Coronary Heart Disease (CHD) is one of the leading causes of death worldwide. Early prediction of CHD risk plays a vital role in preventing severe health complications. This paper presents a method for predicting the ten-year risk of coronary heart disease using data analysis and machine learning techniques. Healthcare datasets containing patient information such as age, cholesterol level, blood pressure, smoking habits, and diabetes are used. Various machine learning models like Logistic Regression, Decision Tree, and Random Forest are applied to predict the risk. The results show that machine learning techniques can provide accurate and efficient predictions, helping healthcare professionals in early diagnosis and treatment planning.