Heart disease has emerged as most primary cause of death across the globe, and it is now considered to be the illness that poses the greatest risk to one’s life. The ability to diagnose the cardiac disease at an earlier stage will be beneficial in lowering the overall death rate. This study uses various machine learning (ML)-based algorithms, such as naive Bayes, logistic regression, K-nearest neighbor (KNN), support vector machine, extreme gradient boost, random forest, and others, for predicting heart disease. The motive of this ML algorithm is to estimate the person developing heart disease based on factors (such as blood pressure, cholesterol, sex, age, and so on) that were extracted from the datasets. During our investigation, two distinct datasets were used, in which the support vector machine (SVM) yielded the best accuracy for very first dataset, which was 82%. The random forest algorithm provided the best level of accuracy for the second dataset, which came in at 88.12%. Then, we took both datasets that we utilized in our research and integrated them. Using AdaBoost we were able to achieve the best accuracy possible, which was 90.32%.