One of the paramount causes of death in humans with death toll increasing with each passing year is heart disease. With early and correct diagnosis, the treatment and preventive measures can be accurately taken and to a large extent, people can get free from living the nightmare of living with heart failure and an impending death. This work explores the possibility of using machine learning algorithms towards building a model which is capable of analysing and predicting what are the chances of heart disease in patients based on their medical history and a few attributes related to their health. Techniques of Machine Learning like KNN, Logistic regression, decision trees, support vector machines, and a few more are explored for building a robust model capable of fairly accurately the possibility of an existing or impending heart disease in a patient. Along with that, the ensembling method with Adaboost is used with the aim of improving the overall performance of our model by selecting two of the best-performing algorithms from their comparative analysis. As per the comparative analysis, Random Forest had the best performance while stacking and Adaboost of Random Forest with Logistic Regression had the best performance for ensembling with 90% accuracy and 90% f1-score.