Machine Learning and Feature Selection-Enabled Optimized Technique for Heart Disease Classification and Prediction

• Published in: Computer assisted methods in engineering and science Vol. 31; no. 4
• Main Authors: P. Nancy, Prasad Raghunath Mutkule, Kalpana Sunil Thakre, Ajay S. Ladkat, S.B.G. Tilak Babu, Sunil L. Bangare, Mohd Naved
• Format: Journal Article
• Language: English
• Published: Institute of Fundamental Technological Research Polish Academy of Sciences 01.08.2024
• Subjects: accuracy; CFS feature selection; heart disease prediction; machine learning; SVM RBF
• ISSN: 2299-3649; 2956-5839
• DOI: 10.24423/cames.2024.602

When dealing with a group of patients seeking treatment for heart-related diseases, doctors who specialize in the diagnosis and treatment of heart-related disorders have a difficult but critical task. It comes as no surprise that cardiovascular disease is a leading source of morbidity and death in contemporary society. An expert system with clear categorization that may assist medical professionals in identifying heart disease condition based on the clinical data of a patient is often required by physicians. The aim of this work is to provide a method for the prediction and classification of cardiac disease based on machine learning and feature selection. The correlation-based feature selection (CFS) method is applied to the input data set in order to extract relevant features for analysis. The support vector machine with radial basis function (SVM RBF) and random forest algorithms are used here for data classification. Cleveland heart disease dataset is used in the experiment work. This dataset has 303 instances and 14 attributes. The accuracy, specificity and sensitivity of SVM RBF are higher than those of the random forest algorithm.