cart algorithm

Considering that the new corona virus (COVID -19) is still prevalent, one of the important concerns isthe variables affecting the severity of the corona disease in the health of the society. In this study, the CART algorithmwas fitted to predict and determin the status of patients infected with the of COVID-19 in Mashhad University ofMedical Sciences.

This paper is a cross sectional-analytical study. Dataset were obtained from all of peoplereferred for the disease of COVID -19 collected at the Sinai system during the second peak and the fourth peak ofthe disease in Mashhad University of Medical Sciences. Data analysis was performed using JMP statistical softwareversion 13. Then for modeling, data mining methods and CART algorithm are used.

The descriptive findingsof our study showed that 6% of patients with positive PCR suffer from severe disease of COVID-19. The age variablewas very important in the severity of the disease. The age of 60 years old is the cut-off point for the severity ofthe disease, which increases the COVID-19 severe from about 3% under the age of 60 to about 18% over the age of60. The diseases of heart, kidney, respiratory, blood fat, and diabetes were other important variables.

The results of the CART model showed that for the age under 60 years the variables of heart disease, age, diabetes,respiratory disease, fat, gender and kidney, and for the age over 60 years the variables of age, heart disease, kidney,respiratory and diabetes were respectivly the most critical risk factors. According to the ROC curve, the fitted modelhas a good performance for COVID-19 severe disease, so that it increases up to 6 times the prediction of the COVID-19severe disease.

Understanding of the risk factors for cardiovascular artery disease, which is the leading cause of death worldwide, can lead to essential changes in its etiology, prevalence, and treatment. The aim of this study was to compare the results of logistic regression model and Classification and Regression Tree Analysis (CART) in determining the prognostic factors for coronary artery disease in people living in Mashhad, Iran.

The present case-control study used the cohort data of Mashhad stroke and heart atherosclerotic disorder (MASHAD STUDY), 2009. The prognostic factors for coronary artery disease were determined by CART and Logistic regression models using R and Stata 14. Then, the efficiency of the models was compared by computing the area under the performance characteristic curve (AUC). All patients with coronary artery disease were considered as the case and for each case, three controls were selected.

According to Logistic model, prognostic factors for coronary artery disease included age, history of myocardial infarction, diabetes, history of hyperlipidemia, and family history of heart disease (father and brother). The CART algorithm showed age, history of myocardial infarction, history of hypertension, depression, physical activity level, and body mass index as prognostic factors for coronary artery disease in people in Mashhad.

Myocardial infarction and age were common prognostic factors for coronary artery disease according to the models applied. According to the efficiency of logistics model, binary multiple logistic regression model is suggested to be used in identifying the factors affecting coronary artery disease, if there is no interaction between the predictors.