Predicting critical health conditions in their early stages can make the difference between life and death, and one such health condition is heart disease. Over the last decade, the main reason for death has been heart disease. Heart Disease is an ailment that affects many lives, is severely life-threatening, and can impair a person's ability to live a conventional life. The delay in treating Heart Disease increases the endangerment of the afflicted person. Consequently, early diagnosis of it can help save countless lives. However, the reasons for Heart Disease are varied, making its prediction very complex. Our objective is to use Machine Learning to enhance the dependability and simplicity of the prediction of Heart Disease. It was concluded that three datasets should be used; two have an immense size, alongside many Machine Learning algorithms. The proposed algorithms were tested: k-Nearest Neighbor, Gradient Boosting, Random Forest, Naïve Bayes, Decision Tree, and Logistic Regression. After rigorous testing, the only algorithm, Logistic Regression, stayed dominant in most of the testing achieving accuracies of 91.6% and 90.8%. Still, on the last dataset, the best algorithm was a random forest which scored the highest accuracy in all the testing, 98.6%. As shown in this paper, Machine Learning is a superb approach to predicting Heart Disease, and results can be further improved with the help of medical professionals and more research.