A happy and healthy life is the primary need of the present time. Following the COVID-19 pandemic, around the whole world, cardiovascular diseases (CVDs) are the leading cause of death. Cardiovascular disease affects approximately half a billion people globally and is responsible for one-third death of all deaths globally. Currently, cardiovascular diseases are a major contributing factor to the high mortality rate which is a major concern. Researchers are giving special emphasis on the use of technological resources and/or AI for its prevention. Various machine learning models and/or techniques have been proposed for the prediction and/or diagnosis of cardiovascular disease by researchers. Now the question is how machine learning technology works and how effective is it in predicting and/or detecting CVD. To answer this question, we review methods proposed by researchers to predict and/or cardiovascular disease through machine learning techniques. For the review, we have conducted a literature search of IEEE Xplore, Scopus, SCI, and Elsevier using Google Scholar and PubMed search engines. The primary goal of this paper is to systematically review machine learning models and/or techniques for CVD detection obtained from search engines to be of service to researchers in developing cutting-edge ML models.