TY - JOUR T1 - Diagnosis of COVID-19 disease by fuzzy expert system designed based on input-output TT - تشخیص بیماری کووید-19 بوسیله سیستم خبره فازی طراحی شده بر اساس ورودی-خروجی JF - joc-isice JO - joc-isice VL - 14 IS - 5 UR - http://joc.kntu.ac.ir/article-1-833-en.html Y1 - 2021 SP - 71 EP - 78 KW - COVID-19 KW - fuzzy expert KW - input-output KW - diagnose. N2 - Accurate prediction and diagnosis of COVID-19 disease is very important for everyone, especially for medical professionals. On the other hand, the use of fuzzy systems in medicine is increasing rapidly. In this study, a fuzzy system was designed using the information of 375 patients suspected of having COVID-19 disease who referred to Imam Khomeini (Tehran), Alborz (Karaj) and Kowsar(Karaj) hospitals. For this purpose, 300 people were considered to extract the rules and 75 people were considered as test data. Information on 12 important parameters of COVID-19 disease including fever, cough, headache, gastrointestinal symptoms, skin rash, sense of smell and taste, underlying disease, chest CT, blood oxygen level, lethargy, age, family history and severity of COVID-19 disease received. The fuzzy expert system was designed with 29 rules after reviewing the rules and removing similar and contradictory rules by using their degree calculation. In this system, by integrating some factors, finally 8 input variables and one output variable were considered that was used by product inference engine, singleton fuzzifier and center average defuzzifier. It was observed that the designed fuzzy expert system provides very good results, so that it detects 93% of Covid-19 disease with high accuracy and also the sensitivity of the system is more than 95% and the specificity of the designed system is more than 87%. M3 10.52547/joc.14.5.71 ER -