The goal of the project is to predict whether the patient has a 10-year risk of future coronary heart disease (CHD). This is done by Exploratory Data Analysis, as the data is imabalanced SMOTE technique was used to handle the imbalance in the data after which the data is split into train and test data and Classification machine learning algorithms are applied on the dataset after which the hyper parameter tuning is done to obtain the optimal parameters so that the algorithm can give us the best predictions possible.
An App has been developed in streamlit which takes all the necessary inputs and makes predictions on whether the patient is at the risk of heart disease or not. The inputs are sent for the model so that the model can make predictions.
Link for the app deployed on streamlit cloud