Data-Driven Heart Disease Risk Prediction with Machine Learning on Healthcare Datasets

The Centers for Disease Control and Prevention (CDC) reports that heart disease remains a leading cause of death among people of all races. Identifying cardiovascular disease early on can help high-risk individuals make informed lifestyle choices, leading to reduced complications and improved health outcomes. To achieve this goal, this research utilizes data mining and analytics techniques to investigate healthcare datasets. The dataset under study includes 803,916 rows and 279 columns, comprising various health-related factors. The data was divided into training and test datasets, and four different machine learning models were employed, including Decision Tree, Binary Logistic Regression, K-Nearest Neighbors, and Random Forest, to compare their accuracy in predicting heart disease. The Binary Logistic Regression model performed the best with an accuracy score of 91.48%. The study's findings can be beneficial to both public and private sectors in developing preventive measures and interventions to reduce mortality rates.