Cardiovascular diseases are a leading cause of mortality globally, with highest death rates. It can be detected and preemptively addressed by identifying clinical factors through the application of Machine Learning (ML) models. This paper employed a variety of machine learning algorithms, like Naïve Bayes (NB), Support Vector Machine (SVM), Random Forest (RF), Logistic Regression (LR), and Extreme Grading Boosting (XGB). Then, the analysis was conducted using the Cleveland UCI dataset which has 303 observations. Then, different metrics of each model were looked at, such as Area Under the Curve (AUC), F1-Score, Accuracy, Precision, Recall were analyzed and determined. The comprehensive comparative analysis was conducted effectively. Although the other algorithms have demonstrated lower levels of accuracy, the result demonstrated that Logistic Regression has an extremely high level of accuracy, which is 72.70%.The results demonstrate that machine learning has great promise as a tool to aid in the decision-making and personalized treatment of patients at risk of cardiovascular disease by healthcare providers.