Over the past few years, heart disease has become one of the leading causes of death worldwide. Lifestyle, nutrition, work culture, etc. are changing all over the world, including developing countries, not developed countries. changes have contributed to this problem. Early detection of heart disease symptoms and ongoing medical care can help reduce the number of patients and ultimately reduce mortality. However, due to the limited number of medical facilities and specialists, it is difficult to provide regular patient care and counselling. Technology is needed to support patient care and treatment. Clinical data from multiple clinical procedures and continuous patient care can be used to develop predictive models for cardiovascular disease. Early diagnosis of heart disease can help inform lifestyle changes to reduce complications in high-risk patients, which may be important in medicine. This article reviews some of the most commonly used machine learning techniques to predict heart disease using clinical and historical data. Various techniques are discussed and compared. This report compares five methods published in the literature for predicting the timing of a heart attack.