We are using Machine learning technique to determine the chances for getting heart disease with features like age, bp and so forth.
The author didn't obtain data from other sources to enrich the initial dataset due to author is focusing on using the initial dataset only. It causes the finalised dataset in this project only contains of 310 rows of data which may result in overfitting of the model. One can input dataset from other sources to increase the diversity of the dataset to avoid the problem.