Heart disease stands out as a prevalent health concern, remaining a leading cause of mortality globally, underscoring the need for effective predictive models to identify at-risk individuals. Encompassing various cardiac conditions, heart disease manifests in diverse forms, including those influenced by genetic factors. Nonetheless, proactive measures can help mitigate its onset and associated complications. Early detection is essential to controlling the effects of heart disease, prompting exploration into data mining techniques for enhanced risk assessment and timely intervention. This study employs six data mining algorithms—Support Vector Classification (SVC), XGBoost (XGB), Decision Trees, Random Forests, Naïve Bayes, and Logistic Regression to predict heart diseases. The show of these algorithms is evaluated based on accuracy metrics. The primary objective is to compare and ascertain which algorithm achieves the highest accuracy in classifying individuals as either normal or abnormal. Comparative analysis reveals that the Decision Tree algorithm outperforms others, exhibiting a precision of 93.75% in heart disease prediction.