Аңдатпа
This study presents an innovative approach to predicting the risk of cardiovascular diseases (CVD) based on a comprehensive analysis of clinical, immunological and biochemical markers using mathematical modeling and machine learning methods. The initial data include indicators of humoral and cellular immunity (CD59, CD16, IL-10, CD14, CD19, CD8, CD4, etc.), cytokines and markers of cardiovascular diseases, cytokines and inflammation markers (TNF, GM-CSF, CRP), growth and angiogenesis factors (VEGF, PGF), proteins involved in apoptosis and cytotoxicity (perforin, CD95), as well as indicators of liver function, kidney function, oxidative stress and heart failure (albumin, cystatin C, N-terminal pro-B-type natriuretic peptide (NT-proBNP), superoxide dismutase (SOD), C-reactive protein (CRP), cholinesterase (ChE), cholesterol and glomerular filtration rate (GFR)). Clinical and behavioral risk factors are also taken into account: arterial hypertension (AH), previous myocardial infarction (PMI), coronary artery bypass grafting (CABG) and/or stenting, coronary heart disease (CHD), atrial fibrillation (AF), atrioventricular block (AV block), diabetes mellitus (DM), as well as lifestyle (smoking, alcohol consumption, physical activity level), education, body mass index (BMI). The study included 52 patients aged 65 years and older. Based on the obtained clinical, biochemical and immunological data, a model for predicting the risk of premature cardiovascular aging was developed using mathematical modeling and machine learning methods. The aim of the study was to develop a prognostic model that allows for early detection of a predisposition to the development of CVD and its complications. To solve the forecasting problem, numerical methods of mathematical modeling were used, including the Runge-Kutta, Adams-Bashforth and backward Euler methods, which made it possible to describe the dynamics of changes in biomarkers and patients' condition over time with high accuracy. The greatest association with aging processes was demonstrated by HLA-DR (50%), CD14 (41%) and CD16 (38%). BMI correlated with placental growth factor (37%). Glomerular filtration rate positively correlated with physical activity (47%), while SOD activity negatively correlated with it (48%), which reflects a decrease in antioxidant protection. The obtained results make it possible to increase the accuracy of cardiovascular risk forecasting and to formulate personalized recommendations for the prevention and correction of its development.