Explainable Ensemble Learning for Maternal Health Risk in Low-Resource Settings

Authors

DOI:

https://doi.org/10.29207/resti.v9i5.6765

Keywords:

ensemble learning, explainable AI, maternal health, risk prediction, SHAP Analysis

Abstract

Maternal health remains a global challenge, particularly in low-resource settings where accurate and timely risk prediction is essential to reducing maternal mortality. This study proposes an explainable machine learning framework for predicting maternal health risks by integrating ensemble learning methods with SHAP (Shapley Additive exPlanations) for interpretability. This study utilized the publicly available Maternal Health Risk Data Set (MHRDS), comprising physiological features such as systolic and diastolic blood pressure, blood sugar level, body temperature, and age. A total of 18 machine learning models including Random Forest, XGBoost, LightGBM, Neural Networks, and TabNet were evaluated to compare individual classifiers and ensemble approaches comprehensively. The selection of this diverse set of models is grounded in the need to benchmark different algorithmic paradigms, as variations in inductive bias, learning capacity, and robustness to clinical data noise can influence predictive performance and generalizability. This comprehensive comparison enables the identification of optimal model types for integration into ensemble frameworks. Evaluation was performed across three different test scenarios (test sizes of 10%, 20%, and 30%) to assess model consistency under varying data partitions. Stacking, Voting, and Histogram-based Gradient Boosting showed consistently high performance, with Stacking achieving the highest accuracy of 87.2%, followed by Histogram Gradient Boosting (86.9%) and Voting (86.7%) at test size 0.2. SHAP analysis identified blood sugar, systolic blood pressure, and maternal age as the top predictors across all test scenarios. The best-performing models were deployed into a web-based clinical decision support system designed for healthcare practitioners in Indonesia. The proposed approach balances predictive accuracy and model transparency, offering a practical solution for improving maternal care in data-limited environments.

Downloads

Download data is not yet available.

Author Biography

  • Lilik Widyawati, Universitas Bumigora

    Departement of Computer Science, Faculty of Engineering, Bumigora University

References

E. K. Ekwuazi, C. O. Chigbu, and N. C. Ngene, “Reducing maternal mortality in low- and middle-income countries,” Case Reports Women’s Heal., vol. 39, no. September, 2023, [Online]. Available: https://doi.org/10.1016/j.crwh.2022.e00471.

S. G. Ahmad et al., “Sensing and Artificial Intelligent Maternal-Infant Health Care Systems : A Review,” Sensors, vol. 22, no. 4362, pp. 1–25, 2022.

B. Jean-Francois, T. Bailey Lash, R. K. Dagher, M. C. Green Parker, S. B. Han, and T. Lewis Johnson, “The Potential for Health Information Technology Tools to Reduce Racial Disparities in Maternal Morbidity and Mortality,” J. Women’s Heal., vol. 30, no. 2, pp. 274–279, 2021, doi: 10.1089/jwh.2020.8889.

A. Bertini, R. Salas, S. Chabert, L. Sobrevia, and F. Pardo, “Using Machine Learning to Predict Complications in Pregnancy: A Systematic Review,” Front. Bioeng. Biotechnol., vol. 9, no. January, pp. 1–16, 2022, doi: 10.3389/fbioe.2021.780389.

A. Fredriksson et al., “Machine learning for maternal health: Predicting delivery location in a community health worker program in Zanzibar,” Front. Digit. Heal., vol. 4, no. August, pp. 1–10, 2022, doi: 10.3389/fdgth.2022.855236.

T. O. Togunwa, A. O. Babatunde, and K. U. R. Abdullah, “Deep hybrid model for maternal health risk classification in pregnancy: synergy of ANN and random forest,” Front. Artif. Intell., vol. 6, 2023, doi: 10.3389/frai.2023.1213436.

N. Ali, W. Khan, A. Ahmad, M. M. Masud, H. Adam, and L. A. Ahmed, “Predictive Modeling for the Diagnosis of Gestational Diabetes Mellitus Using Epidemiological Data in the United Arab Emirates,” Inf., vol. 13, no. 10, pp. 1–12, 2022, doi: 10.3390/info13100485.

A. Maaloul, M. Jemel, and N. Ben Azzouna, XAI based feature selection for gestational diabetes Mellitus prediction, no. Icodai 2024. Atlantis Press International BV, 2024.

N. Goswami et al., “EVATOM: an optical, label-free, machine learning assisted embryo health assessment tool,” Commun. Biol., vol. 7, no. 1, 2024, doi: 10.1038/s42003-024-05960-w.

T. M. Bosschieter et al., “Interpretable Predictive Models to Understand Risk Factors for Maternal and Fetal Outcomes,” J. Healthc. Informatics Res., vol. 8, no. 1, pp. 65–87, 2024, doi: 10.1007/s41666-023-00151-4.

H. B. Mutlu, F. Durmaz, N. Yucel, E. Cengil, and M. Yildirim, “Prediction of Maternal Health Risk with Traditional Machine Learning Methods,” NATURENGS MTU J. Eng. Nat. Sci. Mal. Turgut Ozal Univ., vol. 4, no. 1, pp. 16–23, 2023, doi: 10.46572/naturengs.1293185.

T. R. Noviandy, S. I. Nainggolan, R. Raihan, I. Firmansyah, and R. Idroes, “Maternal Health Risk Detection Using Light Gradient Boosting Machine Approach,” Infolitika J. Data Sci., vol. 1, no. 2, pp. 48–55, 2023, doi: 10.60084/ijds.v1i2.123.

I. Guyon, M. Nikravesh, S. Gunn, and L. A. Zadeh, Feature Extraction: Foundations and Applications. Springer, 2026.

J. Han, M. Kamber, and P. Jian, Data Mining: Concepts and Techniques Third Editions. 2011.

S. Arık and T. Pfister, “TabNet: Attentive Interpretable Tabular Learning,” 35th AAAI Conf. Artif. Intell. AAAI 2021, pp. 6679–6687, 2021, doi: 10.1609/aaai.v35i8.16826.

C. Mosquera, L. Ferrer, D. Milone, D. Luna, and E. Ferrante, “Impact of class imbalance on chest x-ray classifiers: towards better evaluation practices for discrimination and calibration performance,” pp. 1–11, 2021, [Online]. Available: http://arxiv.org/abs/2112.12843.

L. Gómez-Jemes, A. M. Oprescu, Á. Chimenea-Toscano, L. García-Díaz, and M. del C. Romero-Ternero, “Machine Learning to Predict Pre-Eclampsia and Intrauterine Growth Restriction in Pregnant Women,” Electron., vol. 11, no. 19, pp. 1–14, 2022, doi: 10.3390/electronics11193240.

D. Preethi and N. Khare, “Performance Evaluation of Shallow learning techniques and Deep Neural Network for Cyber Security,” Int. Conf. Emerg. Trends Inf. Technol. Eng. ic-ETITE 2020, pp. 1–5, 2020, doi: 10.1109/ic-ETITE47903.2020.128.

T. Saito and M. Rehmsmeier, “The precision-recall plot is more informative than the ROC plot when evaluating binary classifiers on imbalanced datasets,” PLoS One, vol. 10, no. 3, pp. 1–21, 2015, doi: 10.1371/journal.pone.0118432.

G. Litjens et al., “A survey on deep learning in medical image reconstruction,” Med. Image Anal., vol. 42, pp. 60–88, 2017, doi: 10.1016/j.imed.2021.03.003.

S. Tomura, M. J. Wilkinson, M. Cooper, and O. Powell, “Improved genomic prediction performance with ensembles of diverse models,” G3 Genes, Genomes, Genet., vol. 15, no. 5, 2025, doi: 10.1093/g3journal/jkaf048.

D. Wood, T. Mu, A. M. Webb, H. W. J. Reeve, M. Luján, and G. Brown, “A Unified Theory of Diversity in Ensemble Learning,” J. Mach. Learn. Res., vol. 24, pp. 1–49, 2023.

