Keywords:-
Article Content:-
Abstract
Postpartum haemorrhage (PPH) is a leading cause of maternal morbidity and mortality worldwide, with a disproportionate burden in low-resource settings where timely diagnosis is often difficult. This study presents an interpretable AI-based early warning framework for predicting PPH using machine learning. A retrospective dataset of 223 anonymized obstetric records from Mpilo Central Hospital, Zimbabwe, was used for model development. Preprocessing involved missing-value imputation, outlier capping, feature engineering, and normalization, generating clinically relevant features such as labour duration in minutes, binary obstetric risk indicators, and a composite maternal risk score. Random Forest and Multilayer Perceptron (MLP) models were trained and evaluated on an 80:20 split. Random Forest achieved superior performance, with 86.67% accuracy, 89.47% precision, 80.95% recall, an F1-score of 85.00%, and ROC-AUC of 0.8730 for the PPH class. Labour duration and delivery method were the most influential predictors. SHAP (Shapley Additive Explanations) was used to enhance interpretability and clinical transparency. The findings show that interpretable machine learning can deliver reliable predictive performance even on small clinical datasets from resource-constrained settings, supporting proactive obstetric intervention and improved decision-making.
References:-
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., et al. (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 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., & Sunv, Z. (2025). Postpartum Hemorrhage Prediction Based on Convolutional Neural Networks. 2025 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.
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 CAIN, 48-59.