Over the last century, medical knowledge has expanded rapidly, particularly regarding cardiovascular diseases, which remain the leading cause of death worldwide. Early diagnosis significantly reduces mortality rates for most diseases, making the detection of risk factors a primary challenge in modern medicine. Machine learning techniques offer valuable assistance in diagnosing and identifying factors contributing to diseases. However, various machine learning methods, such as decision trees and association rule mining, have their unique advantages and disadvantages, depending on the specific application. Consequently, it is not evident which method is most effective for detecting cardiovascular disease. This paper compares two machine learning algorithms: decision trees and association rule mining. We identify state-of-the-art algorithms for each technique and preprocess them to facilitate a comparison between supervised and unsupervised methods. The results indicate that both techniques yield outcomes consistent with existing medical knowledge. Notably, association rule mining generates a greater number of rules for heart disease, encompassing more features, while decision trees typically produce concise rules highlighting only the most critical features.