Introduction: Metabolic syndrome (MetS) is a complex condition manifested as a group of metabolic disorders and is associated with the prevalence of certain diseases. Early prediction of MetS risk in the middle-aged population can be effective in controlling and preventing cardiovascular diseases. This study aimed to use logistic regression to predict metabolic syndrome and identify risk factors related to this condition. Method: This cohort study investigated factors associated with metabolic syndrome in the Mashhad study, which included a total of 11,570 participants. Factors that increase the relative risk of metabolic syndrome were evaluated using logistic regression, and predictive modeling was performed using logistic regression. Results: The results of the analysis using the logistic regression model showed that some factors, such as body mass index, history of high blood lipids, history of high blood pressure, and diabetes, increased the risk of metabolic syndrome. Various indicators, such as inactivity, high blood urea level, red blood cell hemoglobin content, aging, female gender, high levels of liver gamma-glutamyl transferase, and blood uric acid increase the risk of developing metabolic syndrome. Conclusion: It seems that body mass index, history of diabetes, and heart disease are related to the relative risk of developing the MetS syndrome compared to the other indicators, such as history of blood lipids, sedentary blood pressure, blood urea, uric acid, and hemoglobin content of red blood cells. These findings were obtained using the logistic regression model.