Abstract

It is imperative to determine heart disease promptly, as it is among the world's top causes of mortality. The field of medical diagnosis could be revolutionised by Machine Learning (ML), which has great potential. The paper supplies a thorough outline of the most current developments in methods for machine learning for the identification of heart disease. Various datasets, feature selection procedures, and classification methods are analyzed, highlighting the benefits and drawbacks of each. Deep learning and ensemble techniques are among the other developing technologies that are discussed together with the topic of integration. This study intends to offer insights into the current landscape of machine learningbased heart disease detection and highlight attainable topics for further research and development by a comprehensive evaluation of the corpus of literature.