Globally, cardiovascular diseases (CVDs) constitute the primary cause of morbidity and mortality worldwide. By early diagnosis of those at risk of CVDs, it may lower the number of avoidable fatalities. It has been shown that Machine Learning (ML) is helpful in anticipating cardiac issues. Adoption of a prediction system that can detect cardiac diseases before they deteriorate would offer people worldwide enormous hope and help in decision-making. ML has become a popular technique for generating predictions from enormous real-world datasets. It has been reported that ML classifiers have issues and flaws such as over fitting and external validation on the type of dataset is used. However, the latest ML algorithm i.e. Extreme Gradient Boosting (XGB) and Random Forest (RF) can enhance the performance and assist in exact prediction. As a result, this study compares XGB and RF with other ten prominent classifiers in terms of their capacity to anticipate and improve performance. When compared to competing classifiers, the performance of RF achieves 89.36% accuracy, 86.02% precision, 95.12% sensitivity, 83.03% specificity, 90.34% F1 score, 89.07% ROC, 79.05% Matthews coefficient, and 3.834% log loss. Whereas the performance of XGB achieves 89.36% accuracy, 86.56% precision, 94.30% sensitivity, 83.92% specificity, 90.27% F1 score, 89.11% ROC, 78.93% Matthews coefficient, and 3.834% log loss. Lastly the performance of Extra Tree Classifier achieves 88.93% accuracy, 86.46% precision, 93.44% sensitivity, 83.92% specificity, 89.84% F1 score, 88.71 ROC, 78.02% Matthews coefficient, and 3.987% log loss. With these promising results other datasets of heart disease will be compared in future.