COMPARATIVE ANALYSIS OF MACHINE LEARNING ALGORITHMS FOR CARDIOVASCULAR DISEASES PREDICTION SYSTEMS

Every year, around 20.5 million people die from cardiovascular disorders. People who are diagnosed with the disease early can alter their lifestyles and receive appropriate medical care. A model based on learning algorithms Logistic Regression, K-nearest Neighbors, Support Vector Machine, Decision Tree Classifier, Random Forest XGBoost is presented in paper along various heart disease-related attributes. The Cleveland UCI database of patients used model. There 303 instances 76 attributes data set. Only 14 these attributes—whichare crucial to justifying effectiveness algorithms—are taken into account during testing. main contribution this research work implementation an intuitively understandable system forecasts for diagnosis diseases using modern methods machine learning. Algorithms predicting discussed work, a comparison made between existing systems. Six classification were used: neighbors, Classifier Classifier. predict disease, which much better solution than 5 or 10, as was case reviewedpapers. To ensure high accuracy, hyperparameters adjusted each classifier. As result, good performance obtained. In SVM classifier proved be most effective, providing accuracy 87.91 % test It possible achieve greater studied works.