Human Heart Disease Prediction Using Data Mining Techniques

• Published in: 2019 International Conference on Advances in Computing, Communication and Control (ICAC3) pp. 1 - 5
• Main Authors: Mirza, Imran, Mahapatra, Arnav, Rego, Daryl, Mascarenhas, Kenneth
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.12.2019
• Subjects: Accuracy; Classification algorithms; Data mining; Diseases; Heart; Heart Disease; KNN; Linear SVM; Medical diagnosis; Medical diagnostic imaging; Naive Bayes classifiers; Naive Bayes methods; Nearest neighbor methods; Prediction; Prediction algorithms; RBF SVM
• DOI: 10.1109/ICAC347590.2019.9036836

Heart disease is the major cause of death nowadays. Bad lifestyle habits as well as unavoidable hereditary issues are only contributing even more towards this dynamic. There is an abundance of data which resides in the medical databases. Our purpose behind this project is to apply the field of data science and analysis in the medical sector so as to help the doctors and healthcare professionals all over the world by providing them with meaningful insight and predictions that they can rely upon if need be. We intend to achieve our goal by the using machine learning algorithms to perform data mining on medical datasets of patients so as to find patterns in the data in order to make accurate predictions on the presence of heart disease in an individual. We've identified a list of 13 medical attributes such as age, gender, cholesterol level, resting blood pressure etc. which directly influence the likelihood of a person acquiring a heart disease. We propose the use of classifiers such as RBF SVM and Linear SVM along with KNN and Naive Bayes classifiers to classify users into classes which is non-zero for severity of presence and zero for absence of heart disease and also to measure the performance of our classifiers.