Вackground. In the era of digital transformation in medicine, which is radically changing the way patient information is stored, processed and used, medical professionals need new tools and approaches that can efficiently process and interpret data for fast and accurate decision making. These methods also enable the creation of personalized treatment approaches, taking into account individual patient characteristics and risks. In this article, the authors share their own experience in applying numerical methods in cardiology. Purpose of the study. To develop methods of effective risk assessment of cardiovascular outcomes in different categories of patients. Characteristics of patients and methods of the study. Three variants of outcome prediction were included in the study. The 1st - assessment of the total risk of one-year cardiovascular outcomes after myocardial infarction with ST-segment elevation, the 2nd - assessment of the risk of postinfarction chronic heart failure, the 3rd – assessment of the risk of progressive course of atherosclerosis. Statistical analysis methods included the free cross-platform visual programming system Orange, the SPSS 22.0 package, and the C programming language console. Results and Conclusion. The conducted study has shown that the application of different approaches: regression analysis, machine learning, Excel programming capabilities, C programming language and console interface allows to develop models of cardiovascular outcomes prediction with high accuracy.
Read full abstract