EUVIMEDEUVIMED entdecken
Crossref

Explainable Machine Learning for Heart Attack Risk Prediction Integrating Clinical, Lifestyle, and Socioeconomic Factors

Jepri Banjarnahor, Charles, Niel Artstanta Sinulingga, Gunawansah Tumama Siregar, Muhammad Ikhsan, Jaidup Banjarnahor

Mathematical Modelling of Engineering Problems · 15.05.2026 · 13 (4) · 697-704

DOI: 10.18280/mmep.130407 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Mathematical Modelling of Engineering Problems, online erschienen am 15.05.2026. Verfasst von Jepri Banjarnahor und 5 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Cardiovascular disease remains the leading cause of death globally, underscoring the critical need for risk prediction tools that are both accurate and clinically interpretable.This study developed an explainable machine learning model based on Extreme Gradient Boosting (XGBoost) to predict the risk of heart attack.The model integrates clinical measurements, lifestyle behaviors, and socioeconomic factors as predictive inputs.Rigorous data preprocessing was performed, and class-balancing techniques were applied to address class imbalance within the dataset.The model was trained with early stopping and evaluated using multiple performance metrics.On the validation set, the model achieved a Receiver Operating Characteristic Area Under the Curve (ROC-AUC) of 0.73 and a Precision-Recall Area Under the Curve (PR-AUC) of 0.80.These values reflect moderate discriminative ability with strong sensitivity toward the minority (high-risk) class.On an independent test set, the model achieved an ROC-AUC of 0.79, a recall of 0.84, and a precision of 0.63, demonstrating improved generalization relative to validation performance.These results indicate that the model identified high-risk individuals with a reasonable false-positive rate, supporting its feasibility as a screening tool in clinical practice.To enhance interpretability, feature contributions were quantified using Shapley Additive Explanations (SHAP).The analysis identified systolic blood pressure, smoking status, physical activity, sleep irregularity, and alcohol consumption-among other modifiable lifestyle factors-as the principal determinants of predicted risk.The model further captures the influence of socioeconomic variables, including income level and geographic region, on individual cardiovascular risk profiles.Overall, this study presents a transparent and interpretable predictive framework that balances predictive performance with clinical relevance.The framework supports informed clinical decision-making and targeted preventive interventions for heart attack risk.

Zitieren

APA

Banjarnahor, J., Charles, Sinulingga, N. A., Siregar, G. T., Ikhsan, M., & Banjarnahor, J. (2026). Explainable Machine Learning for Heart Attack Risk Prediction Integrating Clinical, Lifestyle, and Socioeconomic Factors. Mathematical Modelling of Engineering Problems, 13(4), 697-704. https://doi.org/10.18280/mmep.130407

Vancouver

Banjarnahor J, Charles, Sinulingga NA, Siregar GT, Ikhsan M, Banjarnahor J. Explainable Machine Learning for Heart Attack Risk Prediction Integrating Clinical, Lifestyle, and Socioeconomic Factors. Mathematical Modelling of Engineering Problems. 2026;13(4):697-704. doi:10.18280/mmep.130407

BibTeX
@article{Banjarnahor2026,
  author = {Banjarnahor, Jepri and Charles and Sinulingga, Niel Artstanta and Siregar, Gunawansah Tumama and Ikhsan, Muhammad and Banjarnahor, Jaidup},
  title = {Explainable Machine Learning for Heart Attack Risk Prediction Integrating Clinical, Lifestyle, and Socioeconomic Factors},
  journal = {Mathematical Modelling of Engineering Problems},
  year = {2026},
  volume = {13},
  number = {4},
  pages = {697--704},
  doi = {10.18280/mmep.130407}
}
Kostenlos starten →