Cardiovascular disease remains one of the leading causes of death worldwide, necessitating the development of efficient diagnostic tools. This study presents a machine learning framework for predicting cardiovascular disease based on clinical and demographic data. We employ a comprehensive data preprocessing pipeline that includes handling missing values, normalizing data, and balancing the dataset to ensure robust model performance. Feature extraction and selection techniques are applied to identify the most relevant predictors of cardiovascular risk, optimizing model performance and reducing computational complexity. Eight machine learning algorithms were employed to predict cardiovascular disease outcomes, including logistic regression, decision trees, random forest, support vector machines, k-nearest neighbors, naïve Bayes, XGBoost, and AdaBoost model. Our approach achieved an accuracy of surpassing 98%, demonstrating the potential of ML techniques in aiding early diagnosis and improving patient outcomes. This comparative analysis highlights the strengths and limitations of each algorithm, providing insights into the most suitable models for clinical use.