Cardiovascular diseases remain one of the leading causes of mortality worldwide. Early detection of heart disease is essential for reducing health risks and improving patient outcomes. This research proposes a machine learning-based approach for predicting heart disease using synthetic medical data. A dataset containing patient attributes such as age, cholesterol level, and blood pressure was generated using synthetic data generation techniques. The dataset was preprocessed using normalization methods and used to train a classification model. A Random Forest classifier implemented with scikit-learn was used to predict the occurrence of heart disease. Additionally, a Random Forest regression model was developed to estimate the possible time period for disease occurrence. Experimental results demonstrate that ensemble learning methods provide effective prediction performance. The proposed system can support early diagnosis systems and assist healthcare professionals in identifying high-risk patients.
