Machine learning (ML) methods are the main tool of artificial intelligence, the use of which allows you to automate the processing and analysis of large data, on this basis to identify hidden or obscure patterns and gain new knowledge. The review provides an analysis of the scientific literature on the use of MO methods to diagnose and predict the clinical course of coronary heart disease. There is information about the reference database, the use of which allows you to develop templates and validate them. Advantages and disadvantages of individual ML methods (LogisticRegression, RandomForestClassifier, DecisionTreeClassifier, KneighborsClassifier, GradientBoostingClassifier) ​​for the development of diagnostic and predictive algorithms are presented. The most promising methods of MO are in-depth training using multilayer artificial neural networks. It is expected that the development of models based on MO methods and their introduction into clinical practice will help support medical decision-making, increase the effectiveness of treatment and optimize health care costs.