EUVIMEDEUVIMED entdecken
Crossref

An Integrated AI-Driven Framework for Maternal Resource Intelligence Shortages Across U.S. Hospital

Integrative Biomedical Research · 01.03.2026 · 10 (1) · 1-12

DOI: 10.25163/biomedical.10110694 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Integrative Biomedical Research, online erschienen am 01.03.2026.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

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.

Zitieren

APA

(2026). An Integrated AI-Driven Framework for Maternal Resource Intelligence Shortages Across U.S. Hospital. Integrative Biomedical Research, 10(1), 1-12. https://doi.org/10.25163/biomedical.10110694

Vancouver

An Integrated AI-Driven Framework for Maternal Resource Intelligence Shortages Across U.S. Hospital. Integrative Biomedical Research. 2026;10(1):1-12. doi:10.25163/biomedical.10110694

BibTeX
@article{euvimed2026,
  title = {An Integrated AI-Driven Framework for Maternal Resource Intelligence Shortages Across U.S. Hospital},
  journal = {Integrative Biomedical Research},
  year = {2026},
  volume = {10},
  number = {1},
  pages = {1--12},
  doi = {10.25163/biomedical.10110694}
}
Kostenlos starten →