Heart disease is one of the most challenging tasks in health care. Several works have been proposed to address this challenge. In the recent past, some of the research articles are focused on the design of different machine learning algorithms for heart disease in health care, in this paper, we present an overview of supervised, unsupervised, and reinforcement learning algorithms used in the prediction of heart disease wherever possible. This review paper classifies some machine learning algorithms into different categories named Naïve Bays, Decision trees, support vectors, KNN, random forest, genetic algorithms, and structures with their relative performances. This paper also compares different algorithm techniques for heart diseases against accuracy and reliability.