Machine Learning-based Analysis, Diagnosis and Prediction of Cardiovascular Diseases

Abstract

cardiovascular diseases encompass a variety of conditions that impact the heart and blood vessels, presenting significant global health challenges. The condition of CVD patient’s diagnosis, detection, prediction and analysis are difficult tasks. In the dataset, the CVD medical attributes base creates a machine learning (ML) classifier (algorithms) model, which mainly targets patients who are more likely to have or not have a heart disease. Supervised ML models are given by decision trees, random forests, neural networks, k-nearest neighbors, support vector machines and logistic regression, which help in creating a model frame and plotting the dataset CVDs for processing and performance analysis of heart patients. Effected factors, such as coronary artery disease, stroke and heart failure, are among the primary causes of illness and death worldwide. This model is a useful approach to improve the accuracy rate of prediction of the condition of the patient. These ML model, which are very comfortable, cheaper and advanced technology in the medical sector, help in detecting the accurate condition of heart failure patients for diagnosis and predicting the current situation of the patient and the accuracy rate of classifier performance is 75.41% up to 90.16%