Heart Health Forecasting with Machine Learning Techniques

This research study explores the field of machine learning-based heart health forecasting. Through the integration of datasets sourced from the UCI Machine Learning Repository and Kaggle, we amalgamated a comprehensive dataset comprising 14 columns and 1025 observations. Employing a meticulous preprocessing regimen, we ensured data integrity by eliminating null values, conducting one-hot encoding for categorical variables, and normalizing the dataset. Seven well-known machine learning models were assessed in this study. Strict evaluation metrics were used on these models, including precision, sensitivity, specificity, and accuracy. Our research clarifies the subtleties of each model's performance and offers insights into its suitability and effectiveness for heart health forecasting.