Predictive model of macrovascular complications at the time of diagnosis of patients with type 2 diabetes

Introduction: Cardiovascular disease is the main cause of mortality in people with type 2 diabetes mellitus. Objective: Design a predictive model of macrovascular complications in patients with type 2 diabetes at the time of diagnosis. Methods: An observational, of cases and controls, retrospective study was carried out. The population studied were all patients diagnosed with type 2 diabetes mellitus in the "José Martí" health area of the province of Santiago de Cuba, during the period from September 2018 to December 2022. 40 cases with macrovascular complications and 80 controls were studied. randomly selected from the same population, without complications. To build the model, binary logistic regression was applied and those that were associated with macrovascular complications in a previous bivariate analysis were used as independent variables. Results: The variables that were included in the model, after the binary logistic regression analysis, were arterial stiffness, hyperlipidaemia, and arterial hypertension. Hosmer-Lemeshow test= 6.027; p= 0.644. The sensitivity of 77.50 % and specificity of 90.00 %; with a positive predictive value of 79.49 and negative predictive value of 88.89; and validity index equal to 85.83. The observed area under the Receiver Operating Characteristic curve is 0.933, with a significance associated with the calculated statistic of 0.000. Conclusions: The designed model is a good predictor of macrovascular complications in patients with type 2 diabetes at the time of diagnosis.