Abstract. Premature pathological aging is often associated with cardiovascular diseases, which result from a combination of socio-economic, metabolic, behavioral, and environmental risk factors. These factors include gender differences, age, high blood pressure, obesity, low physical activity, smoking, excessive alcohol consumption, elevated cholesterol and glucose levels, and diabetes. All processes in the human body are reflected in biochemical and immunological analyses, which can serve as markers of premature aging of the cardiovascular system. The authors studied the relationships between social factors such as education, employment, gender, marital status, disability, physical activity, smoking, and alcohol consumption, and clinical indicators such as ischemic heart disease (IHD), post-infarction cardiosclerosis (PICS), chronic heart failure (CHF), diabetes mellitus (DM), body mass index (BMI), glucose level, total cholesterol (TC), and blood pressure (BP). Additionally, correlations were identified between the clinical data (biomarkers) and the social life of patients aged 65–74 years, 75–89 years, and over 90 years.

Keywords: artificial intelligence, machine learning, premature aging markers, cardiovascular diseases, immune aging, forecasting.