Heart diseases prediction using hybrid ensemble learning

No Thumbnail Available
Authors
Sharma, Sumit
Issue Date
2020
Degree
MSc in Data Analytics
Publisher
Dublin Business School
Rights
Items in eSource are protected by copyright. Previously published items are made available in accordance with the copyright policy of the publisher/copyright holder.
Abstract
Heart disease usually refers to the conditions like narrowed or blocked blood vessels which will result in heart failure, pain due to reduced blood flow to the heart (angina) or stroke. With the rampant increase within the heart stroke rates at juvenile ages, we'd like to place a system in situ to be ready to observe the symptoms of a heart stroke at associate degree early stage and so forestall it. it's impractical for a standard man to oftentimes endure expensive tests just like the graph and so there must be a system in situ that is handy and at an equivalent time reliable, in predicting the possibilities of a cardiovascular diseases. So, we tend to propose to develop associate degree application which may predict the vulnerability of a cardiovascular diseases given basic symptoms like age, sex, pulse etc. The machine learning algorithms or models has evidenced to be the foremost correct and reliable formula and hence employed in the planned system. The predict of heart disease is done in three phases: feature selection process in this process we will automatically or manually select those features which contribute most to your prediction variable or output in which you are interested in. The second phase is applying the machine learning algorithms which are AdaBoost, XGBoost and Stacking in which the data will be trained and tested. The third and the last phase is the User interface in which the user will enter his details and then the machine learning models will predict that the user will have heart diseases in future or not.