Heart disease has recently caused major concerns over the degradation of people’s living standards. This raises an enormous demand for improvements in cardiac data prediction models wherein machine learning has shown some brilliant results at prediction and decision-making. To test the proposed model, the data scientist applies the heart disease dataset that incorporates more than 3,00,000 records. BMI, smoking habits, asthma, and other features have been enhanced into the dataset for higher performance. The most important features for the dataset will be selected using chi-square test and correlation test. The model mainly focuses on applying statistical analysis. The applied ML algorithms is Decision tree with an accuracy of 93.23%. These upholding results will help in the ongoing endeavor in developing reliable and efficient tools for the early detection and intervention of cardiac disease. In-depth study of more advanced feature selection techniques and hyperparameter optimization methods is guaranteed to boost model performances even further. As a result of today’s sedentary lifestyle due to decline in physical activity such that people spend enormous time in front of their computer screens are putting excess pressure on them, thus increasing the prevalence of risk factors for coronary heart disease and other health problems. Nowadays cardiovascular diseases are getting increasing attention. It is the major cause of death in adult.