<![CDATA[Heart disease remains one of the leading causes of mortality worldwide, making early detection of its risk crucial to prevent severe complications. This study develops a heart disease risk prediction system using machine learning techniques, including Random Forest, Logistic Regression, and Support Vector Machine (SVM). The dataset is processed through several stages, including numerical feature selection, feature engineering with the addition of a total symptoms variable, and class imbalance handling using class-weight adjustments The model training process involves splitting the data into training and testing sets, followed by evaluation using accuracy, confusion matrix, and classification report metrics. The system also integrates an interactive interface that allows users to select symptoms and risk factors through widget-based checklists, enabling real-time prediction. The results show that the best-performing model achieves high accuracy and effectively identifies the most influential factors based on feature importance analysis. These findings indicate that machine learning provides a reliable and efficient tool to support early risk detection of heart disease.]]>
Copyrights © 2026
