Cardio-Vascular Risk Detection System using different Machine Learning Techniques

Cardiovascular disease is a prominent cause of disability and early death worldwide; it significantly contributes to growing healthcare costs. Atherosclerosis is the underlying pathology, which develops over time and is usually advanced by the time symptoms appear, usually in middle life. Acute coronary and cerebrovascular crises occur suddenly, and patients might die before medical treatment arrives. Modifying risk factors have been shown to reduce mortality and morbidity in people with known or undiagnosed cardiovascular disease. Classification methods are used frequently in Medical Sciences. One of the major problems faced in Medical Science is Cardiovascular Risk Detection. Classification has been used intensively to group patients into Risky and Non-Risky. The current methodology performs extensive experimentation over specific models and achieves a recognition accuracy of 98% through Decision Tree Classifier. The comparison of accuracies was made for different predictions recorded through various algorithms. The research aims to provide a patient-level risk detection system so patients can know the risk beforehand and follow their prescribed prevention routines.