Research Article
Feature Selection Using Data Mining Techniques for Prognostication of Cardiovascular Diseases
@INPROCEEDINGS{10.1007/978-3-031-50571-3_24, author={Naga Venkata Jashwanth Vanami and Lohitha Rani Chintalapati and Yagnesh Challagundla and Sachi Nandan Mohanty}, title={Feature Selection Using Data Mining Techniques for Prognostication of Cardiovascular Diseases}, proceedings={Multimedia Technology and Enhanced Learning. 5th EAI International Conference, ICMTEL 2023, Leicester, UK, April 28-29, 2023, Proceedings, Part I}, proceedings_a={ICMTEL}, year={2024}, month={2}, keywords={Cardiovascular disease Feature Selection Random Forest Machine learning}, doi={10.1007/978-3-031-50571-3_24} }- Naga Venkata Jashwanth Vanami
Lohitha Rani Chintalapati
Yagnesh Challagundla
Sachi Nandan Mohanty
Year: 2024
Feature Selection Using Data Mining Techniques for Prognostication of Cardiovascular Diseases
ICMTEL
Springer
DOI: 10.1007/978-3-031-50571-3_24
Abstract
Cardiovascular diseases (CVD) are a major cause of mortality world-wide causing about 17.9 million deaths per year. Cardiovascular illnesses are a group of conditions that affect the heart and blood arteries. These illnesses may have an effect on various parts of the heart and/or blood vessels. CVD encompasses coronary artery disorders (CAD), such as myocardial infarction and angina. To reduce the risk and deaths caused by cardiovascular diseases it is important to predict it at an early stage. It is crucial to be aware of these cardiac disease-related signs in order to forecast outcomes and offer a solid foundation for diagnosis for which data mining and feature selection prove to be useful. However, manual analysis and prediction are laborious and tiring due to the sheer volume of data. In this study, data science is used to predict cardiac problems. The potential method for heart disease prediction is one that analyses the relationships between variables and extracts hidden knowledge from the data. Through a variety of indications, our study attempts to anticipate cardiac disease correctly and promptly. We propose a cardiovascular disease prediction model which uses a dataset obtained from Kaggle on which we perform various data pre-processing techniques on which feature selection is done and the refined data is given to different machine learning models for the prediction of the disease. We obtained the highest accuracy of 99.4% using Random Forest, demonstrating the effectiveness and dependability of the heart disease prediction approach we presented.
