PENGEMBANGAN SISTEM AI HEALTH AGENT UNTUK PREDIKSI PENYAKIT JANTUNG MENGGUNAKAN XGBOOST DAN EXPLAINABLE AI

I Putu Mahendra Putra; Adie Wahyudi Oktavia Gama

doi:10.47353/bj.v6i4.687

Authors

I Putu Mahendra Putra Universitas Pendidikan Nasional
Adie Wahyudi Oktavia Gama Universitas Pendidikan Nasional

DOI:

https://doi.org/10.47353/bj.v6i4.687

Keywords:

Heart Disease Prediction, XGBoost, Explainable Artificial Intelligence (XAI), Particle Swarm Optimization (PSO), Clinical Decision Support System (CDSS)

Abstract

Opaque model decisions remain a practical barrier to the use of machine learning in heart disease screening. This study presents HeartXplain, a web-based AI Health Agent designed as a Clinical Decision Support System for early screening. The system combines XGBoost, Particle Swarm Optimization (PSO), SHAP, LIME, and interpretative narratives generated by a Large Language Model (LLM). The model was trained on 69,105 records represented by 19 clinical and engineered features. PSO optimized a recall-oriented objective, followed by decision-threshold adjustment. At a threshold of 0.4997, the model achieved 71.01% accuracy, 80.08% recall, 67.39% precision, a 73.19% F1-score, 79.29% AUC-ROC, and 78.05% PR-AUC; false negatives decreased from 1,367 to 1,360. SHAP and LIME exposed global and patient-level feature contributions, while the LLM translated those outputs into a more readable narrative. MAPIE reached 95.01% empirical coverage and 83.02% accuracy on singleton sets. Fairlearn indicated minor sex-based differences but wider gaps across age groups. HeartXplain therefore provides a transparent supporting layer for early screening, not a substitute for clinical examination, diagnosis, or professional judgment. External validation on real clinical data remains necessary.

Downloads

Download data is not yet available.

References

“Cardiovascular diseases (CVDs).” Accessed: Aug. 05, 2026. [Online]. Available: https://www.who.int/news-room/fact-sheets/detail/cardiovascular-diseases-(cvds)

[2] Md. E. A. Sourov, Md. S. Hossen, P. Shaha, Md. M. Siddique, Y. Sutradhar, and M. S. Iqbal, “Explainable Machine Learning Framework for Cardiovascular Disease Diagnosis and Prognosis,” in 2026 IEEE International Research Conference on Smart Computing and Systems Engineering (SCSE), Kelaniya, Gampaha, Sri Lanka: IEEE, Mar. 2026, pp. 1–6. doi: 10.1109/SCSE70081.2026.11499913.

[3] S. M. Ganie, P. K. D. Pramanik, and Z. Zhao, “Ensemble learning with explainable AI for improved heart disease prediction based on multiple datasets,” Sci. Rep., vol. 15, no. 1, p. 13912, Apr. 2025, doi: 10.1038/s41598-025-97547-6.

[4] F. Mahmud et al., “HybridTabNet-QC: A Transformer-Based Clinical Feature Fusion Framework for Heart Disease Risk Prediction,” IEEE Open J. Comput. Soc., vol. 7, pp. 1–13, 2026, doi: 10.1109/OJCS.2025.3637308.

[5] N. G. Rezk, S. Alshathri, A. Sayed, E. El-Din Hemdan, and H. El-Behery, “XAI-Augmented Voting Ensemble Models for Heart Disease Prediction: A SHAP and LIME-Based Approach,” Bioengineering, vol. 11, no. 10, p. 1016, Oct. 2024, doi: 10.3390/bioengineering11101016.

[6] A. Adekoya, F. Saeed, W. Ghaban, and S. N. Qasem, “Ensemble learning approach with explainable AI for improved heart disease prediction,” Front. Pharmacol., vol. 16, p. 1654681, Dec. 2025, doi: 10.3389/fphar.2025.1654681.

[7] the Precise4Q consortium, J. Amann, A. Blasimme, E. Vayena, D. Frey, and V. I. Madai, “Explainability for artificial intelligence in healthcare: a multidisciplinary perspective,” BMC Med. Inform. Decis. Mak., vol. 20, no. 1, p. 310, Dec. 2020, doi: 10.1186/s12911-020-01332-6.

[8] H. W. Loh, C. P. Ooi, S. Seoni, P. D. Barua, F. Molinari, and U. R. Acharya, “Application of explainable artificial intelligence for healthcare: A systematic review of the last decade (2011–2022),” Comput. Methods Programs Biomed., vol. 226, p. 107161, Nov. 2022, doi: 10.1016/j.cmpb.2022.107161.

