Proposed Method for Predicting COVID-19 Severity in Chronic Kidney Disease Patients Based on Ant Colony Algorithm and CHAID

Background and Objective: The COVID-19 pandemic is a phenomenon that has infected and killed many people worldwide. Underlying diseases such as diabetes mellitus, heart failure, and chronic kidney disease (CKD) can affect the severity of COVID-19 and aggravate patients' condition. This study aimed to predict the severity of the COVID-19 disease in CKD patients by combining feature selection and classification methods. Materials and Methods: This study was conducted between March 2021 and September 2021 in Isfahan University of Medical Sciences. The data set includes 83 traits of 72 kidney transplant patients, 231 kidney failure patients, and 105 dialysis patients. The data set has 77 input attributes, including age, sex, diabetes mellitus, hypertension, ischemic heart disease, chronic lung disease, and kidney transplant. In the proposed method, the combination of ant colony algorithm and the CHAID method has been used. Results: The combination of the ant colony algorithm and CHAID method leads to better performance than CHAID alone. A total of 22 rules were extracted, of which 6 rules with a confidence of more than 60% were introduced as selected rules. The most reliable rule states that if a person has CKD stage 5, is not undergoing dialysis (5ND), and is short of breath, in 81% of cases the type of COVID-19 disease will be severe. Conclusion: In this study the severity of COVID-19 disease in kidney patients was measured using variables including age, diabetes mellitus, blood pressure, CKD stage, etc. The results showed that high levels of kidney disease can lead to severe COVID-19.