Abstract
As a result of a review of articles devoted to predicting these ailments, shortcomings in the diagnosis of an early stage were identified. Health care workers diagnose coronary heart disease relying on the values of the electrocardiogram, blood test and others, but the human factor cannot be noted, and as practice shows, there is a huge risk of incorrect diagnosis of patients at an early stage. According to the World Health Organization, “Coronary disease” (CVD) is the leading cause of death worldwide - more people die from CVD every year than from any other disease. There are a huge number of decision-making methods for early diagnosis of coronary heart disease (CHD), including machine learning technologies. This article is devoted to the study of the work of neural networks using correlation analysis of signs to predict the risk of developing coronary heart disease.