[9] A. F. Markus, J. A. Kors, and P. R. Rijnbeek, “The role of explainability in creating trustworthy artificial intelligence for health care: A comprehensive survey of the terminology, design choices, and evaluation strategies,” J. Biomed. Inform., vol. 113, p. 103655, Jan. 2021, doi: 10.1016/j.jbi.2020.103655.

[10] M. Moor et al., “Foundation models for generalist medical artificial intelligence,” Nature, vol. 616, no. 7956, pp. 259–265, Apr. 2023, doi: 10.1038/s41586-023-05881-4.

[11] K. Singhal et al., “Large language models encode clinical knowledge,” Nature, vol. 620, no. 7972, pp. 172–180, Aug. 2023, doi: 10.1038/s41586-023-06291-2.

[12] R. K. Halder, “Cardio Data.” IEEE DataPort, Nov. 10, 2020. doi: 10.21227/7QM5-DZ13.

[13] A. V. Chobanian et al., “Seventh Report of the Joint National Committee on Prevention, Detection, Evaluation, and Treatment of High Blood Pressure,” Hypertension, vol. 42, no. 6, pp. 1206–1252, Dec. 2003, doi: 10.1161/01.HYP.0000107251.49515.c2.

[14] T. Chen and C. Guestrin, “XGBoost: A Scalable Tree Boosting System,” in Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco California USA: ACM, Aug. 2016, pp. 785–794. doi: 10.1145/2939672.2939785.

[15] J. Kennedy and R. Eberhart, “Particle swarm optimization,” in Proceedings of ICNN’95 - International Conference on Neural Networks, Perth, WA, Australia: IEEE, 1995, pp. 1942–1948. doi: 10.1109/ICNN.1995.488968.

[16] P. R. Lorenzo, J. Nalepa, M. Kawulok, L. S. Ramos, and J. R. Pastor, “Particle swarm optimization for hyper-parameter selection in deep neural networks,” in Proceedings of the Genetic and Evolutionary Computation Conference, Berlin Germany: ACM, Jul. 2017, pp. 481–488. doi: 10.1145/3071178.3071208.

[17] M. T. Ribeiro, S. Singh, and C. Guestrin, “‘Why Should I Trust You?’: Explaining the Predictions of Any Classifier,” in Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco California USA: ACM, Aug. 2016, pp. 1135–1144. doi: 10.1145/2939672.2939778.

[18] S. Lundberg and S.-I. Lee, “A Unified Approach to Interpreting Model Predictions,” 2017, arXiv. doi: 10.48550/ARXIV.1705.07874.

[19] S. M. Lundberg et al., “From local explanations to global understanding with explainable AI for trees,” Nat. Mach. Intell., vol. 2, no. 1, pp. 56–67, Jan. 2020, doi: 10.1038/s42256-019-0138-9.

[20] V. Taquet, V. Blot, T. Morzadec, L. Lacombe, and N. Brunel, “MAPIE: an open-source library for distribution-free uncertainty quantification,” 2022, arXiv. doi: 10.48550/ARXIV.2207.12274.

[21] A. N. Angelopoulos and S. Bates, “Conformal Prediction: A Gentle Introduction,” Found. Trends® Mach. Learn., vol. 16, no. 4, pp. 494–591, Mar. 2023, doi: 10.1561/2200000101.

[22] A. Fisch, T. Schuster, T. Jaakkola, and R. Barzilay, “Conformal Prediction Sets with Limited False Positives,” 2022, arXiv. doi: 10.48550/ARXIV.2202.07650.

[23] H. Weerts, M. Dudík, R. Edgar, A. Jalali, R. Lutz, and M. Madaio, “Fairlearn: Assessing and Improving Fairness of AI Systems,” 2023, arXiv. doi: 10.48550/ARXIV.2303.16626.

[24] F. Li, P. Wu, H. H. Ong, J. F. Peterson, W.-Q. Wei, and J. Zhao, “Evaluating and mitigating bias in machine learning models for cardiovascular disease prediction,” J. Biomed. Inform., vol. 138, p. 104294, Feb. 2023, doi: 10.1016/j.jbi.2023.104294.

[25] S. S. Khan et al., “Development and Validation of the American Heart Association’s PREVENT Equations,” Circulation, vol. 149, no. 6, pp. 430–449, Feb. 2024, doi: 10.1161/CIRCULATIONAHA.123.067626.