CARDIORISK_ME: A MACHINE LEARNING-BASED PREDICTIVE ANALYTICS FOR HEART DISEASE
Journal of Information System and Technology Management · 30.09.2026 · 11 (44) · 975
DOI: 10.35631/jistm.1144057 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Information System and Technology Management, online erschienen am 30.09.2026. Verfasst von Daniyal Rosli und 3 weiteren Autor:innen. Die Arbeit nennt 30 Literaturangaben.
Abstract (Originalsprache)
Heart disease remains one of the leading causes of death worldwide. Therefore, timely detection is essential to help improve patients' health. While machine learning and artificial intelligence have advanced significantly, implementation and development challenges remain. This study addresses these issues by providing a machine learning-based heart disease prediction model and presenting the results through an accessible, user-friendly web interface. In addition, this research analyzes and assesses clinical and physiological parameters relevant to heart disease risk prediction and develops a prediction system using Logistic Regression, Decision Tree, and Random Forest classifiers. This work supports efforts to increase awareness and control of heart disease, which continues to affect public health globally. In this study, a cardiac risk prediction system (CardioRisk_Me) was developed using a machine learning approach based on clinical and physiological attributes. The dataset is represented by 304 patient records from open-access repositories. The pre-processed data includes scaled features, encoded variables, cleaned extractions, and a training-testing split. Three machine learning algorithms were tested: Logistic Regression, Decision Tree, and Random Forest, using test-based measures of Accuracy, Precision, Recall, F1-Score, and ROC-AUC. Logistic Regression achieved the highest accuracy (86.27%) and the closest to perfect precision, Recall, F1-score, and ROC-AUC (90.00%, 87.10%, 88.52%, and 89.19%, respectively). The chosen model was incorporated into a web-based prototype built with Next.js and Django, creating a real time heart disease risk prediction system. Overall, the results illustrate the promise of machine learning in supporting risk assessment and preventive healthcare.
Zitieren
APA
Rosli, D., Idrus, Z., Ahmarofi, A. A., & Mahadzir, N. H. (2026). CARDIORISK_ME: A MACHINE LEARNING-BASED PREDICTIVE ANALYTICS FOR HEART DISEASE. Journal of Information System and Technology Management, 11(44), 975. https://doi.org/10.35631/jistm.1144057
Vancouver
Rosli D, Idrus Z, Ahmarofi AA, Mahadzir NH. CARDIORISK_ME: A MACHINE LEARNING-BASED PREDICTIVE ANALYTICS FOR HEART DISEASE. Journal of Information System and Technology Management. 2026;11(44):975. doi:10.35631/jistm.1144057
BibTeX
@article{Rosli2026,
author = {Rosli, Daniyal and Idrus, Zanariah and Ahmarofi, Ahmad Afif and Mahadzir, Nurul Husna},
title = {CARDIORISK_ME: A MACHINE LEARNING-BASED PREDICTIVE ANALYTICS FOR HEART DISEASE},
journal = {Journal of Information System and Technology Management},
year = {2026},
volume = {11},
number = {44},
pages = {975},
doi = {10.35631/jistm.1144057}
}
EUVIMED