In Aim of the study was to check the most effective and precise data mining method for predicting cardiac patient mortality. Heart disease rates are rising, and misdiagnosis of the condition can have significant consequences. The high mortality rate seen throughout the world is a result of these mistakes. The healthcare department has a tone of data, yet there is little understanding of the data. For the correct diagnosis of heart illness, medical experts need a lot of experience, a battery of tests, and a lot of time, which is vital in the case of heart disease. As a result, data mining techniques are currently frequently employed for the most accurate Mortality Prediction. These methods expose sickness and important information that is buried patterns. Many lives can be spared and even the life expectancy of many heart patients can be extended if cardiac disorders are detected early. Age, sex, high blood pressure, excessive cholesterol, and irregular pulse rate are only a few of the many variables that influence the development of the condition. 470 patients’ secondary data were used, and 56 distinct qualities were chosen. Then, K-Nearest Neighbor, Decision Tree, Support Vector Machine, and Logistic Regression were employed as the four primary data mining approaches. Results were then generated using the R language, which was utilized to code these procedures. The Decision Tree approach had the highest accuracy rate and was thus the most effective.