Prediction of Cardiovascular Diseases Using Machine Learning: A Study Incorporating Cholesterol, Resting Blood Pressure, Chest Pain Type, Number of major vessels and thalassemia as a Crucial Feature

Abstract

Cardiovascular diseases (CVD) are the leading cause of death in most countries. This paper involves the prediction of CVD using machine learning (ML) techniques along with recognizing Cholesterol, Resting Blood Pressure, Chest Pain Type, Number of major vessels and thalassemia as a crucial feature. A predictive model was developed by fitting Support Vector Machine, K Neighbors, Random Forest, Gradient Boosting, Naive Bayes and Decision Tree Classifier ML algorithms with logistic regression to a dataset. The common stringent methodologies are data preprocessing, feature extraction, and classification. The research suggests that incorporating Cholesterol, Resting Blood Pressure, Chest Pain Type, Number of major vessels and thalassemia with alternative measures of health risk provides a more accurate predictive capacity. The most accurate algorithm for the cardiovascular disease dataset we evaluated was Random Forest, with an 83.52 percent accuracy rate, suggesting possible value as a tool to support clinical decision-making based on our approach. This study highlighted the growing importance of ML in health care, especially for early diagnosis and treatment planning to prevent heart diseases.

Ähnliche Arbeiten