Machine Learning Model for Heart Disease Prediction

Abstract

In this research paper, as we all know, machine learning is used in various fields including healthcare in this research work. ML plays an important role in determining the presence or absence of various heart conditions that pose a risk, including heart disease, exercise disorders, and other artery-related disorders. Therefore, we performed a comparative analysis on heart disease datasets to understand and explore the application of different algorithms for predicting heart-related conditions. Comprehensive analysis including preprocessing steps for feature selection using correlation matrix and evaluation of several algorithms such as Support Vector Machine (SVM), k Nearest Neighbors (KNN), Logistic Regression, Naive Bayes, Decision Tree to select relevant features. Via Random Forest, XG Boost. The goal is to evaluate the presence or absence of cardiovascular disease using input characteristics in the form of various parameters and evaluate its accuracy. Our results highlight the effectiveness of Random Forest in achieving favorable outcomes with 95% accuracy and provide ideas for improving diagnosis and medical interventions.