Research on Comparative Analysis of Classification Algorithms for Heart Disease

Research on Comparative Analysis of Classification Algorithms for Heart Disease

Prof. Poonam Pathekar (Professor), Yash Surana(Student), Prajit Thube(Student),

Shraddha Solapure(Student), Ruchika Jadhav(Student)

Poonamjaikar@gmail.com, yash.surana.zeal@gmail.com, prajitthube@gmail.com, shraddhasolapure@gmail.com,  ruchikajadhav2432002@gmail.com

Computer Department Zeal Collage of Engineering and Research, Pune, Maharashtra, India

Abstract : Heart disease, also referred to as cardiovascular disease, is the leading cause of death globally over the past few decades. It includes a variety of disorders that have an impact on the heart. Numerous risk factors for heart disease are linked to the requirement for timely access to accurate, trustworthy, and practical methods for early diagnosis and disease management. Data mining is a popular method for processing vast amounts of data in the healthcare industry. In order to forecast cardiac disease, researchers evaluate vast amounts of complex medical data using a variety of data mining and machine learning approaches. This study proposes a model based on supervised learning methods such as decision trees, and numerous heart disease-related variables. K is for closest neighbour, The random forest algorithm and the support vector machine. It makes use of the current dataset from the UCI heart disease patient repository's Cleveland database. There are 303 instances and 76 attributes in the collection. Only 14 of these 76 attributes—which are crucial to demonstrating the effectiveness of various algorithms—are tested. The purpose of this study work is to estimate the likelihood that patients will develop heart disease.

Keywords: Heart disease, SVM; Decision Tree; Random Forest;, Data Mining, KNN