Cardio–Vascular Disease Prediction Using Machine Learning

The human heart, a vital organ orchestrating the circulation of blood through the intricate network of arteries and veins within the cardiovascular system, stands as a linchpin of overall health. Unfortunately, heart disease continues to claim numerous lives, emphasizing the critical need for effective predictive tools. In this research endeavor, we employ cutting-edge machine learning algorithms—Logistic Regression, Decision Trees, and K-Neighbor Classifier—to predict cardiovascular disease. Our focus extends beyond algorithmic selection, delving into an in-depth comparison of features to optimize predictive accuracy. The testing phase reveals performance metrics, with Logistic Regression achieving 84.62%, Decision Tree at $82.42 \%$, and K-Neighbor Classifier at $83.52 \%$ accuracy. The pursuit of superior accuracy underscores our commitment to advancing the field of cardiovascular disease prediction through nuanced algorithmic analysis and feature comparison.