Background. Relevance Progressive atherosclerosis has attracted researchers for the last decade due to the fact that it is associated with unfavorable clinical outcomes. Application of modern methods of mathematical modeling will allow to identify patients with such extreme risk of cardiovascular events and optimize their management. Purpose of the study. To develop a mathematical model of the risk of progressive atherosclerosis using the free cross-platform visual programming system Orange and to compare it with the method of nonlinear regression model of logistic type implemented in C++ programming language. Materials and Methods. Female and male patients diagnosed with coronary heart disease (CHD) were included in the study, 100 of them had signs of progressive course of atherosclerosis, 102 - its spontaneous course. Risk models were built using the free cross-platform visual programming system Orange, SPSS 22.0 package, and C++ console. Results and conclusion. The author's proposed approaches to assess the risk of progressive atherosclerosis using regression analysis and machine learning have good prognostic accuracy; both methods are recommended by the authors for application in practice.