Integrative Biomedical Research
Integrative Biomedical Research (Journal of Angiotherapy) | Online ISSN 3068-6326
685
Citations
1.4m
Views
731
Articles
Volume 10 Number 1 2026
RESEARCH ARTICLE (Open Access)
An Integrated AI-Driven Framework for Maternal Resource Intelligence Shortages Across U.S. Hospital
Shaid Hasan 1*, Khandaker Ataur Rahman 1, Fahad Ahmed 2, Adib Hossain 3
Integrative Biomedical Research 10 (1) 1-8 https://doi.org/10.25163/biomedical.10110694
Submitted: 31 December 2025 Revised: 12 March 2026 Accepted: 16 March 2026 Published: 18 March 2026
Abstract
Background: Maternal mortality in the United States remains persistently high, with pronounced disparities across racial, geographic, and socioeconomic groups. While advances in machine learning have improved the prediction of obstetric complications, these models rarely translate into actionable operational decisions. As a result, a critical gap remains between clinical risk identification and the availability of essential resources—such as blood products and staffing—during obstetric emergencies.Methods: This study developed a multicenter, retrospective cohort framework integrating electronic health records, hospital supply chain data, workforce capacity, and community-level vulnerability indicators. Gradient boosting models were used to predict postpartum hemorrhage risk and short-term resource demand. These predictions were then incorporated into a reinforcement learning–based optimization system to guide dynamic resource allocation. Causal effects of resource adequacy on maternal outcomes were estimated using marginal structural models with inverse probability weighting, while equity was integrated through Social Vulnerability Index–based weighting.Results: The predictive model demonstrated strong performance (AUROC = 0.89) and accurately forecasted maternal blood demand (RMSE = 2.8 units/day). Reinforcement learning–based optimization reduced resource shortages by 37% and product wastage by 18%, with a 42% reduction in shortages observed in high-vulnerability settings. Causal analysis indicated that adequate resource availability was associated with a 21% reduction in severe maternal morbidity (ARR = 0.79; 95% CI: 0.72–0.87), with stronger effects in structurally vulnerable populations.Conclusion: Integrating predictive analytics with operational decision intelligence and causal evaluation offers a promising pathway to improve maternal health outcomes. By aligning clinical risk with real-time resource readiness and embedding equity into decision-making, this framework advances a more resilient and responsive maternal healthcare system.
Keywords: Maternal mortality; Machine learning; Reinforcement learning; Healthcare supply chain; Health equity
References
Chen, T., & Guestrin, C. (2016). XGBoost: A scalable tree boosting system. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. https://doi.org/10.1145/2939672.2939785
Chen, T., & Guestrin, C. (2016). XGBoost: A scalable tree boosting system. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. https://doi.org/10.1145/2939672.2939785
Chen, T., & Guestrin, C. (2016). XGBoost: A scalable tree boosting system. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. https://doi.org/10.1145/2939672.2939785
Flanagan, B. E., Gregory, E. W., Hallisey, E. J., Heitgerd, J. L., & Lewis, B. (2011). A social vulnerability index for disaster management. Journal of Homeland Security and Emergency Management, 8(1). https://doi.org/10.2202/1547-7355.1792
Flanagan, B. E., Gregory, E. W., Hallisey, E. J., Heitgerd, J. L., & Lewis, B. (2011). A social vulnerability index for disaster management. Journal of Homeland Security and Emergency Management, 8(1). https://doi.org/10.2202/1547-7355.1792
Flanagan, B. E., Gregory, E. W., Hallisey, E. J., Heitgerd, J. L., & Lewis, B. (2011). A social vulnerability index for disaster management. Journal of Homeland Security and Emergency Management, 8(1). https://doi.org/10.2202/1547-7355.1792
Friedman, J. H. (2001). Greedy function approximation: A gradient boosting machine. Annals of Statistics, 29(5), 1189–1232. https://doi.org/10.1214/aos/1013203451
Friedman, J. H. (2001). Greedy function approximation: A gradient boosting machine. Annals of Statistics, 29(5), 1189–1232. https://doi.org/10.1214/aos/1013203451
Friedman, J. H. (2001). Greedy function approximation: A gradient boosting machine. Annals of Statistics, 29(5), 1189–1232. https://doi.org/10.1214/aos/1013203451
Gottesman, O., Johansson, F., Komorowski, M., et al. (2019). Guidelines for reinforcement learning in healthcare. Nature Medicine, 25(1), 16–18. https://doi.org/10.1038/s41591-018-0310-5
