yellow fever, zika, and chikungunya are diseases that in their early stages are difficult to distinguish since they have great similarities in their symptoms, making diagnosis even more difficult. Based on research, the six most relevant symptoms that allow a better diagnosis have been selected. The six input fields are pain, temperature, bleeding, poor appetite, muscle weakness, and shortness of breath. The four output fields refer to diseases and each one is made up of several fuzzy sets that make it possible to identify the level of infection in each disease. The fuzzy system implementation has been done in MATLAB, using fuzzy rules developed with the help of a human expert. The system is not a substitute for expert medical practitioners, but rather an aid in the diagnosis, which is based on the symptoms experienced by the patient. The tests were carried out in 15 cases with viral diseases and the results show that the diagnosis using the fuzzy system has an accuracy of 86.6%, displaying its helpfulness in the early diagnosis of the disease.