Heart disease patients have risen at an alarming rate due to a change in people’s eating habits and lifestyles. Early detection of heart disease in a person significantly reduces the risk of further complications which could have been life-threatening. In the proposed work we have applied various machine learning algorithms such as Random Forest, KNN, CART, etc. on a combined dataset of the Cleveland, Hungary, and Statlog datasets. Experimental results show that the Random Forest delivers the most promising outputs as it yields an accuracy of 93.03 on which when hyperparameter tuning is applied yields an accuracy of 97.7 which is significantly higher than other implementations of Random Forests.