Volume 15, Issue 8 · IJARST · ISSN 2319-1783 / 2320-1126

ADVANCING AI-DRIVEN EARLY WARNING SYSTEMS FOR PREDICTION AND PREVENTION OF POSTPARTUM HAEMORRHAGE

ADVANCING AI-DRIVEN EARLY WARNING SYSTEMS FOR PREDICTION AND PREVENTION OF POSTPARTUM HAEMORRHAGE is an open-access, peer-reviewed research paper by Ohia Paul Ndudiri and Olojido Joseph Bamikole, published in Volume 15, Issue 8 of the International Journal of Advanced Research in Science and Technology (IJARST), a UGC-approved journal (Print ISSN 2319-1783, Online ISSN 2320-1126).

Author

Ohia Paul Ndudiri and Olojido Joseph Bamikole

Abstract

Postpartum haemorrhage (PPH) remains one of the leading causes of maternal morbidity and mortality worldwide, particularly in low-resource healthcare settings where delayed diagnosis and limited access to timely intervention significantly increase adverse maternal outcomes. This study developed and evaluated an artificial intelligence (AI)-based early warning model for predicting PPH risk using machine learning techniques to support timely clinical decision-making. A retrospective dataset comprising 223 anonymised maternal records obtained from Mpilo Central Hospital, Zimbabwe, was analysed. Data preprocessing involved handling missing values, capping outliers, and engineering clinically relevant features  including labour duration, binary risk indicators, and a composite risk score followed by Min-Max normalization. Two supervised machine learning algorithms, Random Forest (RF) and Multilayer Perceptron (MLP), were trained and evaluated using an 80:20 train-test split. The RF model demonstrated superior predictive performance, achieving an accuracy of 86.67%, precision of 89.47%, recall of 80.95%, F1-score of 85.00%, and an area under the receiver operating characteristic curve (ROC-AUC) of 0.8730. Model interpretability was enhanced using SHapley Additive exPlanations (SHAP), which identified labour duration and mode of delivery as the most influential predictors of PPH. Compared with previously reported machine learning approaches, the proposed framework achieves competitive predictive performance while maintaining transparency on a relatively small, real-world dataset from a resource-constrained setting. The model offers a practical decision support tool for the early identification of women at high risk of PPH, enabling prompt clinical intervention and potentially reducing PPH related maternal morbidity and mortality.

Keywords: Postpartum haemorrhage; machine learning; early warning system; Random Forest; SHAP; maternal health.

DOI: https://doi.org/10.62226/ijarst20262788

References

Elser, H., Mumford, S., Grantz, K., Pollack, A., Mendola, P., Mills, J., Yeung, E., Zhang, C., Schisterman, E., & Hinkle, S. (2025). Postpartum Haemorrhage and Long-Term Mortality. Paediatric and Perinatal Epidemiology. https://doi.org/10.1111/ppe.13166

Lee, S., & Kang, Y. (2022). Postpartum hemorrhage. Taiwanese Journal of Obstetrics & Gynecology, 61(1), 5-7. https://doi.org/10.1016/j.tjog.2021.11.003

Riches, J., Jafali, J., Twabi, H., Chimwaza, Y., Onrust, M., Bilesi, R., Gadama, L., Kachale, F., Kuyere, A., Makhaza, L., Makuluni, R., Munthali, L., Musopole, O., Ndamala, C., Phiri, D., Coomarasamy, A., Merriel, A., Waitt, C., Odland, M., & Lissauer, D. (2025). Avoidable factors associated with maternal death from postpartum haemorrhage: a national Malawian surveillance study. BMJ Global Health, 10. https://doi.org/10.1136/bmjgh-2024-015781

Sumikura, H. (2025). Postpartum Hemorrhage: Preventable Maternal Deaths and the Role of Coagulation Monitoring. Journal of Obstetrics and Gynaecology Research, 51. https://doi.org/10.1111/jog.70134

Ende, H., & Butwick, A. (2021). Current State and Future Direction of Postpartum Hemorrhage Risk Assessment. Obstetrics & Gynecology, 138, 924-930. https://doi.org/10.1097/aog.0000000000004579

Joshi, D. (2025). Why Traditional Statistical Methods Need to Evolve in the Age of Artificial Intelligence: A Biostatistical Perspective. Nepal Journal of Public Health. https://doi.org/10.70280/njph(2025)v2i1.31

Raman, R., Kumar, V., Pillai, B., Verma, A., Rastogi, S., & Pandey, D. (2025). Predictive Machine Learning Models for Postpartum Hemorrhage Risk Assessment. 2025 International Conference on Intelligent and Innovative Technologies in Computing, Electrical and Electronics (IITCEE), 1-6. https://doi.org/10.1109/iitcee64140.2025.10915212

Yao, X., Bao, Y., Wu, N., Shan, S., Xu, Y., Huo, K., Huang, R., & Ying, H. (2025). Interpretable machine-learning-based prediction of postpartum haemorrhage in normal vaginal births in Shanghai, China. Frontiers in Medicine, 12. https://doi.org/10.3389/fmed.2025.1670987

Xiao, Y., Hu, Z., Yuan, B., & Sun, Z. (2025). Postpartum Hemorrhage Prediction Based on Convolutional Neural Networks. 2025 2nd International Conference on Digital Image Processing and Computer Applications (DIPCA), 182-186. https://doi.org/10.1109/dipca65051.2025.11042290

Lérias-Cambeiro, M., Mugeiro-Silva, R., Rodrigues, A., Dias-Domingues, T., Lança, F., & Carneiro, A. (2025). Enhancing Postpartum Haemorrhage Prediction Through the Integration of Classical Logistic Regression and Machine Learning Algorithms. Mathematics. https://doi.org/10.3390/math13213376

Nelli, F. (2023). Python Data Analytics: With Pandas, NumPy, and Matplotlib. Python Data Analytics. https://doi.org/10.1007/978-1-4842-9532-8

Adugna, T., Xu, W., & Fan, J. (2022). Comparison of Random Forest and Support Vector Machine Classifiers for Regional Land Cover Mapping Using Coarse Resolution FY-3C Images. Remote Sensing, 14, 574. https://doi.org/10.3390/rs14030574

Nohara, Y., Matsumoto, K., Soejima, H., & Nakashima, N. (2021). Explanation of Machine Learning Models Using Shapley Additive Explanation and Application for Real Data in Hospital. Computer Methods and Programs in Biomedicine, 214, 106584. https://doi.org/10.1016/j.cmpb.2021.106584

Parida, S., Gerostathopoulos, I., & Bogner, J. (2025). How Do Model Export Formats Impact the Development of ML-Enabled Systems? A Case Study on Model Integration. 2025 IEEE/ACM 4th International Conference on AI Engineering - Software Engineering for AI (CAIN), 48-59. https://doi.org/10.1109/cain66642.2025.00014

DOI

10.62226/ijarst20262788

PAGES : 2550-2558 | 4 VIEWS | 2 DOWNLOADS

How do you cite this paper?

Ohia Paul Ndudiri and Olojido Joseph Bamikole — “ADVANCING AI-DRIVEN EARLY WARNING SYSTEMS FOR PREDICTION AND PREVENTION OF POSTPARTUM HAEMORRHAGE.” International Journal of Advanced Research in Science and Technology (IJARST), Volume 15, Issue 8. DOI: 10.62226/ijarst20262788.

Read / Download Full Article