This project can be divided into 3 modules, which are data analyzation and visualization module, data accuracy assessment module and outcome prediction module.

In data analyzation and visualization module, the heart disease data will be analyzed according to the specific attributes. The attributes include age, gender, chest pain type, blood sugar level, electrocardiographic result, exercise induced angina, slope of peak exercise ST Segment, blood pressure, cholesterol level, number of major vessels colored by fluoroscopy, thallium stress result and age. The analyzed result will be visualized into graphs and charts with the explanation.

In the data assessment module, several algorithms like Logistic Regression and Decision Tree Classifier will be used to evaluate the accuracy score of the dataset. The accuracy score included training accuracy score and testing accuracy score. The accuracy score of each algorithm will be displayed in table and graph form.

In outcome prediction module, a risk prediction equation will be applied in this module to assist the user in heart risk prediction. Users are required to input the values into the specific attributes like age, gender, chest pain type, cholesterol, glucose levels, blood pressure & machine learning model, and the risk of heart disease will be estimated in percentage units. Below 10% can be considered as low risk. 10-15% can be considered as moderate risk, while above 15% can be considered as high risk. If the risk score is in the moderate or high-risk range, the system will show the possible diseases while the low risk range will not.