PENGEMBANGAN MODEL PREDIKTIF RISIKO PENYAKIT JANTUNG MENGGUNAKAN ALGORITMA XGBOOST DENGAN OPTIMASI HYPERPARAMETER

  • Hery Oktafiandi Universitas Satu
  • Winarnie Winarnie Universitas Satu
  • Pebriyanti Panjaitan Universitas Satu
  • M.Fajar Ramadhan Universitas Satu
  • Yohanes Yohanes Universitas Satu
  • M. Denny Ricardo Universitas Satu

Abstract

Heart disease remains one of the leading causes of mortality worldwide, posing a major challenge to global healthcare. Early detection of heart disease risk is crucial for improving prevention efficacy and patient management. This study aimed to develop a heart disease risk prediction model using the Extreme Gradient Boosting (XGBoost) algorithm optimized with GridSearchCV-based hyperparameter tuning. The dataset was sourced from the Heart Disease Dataset, comprising 1,025 patient records and 14 medical attributes reflecting physiological conditions. The experimental method involved exploratory data analysis, data cleaning, train-test splitting (80:20), data standardization, hyperparameter tuning, and model evaluation using a confusion matrix. The results demonstrated that the optimized hyperparameter configuration achieved a high classification performance, yielding an accuracy of 98.54%, precision of 100%, recall of 97.09%, and an F1-score of 98.52%. Based on the feature importance analysis, thalach (maximum heart rate achieved), cp (chest pain type), and ca (number of major vessels) were identified as the three most influential clinical factors driving the model's predictions. These findings prove that the optimized XGBoost algorithm holds significant potential as a clinical decision support tool to assist in the early screening of heart disease risk consistently and accurately.

References

P. Rani, R. Kumar, N. M. O. S. Ahmed, and A. Jain, “A decision support system for heart disease prediction based upon machine learning,” J. Reliab. Intell. Environ., vol. 7, no. 3, pp. 263–275, 2021, doi: 10.1007/s40860-021-00133-6.

S. K. Kiangala and Z. Wang, “An effective adaptive customization framework for small manufacturing plants using extreme gradient boosting-XGBoost and random forest ensemble learning algorithms in an Industry 4.0 environment[Formula presented],” Mach. Learn. with Appl., vol. 4, no. December 2020, p. 100024, 2021, doi: 10.1016/j.mlwa.2021.100024.

S. A. Naghibi, H. Hashemi, R. Berndtsson, and S. Lee, “Application of extreme gradient boosting and parallel random forest algorithms for assessing groundwater spring potential using DEM-derived factors,” J. Hydrol., vol. 589, p. 125197, 2020, doi: 10.1016/j.jhydrol.2020.125197.

P. H. V. Sesha Talpa Sai et al., “Cardiovascular Disease Prediction Using Machine Learning,” Lect. Notes Networks Syst., vol. 1107 LNNS, pp. 443–453, 2024, doi: 10.1007/978-981-97-6581-2_36.

E. T. Kimchi, M. Nikfarjam, N. J. Gusani, D. M. Avella, and K. F. Staveley-O’Carroll, “Combined pancreaticoduodenectomy and extended right hemicolectomy: Outcomes and indications,” Hpb, vol. 11, no. 7, pp. 559–564, 2009, doi: 10.1111/j.1477-2574.2009.00087.x.

M. Niang, M. Ndong, I. Dioum, I. Diop, M. Mashaly, and M. A. A. El Ghany, “Comparison of Random Forest and Extreme Gradient Boosting Fingerprints to Enhance an indoor Wifi Localization System,” 2021 Int. Mobile, Intelligent, Ubiquitous Comput. Conf. MIUCC 2021, no. 4, pp. 143–148, 2021, doi: 10.1109/MIUCC52538.2021.9447676.

E. Casiraghi et al., “Explainable Machine Learning for Early Assessment of COVID-19 Risk Prediction in Emergency Departments,” IEEE Access, vol. 8, no. December 2019, pp. 196299–196325, 2020, doi: 10.1109/ACCESS.2020.3034032.

K. Yuan, L. Yang, Y. Huang, and Z. Li, “Heart Disease Prediction Algorithm Based on Ensemble Learning,” Proc. - 2020 7th Int. Conf. Dependable Syst. Their Appl. DSA 2020, pp. 293–298, 2020, doi: 10.1109/DSA51864.2020.00052.

A. C. Dimopoulos et al., “Machine learning methodologies versus cardiovascular risk scores, in predicting disease risk,” BMC Med. Res. Methodol., vol. 18, no. 1, pp. 1–11, 2018, doi: 10.1186/s12874-018-0644-1.

M. L. Dobias, M. B. Sugarman, M. C. Mullarkey, and J. L. Schleider, “Predicting Mental Health Treatment Access Among Adolescents With Elevated Depressive Symptoms: Machine Learning Approaches,” Adm. Policy Ment. Heal. Ment. Heal. Serv. Res., vol. 49, no. 1, pp. 88–103, 2022, doi: 10.1007/s10488-021-01146-2.

W. Zhang, C. Wu, H. Zhong, Y. Li, and L. Wang, “Prediction of undrained shear strength using extreme gradient boosting and random forest based on Bayesian optimization,” Geosci. Front., vol. 12, no. 1, pp. 469–477, 2021, doi: 10.1016/j.gsf.2020.03.007.

S. Meacham, G. Isaac, D. Nauck, and B. Virginas, “Towards Explainable AI: Design and Development for Explanation of Machine Learning Predictions for a Patient Readmittance Medical Application,” Adv. Intell. Syst. Comput., vol. 997, pp. 939–955, 2019, doi: 10.1007/978-3-030-22871-2_67.

Published
2026-09-26