Tanvi, Rustagi and Meenu, Vijarania (2025) CDRPM: Cardiac Disease Risk Prediction Model. International Journal of Science, Mathematics and Technology Learning, 33 (1). pp. 424-440. ISSN 2327-915X

Text fileserve.pdf Download (623kB)

Abstract

The treatment of heart disease, a widespread health problem, requires a rapid and accurate diagnosis. This study improves the diagnosis of heart disease by combining XGBoost with a grey wolf search algorithm (GWSA). Hyperparameters such as regularization, tree depth and learning rate are used by GWSA to optimize the performance of XGBoost classifier. Data pre-processing ensured consistency in the scaling and processed missing data. When combined with XGBoost and GWSA, it improves the accuracy of the cardiac algorithm more than when using traditional parametric tuning methods. Numerous metrics demonstrate the ability of the improved XGBoost model to differentiate between different heart states. The result of the model proposed shows an accuracy of 97.8 percent, which is significantly higher than the traditional ML algorithm. The proposed model has a precision of 97, a recall of 89 and an F1 score of 93. Explanations on the interpretability of the model and the importance of the characteristics for the diagnostic decision are given in the paper. The proposed techniques in clinical practice will improve patient care and health outcomes.

Item Type:	Article
Subjects:	Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Divisions:	Postgraduate > Master's of Islamic Education
Depositing User:	Journal Editor
Date Deposited:	24 Jul 2025 10:22
Last Modified:	24 Jul 2025 10:22
URI:	http://eprints.umsida.ac.id/id/eprint/16296

Actions (login required)

View Item