Gottesman, O., Johansson, F., Komorowski, M., et al. (2019). Guidelines for reinforcement learning in healthcare. Nature Medicine, 25(1), 16–18. https://doi.org/10.1038/s41591-018-0310-5
Gottesman, O., Johansson, F., Komorowski, M., et al. (2019). Guidelines for reinforcement learning in healthcare. Nature Medicine, 25(1), 16–18. https://doi.org/10.1038/s41591-018-0310-5
Kozhimannil, K. B., Hung, P., Henning-Smith, C., Casey, M. M., & Prasad, S. (2018). Association between loss of hospital-based obstetric services and birth outcomes in rural counties in the United States. JAMA, 319(12), 1239–1247. https://doi.org/10.1001/jama.2018.1830
Li, N., Pham, T., Cheng, C., et al. (2024). Blood demand forecasting and supply management: An analytical assessment of key studies utilizing novel computational techniques. Transfusion Medicine Reviews. https://doi.org/10.1016/j.tmrv.2023.150768
Li, N., Pham, T., Cheng, C., et al. (2024). Blood demand forecasting and supply management: An analytical assessment of key studies utilizing novel computational techniques. Transfusion Medicine Reviews. https://doi.org/10.1016/j.tmrv.2023.150768
MacDorman, M. F., Thoma, M. E., Declercq, E., & Howell, E. A. (2021). Racial and ethnic disparities in maternal mortality in the United States using enhanced vital records. American Journal of Public Health, 111(9), 1673–1681. https://doi.org/10.2105/AJPH.2021.306375
MacDorman, M. F., Thoma, M. E., Declercq, E., & Howell, E. A. (2021). Racial and ethnic disparities in maternal mortality in the United States using enhanced vital records, 2016–2017. American Journal of Public Health, 111(9), 1673–1681. https://doi.org/10.2105/AJPH.2021.306375
MacDorman, M. F., Thoma, M. E., Declercq, E., & Howell, E. A. (2021). Racial and ethnic disparities in maternal mortality in the United States using enhanced vital records, 2016–2017. American Journal of Public Health, 111(9), 1673–1681. https://doi.org/10.2105/AJPH.2021.306375
Niakan, P. B., Keramatpour, M., Afshar-Nadjafi, B., & Komijan, A. R. (2024). An integrated supply chain model for predicting demand and supply and optimizing blood distribution. Logistics, 8(4), 134. https://doi.org/10.3390/logistics8040134
Niakan, P. B., Keramatpour, M., Afshar-Nadjafi, B., & Komijan, A. R. (2024). An integrated supply chain model for predicting demand and supply and optimizing blood distribution. Logistics, 8(4), 134. https://doi.org/10.3390/logistics8040134
Niakan, P. B., Keramatpour, M., Afshar-Nadjafi, B., & Komijan, A. R. (2024). An integrated supply chain model for predicting demand and supply and optimizing blood distribution. Logistics, 8(4), 134. https://doi.org/10.3390/logistics8040134
Rajkomar, A., Oren, E., Chen, K., et al. (2018). Scalable and accurate deep learning with electronic health records. npj Digital Medicine, 1, 18. https://doi.org/10.1038/s41746-018-0029-1
Rajkomar, A., Oren, E., Chen, K., et al. (2018). Scalable and accurate deep learning with electronic health records. npj Digital Medicine, 1, 18. https://doi.org/10.1038/s41746-018-0029-1
Rajkomar, A., Oren, E., Chen, K., et al. (2018). Scalable and accurate deep learning with electronic health records. npj Digital Medicine, 1, 18. https://doi.org/10.1038/s41746-018-0029-1
Robins, J. M., Hernán, M. A., & Brumback, B. (2000). Marginal structural models and causal inference in epidemiology. Epidemiology, 11(5), 550–560. https://doi.org/10.1097/00001648-200009000-00011
Robins, J. M., Hernán, M. A., & Brumback, B. (2000). Marginal structural models and causal inference in epidemiology. Epidemiology, 11(5), 550–560. https://doi.org/10.1097/00001648-200009000-00011
Robins, J. M., Hernán, M. A., & Brumback, B. (2000). Marginal structural models and causal inference in epidemiology. Epidemiology, 11(5), 550–560. https://doi.org/10.1097/00001648-200009000-00011
Saillant, N. N., & colleagues. (2022). The national blood shortage—An impetus for change. Annals of Surgery, 275(4), 641–643. https://doi.org/10.1097/SLA.0000000000005393
Saillant, N. N., et al. (2022). The national blood shortage—An impetus for change. Annals of Surgery, 275(4), 641–643. https://doi.org/10.1097/SLA.0000000000005393
Venkatesh, K. K., Strauss, R. A., Grotegut, C. A., et al. (2020). Machine learning and statistical models to predict postpartum hemorrhage. Obstetrics & Gynecology, 135(4), 935–944. https://doi.org/10.1097/AOG.0000000000003759
Venkatesh, K. K., Strauss, R. A., Grotegut, C. A., et al. (2020). Machine learning and statistical models to predict postpartum hemorrhage. Obstetrics & Gynecology, 135(4), 935–944. https://doi.org/10.1097/AOG.0000000000003759
Venkatesh, K. K., Strauss, R. A., Grotegut, C. A., et al. (2020). Machine learning and statistical models to predict postpartum hemorrhage. Obstetrics & Gynecology, 135(4), 935–944. https://doi.org/10.1097/AOG.0000000000003759