Cross-Dataset Evaluation of Boosting Models for Hypertension Prediction

Bety Wulan  Sari; Dewi Ayu  Murtiningsih; Donni  Prabowo; Yoga Pristyanto; Ika Nur Fajri; Ike Verawati

doi:10.29207/resti.v10i4.7620

Authors

Bety Wulan Sari Universitas AMIKOM Yogyakarta
Dewi Ayu Murtiningsih Universitas AMIKOM Yogyakarta
Donni Prabowo Universitas AMIKOM Yogyakarta
Yoga Pristyanto Universitas AMIKOM Yogyakarta
Ika Nur Fajri Universitas AMIKOM Yogyakarta
Ike Verawati Universitas AMIKOM Yogyakarta

DOI:

https://doi.org/10.29207/resti.v10i4.7620

Keywords:

AUC, boosting algorithms, cross-dataset evaluation, hypertension prediction, hyperparameter tuning

Abstract

Hypertension remains a significant global risk factor for cardiovascular disease and related mortality, necessitating reliable early risk prediction models. Although boosting algorithms have demonstrated strong performance in structured medical data, limited studies have examined their consistency across heterogeneous datasets. This study aims to evaluate the cross-dataset performance and stability of three boosting models, such as XGBoost, LightGBM, and CatBoost, for hypertension prediction under multiple train–test split ratios. Two independent structured datasets were analyzed using 60:40, 70:30, 80:20, and 90:10 splits. To identify the optimal hyperparameters, grid search was performed using repeated stratified 5-fold cross-validation with three repetitions. Model effectiveness was measured using the evaluation metrics of accuracy, precision, recall, F1-score, and AUC. Results show that Dataset 1 gained consistently high predictive performance (accuracy > 0.98; AUC ≈ 1.00), indicating strong and well-separated predictive signals, whereas Dataset 2 demonstrated substantially lower discriminative ability (accuracy ≈ 0.71–0.72; AUC ≈ 0.50), suggesting limited predictive structure. Across both datasets, CatBoost consistently obtained the highest accuracy, particularly at the 90:10 split ratio. These findings demonstrate that dataset characteristics critically determine model effectiveness and that among the evaluated boosting algorithms, CatBoost delivered the strongest overall predictive performance.

Downloads

Download data is not yet available.

References

S. Goorani, S. Zangene, and J. D. Imig, “Hypertension: A Continuing Public Healthcare Issue,” Int. J. Mol. Sci., vol. 26, no. 1, p. 123, Dec. 2024, doi: 10.3390/ijms26010123.

H. Kohjitani, H. Koshimizu, K. Nakamura, and Y. Okuno, “Recent developments in machine learning modeling methods for hypertension treatment,” Hypertension Research, vol. 47, no. 3, pp. 700–707, Mar. 2024, doi: 10.1038/s41440-023-01547-w.

U. Singh, M. Rizwan, M. Alaraj, and I. Alsaidan, “A Machine Learning-Based Gradient Boosting Regression Approach for Wind Power Production Forecasting: A Step towards Smart Grid Environments,” Energies (Basel)., vol. 14, no. 16, p. 5196, Aug. 2021, doi: 10.3390/en14165196.

M. Tanaka et al., “Machine learning-based analyses of contributing factors for the development of hypertension: a comparative study,” Clin. Exp. Hypertens., vol. 47, no. 1, 2025, doi: 10.1080/10641963.2025.2449613.

M. Fang et al., “A hybrid machine learning approach for hypertension risk prediction,” Neural Comput. Appl., vol. 35, no. 20, pp. 14487–14497, Jul. 2023, doi: 10.1007/s00521-021-06060-0.

V. E. Gutiérrez-Carmona, M. A. Luna-Montes, A. Guzmán-Pando, J. Camarillo-Cisneros, and N. G. Sámano-Lira, “Hypertension Risk Prediction in Mexican Population Using Machine Learning Models,” 2026, pp. 79–88. doi: 10.1007/978-3-032-13729-6_9.

E. Septian et al., “Prediction of Personalised Hypertension Using Machine Learning in Indonesian Population,” J. Med. Syst., vol. 49, no. 1, Dec. 2025, doi: 10.1007/s10916-025-02253-5.

Y. Wang et al., “Prediction Model of Intradialytic Hypertension in Hemodialysis Patients Based on Machine Learning,” J. Med. Syst., vol. 49, no. 1, Dec. 2025, doi: 10.1007/s10916-025-02237-5.

S. Montagna et al., “Machine Learning in Hypertension Detection: A Study on World Hypertension Day Data,” J. Med. Syst., vol. 47, no. 1, Dec. 2023, doi: 10.1007/s10916-022-01900-5.

S. M. S. Islam et al., “Machine Learning Approaches for Predicting Hypertension and Its Associated Factors Using Population-Level Data From Three South Asian Countries,” Front. Cardiovasc. Med., vol. 9, Mar. 2022, doi: 10.3389/fcvm.2022.839379.

