Prophesising of Cardiovascular Disease Using Decision Tree Classification Algorithm

Heart disease prediction is the biggest complication nowadays, completely monitoring is not possible in any patient cases. We have to always keep a track in regular intervals but not daily bases. Data science is critical in the processing of massive amounts of data in the realm of health care. Because the prediction of cardiovascular illness is complicated to analyse, there is a need for automation for the prediction process to prevent risk by keeping watch of patients so that they will be cautious at the proper time. Cardiovascular disease has been the major cause of mortality for many people during the previous decade. Early check-ups and regular diagnostics in equal intervals can help to reduce mortality. However, it is not feasible to correctly monitor patients on a regular basis in all circumstances, and 24/7 consultation is more difficult since it needs more intelligence time and skill. In this thesis, we will develop and research models for cardiovascular disease prediction based on various heart disease characteristics of patients and detect impending heart disease using machine learning techniques such as the decision tree algorithm, backward elimination algorithm, and REFCV on data sets available on the Kaggle website. Early detection of cardiac disease can help patients make decisions about lifestyle modifications and avoid consequences. If this thesis taken into real life, this will be a progressive milestone.