Cardiovascular disease (CVD) is a significant global health issue, claiming millions of lives annually. Early diagnosis is essential for lowering mortality rates and improving patient outcomes through prompt treatment. The condition often manifests with symptoms such as chest pain, difficulty breathing, and irregular heartbeats, frequently linked to risk factors like hypertension, high cholesterol, and unhealthy lifestyle choices. This research proposes a machine learning framework to predict cardiovascular disease by analyzing diverse patient data, including metrics such as blood pressure, cholesterol levels, and lifestyle habits. The primary predictive model is a Support Vector Machine (SVM), complemented by a Logistic Regression algorithm for comparative evaluation.