*WINNER* Data Mining for Cardiovascular Disease Prediction

Abstract

Cardiovascular diseases (CVDs) are disorders of the heart and blood vessels and are a major cause of disability and early death worldwide. For example, in the USA, one person dies every 36 seconds due to CVDs. In addition, it affects national income due to the cost of health care services, medicines, and lost productivity due to death. It's important to early notification for the individual at higher risk of developing CVD to prevent early deaths. Most often it's challenging for medical practitioners to predict cardiovascular disease as it requires experience and knowledge. The advances in the field of computational intelligence, together with the massive amount of data produced every day in clinical settings, have made it possible to create recognition systems capable of predicting whether an individual has CVD. Support Vector Machine (SVM), and Convolutional Neural Network (CNN) will be used to train on the Kaggle dataset of CVD cases, which includes 70000 registers of patients and 12 attributes divided into three types (Objective, Examination, and Subjective) considered relevant for identifying the disease. A feature weight is used to select which features are more useful in the training process in order to achieve a better accuracy.