Article Per Year (5 Year)
p-Index From 2021 - 2026
0.23
P-Index
This Author published in this journals
All Journal BAREKENG: Jurnal Ilmu Matematika dan Terapan
Dina Tri Utari
Department of Statistics, Faculty of Mathematics and Natural Sciences, Universitas Islam Indonesia, Indonesia
Computer Science & IT Control & Systems Engineering Economics, Econometrics & Finance Energy Engineering Mathematics Mechanical Engineering Physics Transportation

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
RANDOM FOREST-BASED CARDIOVASCULAR DISEASE PREDICTION WITH SHAP-DRIVEN INTERPRETABILITY Farrel Rafa Akbar; Dina Tri Utari
BAREKENG: Jurnal Ilmu Matematika dan Terapan Vol 20 No 4 (2026): BAREKENG: Journal of Mathematics and Its Application
Publisher : PATTIMURA UNIVERSITY

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30598/barekengvol20iss4pp3547-3558

Abstract

Cardiovascular disease continues to be a significant worldwide health issue, where early detection is essential due to the frequently asymptomatic beginning of heart attacks. This research presents a model for predicting the risk of heart disease utilizing the Random Forest (RF) algorithm, trained on clinical data obtained from Zheen Hospital in Erbil, Iran. The data can be found online through the Mendeley Data website. The Synthetic Minority Oversampling Technique (SMOTE) was used to fix the problem of uneven class sizes, and Shapley Additive Explanations (SHAP) were used to explain how the model made its predictions. The RF model, improved with the best settings and evaluated with the F1-score, achieved impressive results, which are more than 99% for training, validation, and testing data. These results underscore its capacity to discover minority class patterns, crucial for recognizing rare yet significant occurrences. SHAP analysis identified troponin, creatine kinase-MB, and age as the primary predictors. The new idea is not just about individual methods but how they work together for predicting cardiovascular disease, especially by making AI easier to understand and dealing with uneven data using real clinical information. The subsequent study will aim to enhance robustness and generalizability across diverse patient populations.
Co-Authors Farrel Rafa Akbar