Cardiovascular diseases (CVDs) remain a leading cause of morbidity and mortality worldwide. This study explores the early detection of acute myocardial infarction (AMI) risk through a comparative analysis of eight machine learning models, including Random Forest, Support Vector Machines, and Gradient Boosting, among others. The methodology incorporates an enhanced data preprocessing framework, which involves outlier detection, a combination of nominal and ordinal encoding techniques, and imputation using both K-Nearest Neighbors (KNN) and Random Forest approaches. Feature selection and hyperparameter tuning were performed using Grid Search to optimize model performance. Our results indicate that the Random Forest model with Random Forest imputation achieved the highest accuracy of 68%, demonstrating its effectiveness in predictive tasks. These findings underscore the potential of machine learning models in enhancing clinical decision-making for cardiovascular risk assessment.