Cardiovascular Disease Detection Using Sand Cat Swarm-driven AdaBoost Approach

Authors:
Open Access
Publisher website
Google Scholar
Abstract
Cardiovascular diseases (CVDs) constitute a major cause of death and disability worldwide and represent a major public health problem. Timely intervention and better patient outcomes depend on early identification of CVD. A novel Sand Cat Swarm-driven AdaBoost (SCS-AB) technique is presented for the diagnosis of CVD. The suggested strategy chooses useful features from intricate cardiovascular (CV) datasets by utilizing the shared knowledge of the SCS optimization technique. The SCS method, which addresses feature selection issues in CVD diagnosis, is motivated by the social behaviour of sand cats. It demonstrates a cooperative and self-organizing decision-making process. The AdaBoost incorporates the chosen features, improving its ability to distinguish between patients. The gathered dataset is used in this study's analysis of the suggested SCS-AB approach. The SCS-AB driven CVD prognosis is tested on the Python platform in this study. When contrasted with other standard approaches, the experimental results show that the suggested methodology is beneficial with regard to accuracy, sensitivity and specificity. The method has demonstrated its potential for practical clinical applications as well, offering a useful instrument for rapid CVD identification and risk evaluation.

This publication has 19 references indexed in Scilit: