AN AI-BASED MATERNAL HEALTH RISK PREDICTION MODEL USING MULTILAYER PERCEPTRON AND COMPREHENSIVE DATA PREPROCESSING

Dien Kartika Lutfi

Authors

Dien Kartika Lutfi Universitas Sebelas Maret

Keywords:

Artificial Intelligence, Maternal Health, Risk Prediction, Multilayer Perceptron, Machine Learning

Abstract

Background: Maternal health risk detection is essential for reducing pregnancy-related complications and improving maternal and fetal outcomes. However, conventional risk assessment remains challenging due to data quality issues and limitations in accurately identifying high-risk pregnancies. Artificial Intelligence (AI) offers promising solutions for improving maternal health risk prediction. Objectives: This study aims to develop and evaluate an AI-based maternal health risk prediction model using the Multilayer Perceptron (MLP) classifier and to assess the contribution of comprehensive data preprocessing techniques in improving prediction performance. Methods: The study utilized the Maternal Health and High-Risk Pregnancy Dataset containing maternal clinical and physiological indicators. Data preprocessing included missing value imputation, duplicate removal, outlier treatment using the capping method, feature scaling with Robust Scaler, and class balancing through Random Oversampling (ROS). The MLP classifier was trained using a supervised learning approach and evaluated using Accuracy, Precision, Recall, F1-score, Specificity, and Classification Error. Results: The proposed model achieved an accuracy of 97.60%, precision of 97.07%, recall of 98.20%, F1-score of 97.62%, specificity of 96.99%, and a classification error of 2.40%, demonstrating excellent predictive performance. Conclusions: The integration of comprehensive preprocessing techniques with the MLP classifier significantly improves maternal health risk prediction. The proposed model shows strong potential to support early risk detection, clinical decision-making, and preventive maternal healthcare through accurate and reliable AI-based prediction.

References

Al Mashrafi, S. S., Tafakori, L., & Abdollahian, M. (2024). Predicting maternal risk level using machine learning models. BMC Pregnancy and Childbirth, 24(1). https://doi.org/10.1186/s12884-024-07030-9

Chayan, A. R. (2024). Maternal Health and High-Risk Pregnancy Dataset. https://doi.org/10.17632/8k9pvpmykk.1

Gao, J., Yao, Y., Xue, J., Chen, R., Yang, X. Y., Xu, J., & Cheng, W. (2025). Methodological conduct and risk of bias in studies on prenatal birthweight prediction models using machine learning techniques: a systematic review. BMC Pregnancy and Childbirth, 25(1). https://doi.org/10.1186/s12884-025-07727-5

Islam, S., Shahriyar, R., Agarwala, A., Zaman, M., Ahamed, S., Rahman, R., Chowdhury, M. H., Sarker, F., & Mamun, K. A. (2025). Artificial intelligence-based risk assessment tools for sexual, reproductive and mental health: a systematic review. BMC Medical Informatics and Decision Making, 25(1). https://doi.org/10.1186/s12911-025-02864-5

Khadidos, A. O., Saleem, F., Selvarajan, S., Ullah, Z., & Khadidos, A. O. (2024). Ensemble machine learning framework for predicting maternal health risk during pregnancy. Scientific Reports, 14(1), 1–21. https://doi.org/10.1038/s41598-024-71934-x

Li, T., Xu, M., Wang, Y., Wang, Y., Tang, H., Duan, H., Zhao, G., Zheng, M., & Hu, Y. (2024). Prediction model of preeclampsia using machine learning based methods: a population based cohort study in China. Frontiers in Endocrinology, 15(June), 1–14. https://doi.org/10.3389/fendo.2024.1345573

Malde, A., Prabhu, V. G., Banga, D., Hsieh, M., Renduchintala, C., & Pirrallo, R. (2025). A Machine Learning Approach for Predicting Maternal Health Risks in Lower-Middle-Income Countries Using Sparse Data and Vital Signs. Future Internet, 17(5). https://doi.org/10.3390/fi17050190

Malik, V., Agrawal, N., Prasad, S., Talwar, S., Khatuja, R., Jain, S., Sehgal, N. P., Malik, N., Khatuja, J., & Madan, N. (2024). Prediction of Preeclampsia Using Machine Learning: A Systematic Review. Cureus, 16(12). https://doi.org/10.7759/cureus.76095

Mamun, M., Chowdhury, S. H., Faruq, M. O., Azad, M. M., Biswas, B. R., Hussain, M. I., & Hossain, M. M. (2025). Identification of Maternal Health Risk From Optimal Features Using Explainable Machine Learning. Engineering Reports, 7(11). https://doi.org/10.1002/eng2.70491

Özcan, M., & Peker, S. (2025). Preeclampsia prediction via machine learning: a systematic literature review. Health Systems, 14(3), 208–222. https://doi.org/10.1080/20476965.2024.2435845

Pavagada, K., & Vemuri, J. (2025). Prediction of Maternal Health Risk Factors Using Machine Learning Algorithms. Procedia Computer Science, 258, 2713–2722. https://doi.org/10.1016/j.procs.2025.04.532

Tzimourta, K. D., Tsipouras, M. G., Angelidis, P., Tsalikakis, D. G., & Orovou, E. (2025). Maternal Health Risk Detection: Advancing Midwifery with Artificial Intelligence. Healthcare (Switzerland), 13(7). https://doi.org/10.3390/healthcare13070833

Vasudevan, L., Kibria, M. G., Kucirka, L. M., Shieh, K., Wei, M., Masoumi, S., Balasubramanian, S., Victor, A., Conklin, J. L., Gurcan, M. N., Stuebe, A. M., & Page, D. (2025). Machine Learning Models to Predict Risk of Maternal Morbidity and Mortality From Electronic Medical Record Data: Scoping Review. Journal of Medical Internet Research, 27, 1–13. https://doi.org/10.2196/68225

WHO. (2025). Maternal Mortality.

Xinyu Pi, et al. (2021). Prediction of high-risk pregnancy based on machine learning algorithms. International Eye Science, 21(9), 1644–1648. https://doi.org/https://doi.org/10.1038/s41598-025-00450-3 1