R. Kurniawan et al., “Hypertension prediction using machine learning algorithm among Indonesian adults,” IAES International Journal of Artificial Intelligence, vol. 12, no. 2, pp. 776–784, Jun. 2023, doi: 10.11591/ijai.v12.i2.pp776-784.

R. Oulhiq, K. Benjelloun, Y. Kali, and M. Saad, “A data mining based approach for process identification using historical data,” International Journal of Modelling and Simulation, vol. 42, no. 2, pp. 335–349, Mar. 2022, doi: 10.1080/02286203.2021.1905375.

J. Sadaiyandi, P. Arumugam, A. K. Sangaiah, and C. Zhang, “Stratified Sampling-Based Deep Learning Approach to Increase Prediction Accuracy of Unbalanced Dataset,” Electronics (Basel)., vol. 12, no. 21, p. 4423, Oct. 2023, doi: 10.3390/electronics12214423.

T. Yousefi and Ö. Varlıklar, “New hybrid multi-objective feature selection: Boruta-XGBoost,” PeerJ Comput. Sci., vol. 12, p. e3463, Jan. 2026, doi: 10.7717/peerj-cs.3463.

Y. Pristyanto, A. F. Nugraha, B. Wulan Sari, M. Sulistiyono, and A. Sunyoto, “Enhancement of Machine Learning Models Using Intersection Filtering Model Based on Recursive Feature Elimination on Specified Android Malware Classification,” International Journal of Intelligent Engineering and Systems, vol. 18, no. 3, pp. 836–852, Apr. 2025, doi: 10.22266/ijies2025.0430.56.

B. Wulan Sari and D. Prabowo, “Optimization of Thyroid Disease Prediction Using Feature Selection with Dynamic Threshold,” International Journal of Intelligent Engineering and Systems, vol. 18, no. 8, pp. 168–183, Sep. 2025, doi: 10.22266/ijies2025.0930.12.

S. Abdumalikov, J. Kim, and Y. Yoon, “Performance Analysis and Improvement of Machine Learning with Various Feature Selection Methods for EEG-Based Emotion Classification,” Applied Sciences, vol. 14, no. 22, p. 10511, Nov. 2024, doi: 10.3390/app142210511.

A. A. Engda, A. O. Salau, and O. Ajala, “Classical Machine Learning Approaches for Early Hypertension Risk Prediction: A Systematic Review,” Oct. 01, 2025, John Wiley and Sons Inc. doi: 10.1002/ail2.70005.

N. L. Fitriyani et al., “A Novel Approach Utilizing Bagging, Histogram Gradient Boosting, and Advanced Feature Selection for Predicting the Onset of Cardiovascular Diseases,” Mathematics, vol. 13, no. 13, p. 2194, Jul. 2025, doi: 10.3390/math13132194.

K. Thomas, A. Khandakar, P. Chelvanathan, B. Aissa, and M. I. Hossain, “Enhanced prediction and optimization of thin metal film optical properties using optimized ensemble learning models,” Sci. Rep., vol. 15, no. 1, p. 43523, Dec. 2025, doi: 10.1038/s41598-025-27524-6.

D. Prabowo, Bety Wulan Sari, Yoga Pristyanto, and Afrig Aminuddin, “Enhanced Predictive Modeling for Non-Invasive Liver Disease Diagnosis,” Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi), vol. 9, no. 4, pp. 745–753, Aug. 2025, doi: 10.29207/resti.v9i4.6449.

M.-L. Leitner and M. Arendasy, “Comparing machine learning and artificial neural network models in psychological research: a ROC-based analysis,” Front. Psychol., vol. 17, Feb. 2026, doi: 10.3389/fpsyg.2026.1746479.

J. Li, “Area under the ROC Curve has the most consistent evaluation for binary classification,” PLoS One, vol. 19, no. 12, p. e0316019, Dec. 2024, doi: 10.1371/journal.pone.0316019.

H. Han, “The Utility of Receiver Operating Characteristic Curve in Educational Assessment: Performance Prediction,” Mathematics, vol. 10, no. 9, p. 1493, Apr. 2022, doi: 10.3390/math10091493.

K. Merabet et al., “Predicting water quality variables using gradient boosting machine: global versus local explainability using SHapley Additive Explanations (SHAP),” Earth Sci. Inform., vol. 18, no. 3, p. 298, Sep. 2025, doi: 10.1007/s12145-025-01796-y.

B. Oral, H. A. Maddah, and R. Yildirim, “Predictive Modeling and SHAP (SHapley Additive ExPlanations) Analysis for Enhancing Natural Dye‐Sensitized Solar Cell Performance,” Solar RRL, vol. 8, no. 22, Nov. 2024, doi: 10.1002/solr.202400432.

Y. Sakka, D. Qarashai, and A. Altarawneh, “Predicting Hypertension using Machine Learning: A Case Study at Petra University,” 2023, doi: 10.14569/IJACSA.2023.0140368.

M. M. Islam et al., “Predicting the risk of hypertension using machine learning algorithms: A cross sectional study in Ethiopia,” PLoS One, vol. 18, no. 8 August, Aug. 2023, doi: 10.1371/journal.pone.0289613.