Recent healthcare reports indicate clearly an increasing mortality rates worldwide which puts a significant burden on the healthcare sector due to different diseases. Coronary artery diseases (CAD) is one of the main reasons of these uprising death rates since it affects the heart directly. For early diagnosis and treatment of CADs, a swiftly growing technology called data mining (DM) has been used to collect and categorize necessary data from patients; age, blood sugar and pressure, a type of thorax pain, cholesterol, and so on. Therefore, this paper adopted four DM methods; Decision tree (DT), logistic regression (LR), random forest (RF), and Naïve Bayes (NB) to achieve the goal. The paper utilized the Cleveland dataset along with Python programming language to compare among the four DM methods in terms of precision, accuracy, recall, and area under the curve. The results illustrated that NB method has the best accuracy of 89.47% compared with previous studies which will help with accurate, fast and inexpensive diagnosis of CADs.