J. M. Reps, R. D. Williams, M. J. Schuemie, P. B. Ryan, and P. R. Rijnbeek, “Learning patient-level prediction models across multiple healthcare databases: evaluation of ensembles for increasing model transportability,” BMC Med. Inform. Decis. Mak., vol. 22, no. 1, pp. 1–14, 2022, doi: 10.1186/s12911-022-01879-6.

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, pp. 1–34, 2025, doi: 10.1038/s41598-025-97547-6.

M. M. Hossain, M. A. Kashem, N. M. Nayan, and M. A. Chowdhury, “A Medical Cyber-physical system for predicting maternal health in developing countries using machine learning,” Healthc. Anal., vol. 5, no. October 2023, 2024, doi: 10.1016/j.health.2023.100285.

S. Diana, C. U. Wahyuni, and B. Prasetyo, “Maternal complications and risk factors for mortality,” J. Public health Res., vol. 9, no. 2, pp. 195–198, 2020, doi: 10.4081/jphr.2020.1842.

Csafrit, “Maternal Health Risk Data,” 2021. https://www.kaggle.com/datasets/csafrit2/maternal-health-risk-data.

M. Ahmed and M. A. Kashem, “IoT Based Risk Level Prediction Model for Maternal Health Care in the Context of Bangladesh,” 2020 2nd Int. Conf. Sustain. Technol. Ind. 4.0, STI 2020, no. February, 2020, doi: 10.1109/STI50764.2020.9350320.

Y. Xu and V. Keselj, “Stock Prediction using Deep Learning and Sentiment Analysis,” Proc. - 2019 IEEE Int. Conf. Big Data, Big Data 2019, pp. 5573–5580, 2019, doi: 10.1109/BigData47090.2019.9006342.

W. Li, Y. Yin, X. Quan, and H. Zhang, “Gene Expression Value Prediction Based on XGBoost Algorithm,” Front. Genet., vol. 10, no. November, pp. 1–7, 2019, doi: 10.3389/fgene.2019.01077.

J. M. Johnson and T. M. Khoshgoftaar, “Survey on deep learning with class imbalance,” J. Big Data, vol. 6, no. 1, 2019, doi: 10.1186/s40537-019-0192-5.

G. Ke et al., “LightGBM: A highly efficient gradient boosting decision tree,” Adv. Neural Inf. Process. Syst., vol. 2017-Decem, no. Nips, pp. 3147–3155, 2017.

L. Prokhorenkova, G. Gusev, A. Vorobev, A. V. Dorogush, and A. Gulin, “Catboost: Unbiased boosting with categorical features,” Adv. Neural Inf. Process. Syst., vol. 2018-Decem, no. Section 4, pp. 6638–6648, 2018.

M. Arif, “Explainable AI in Maternal Health: Utilizing XGBoost and SHAP Values for Enhanced Risk Prediction and Interpretation,” Int. J. Emerg. Multidiciplinaries Comput. Sci. Artif. Intell., vol. 4, no. 1, p. 16, 2025, doi: 10.54938/ijemdcsai.2025.04.1.419.

A. Raza, H. U. R. Siddiqui, K. Munir, M. Almutairi, F. Rustam, and I. Ashraf, “Ensemble learning-based feature engineering to analyze maternal health during pregnancy and health risk prediction,” PLOS ONE |, vol. 17, no. 11, pp. 1–29, 2021, doi: ttps://doi.org/10.1371/journal.pone.0276525.

Downloads

Published

2025-10-24

Issue

Section

Computer Science Applications

How to Cite

Widyawati, L., & Sulistianingsih, N. (2025). Explainable Ensemble Learning for Maternal Health Risk in Low-Resource Settings. Jurnal RESTI (Rekayasa Sistem Dan Teknologi Informasi), 9(5), 1121-1130. https://doi.org/10.29207/resti.v9i5.6765