Heart disease has a serious impact on morbidity and impermanence worldwide. In recent years, a number of prediction models have been created to help identify those who have more risk of developing heart disease. While these models have shown promising results in predicting the risk of heart disease, there are still problems that need to be fixed in order to improve their accuracy and usefulness in clinical practice. The goal of this review paper is to evaluate the heart disease prediction models currently in use based on accuracy and to pinpoint their limitations, problems, and potential growth areas. It was found that ANN outperformed other models in terms of predicting the risk of heart disease. Artificial General Intelligence (AGI) also possesses a vital role in heart disease prediction models due to its technology intelligence. The imbalance, small dataset, and generalizability of the prediction model were the limitations.