header

Scalable Predictive Analytics for Hospital Resource Allocation and ICU Bed Capacity Optimization During National Public Health Emergencies in the U.S

Authors

  • Sunday Sunday

    Ladoke Akintola University of Technology
    Author
Keywords:
Predictive Analytics, ICU Capacity Optimization, Machine Learning, HealthcareResource Allocation, Public Health Emergencies
Abstract
National public health emergencies consistently expose critical vulnerabilities in healthcareresource allocation, particularly in intensive care unit (ICU) bed capacity management. Existingapproaches treat epidemic forecasting and operational resource planning as disconnectedsequential processes, resulting in reactive rather than proactive capacity decisions. This studyaddresses this gap by developing and validating a scalable predictive analytics framework thatintegrates machine learning-based demand forecasting with optimization-driven allocationmechanisms. The proposed framework combines a LightGBM-based ensemble forecastingmodel with a newsvendor critical fractile allocation policy that incorporates forecast uncertaintydirectly into capacity decisions. Using retrospective COVID-19 data from U.S. hospitals spanning April 2021 to May 2022, the framework achieved 89.4% accuracy in predicting 7-dayICU occupancy, outperforming traditional time-series methods (p < 0.01). The allocation modelmaintained zero shortage periods during validation while reducing capacity overprovisioning by23.7% compared to static budgeting approaches. This study contributes a replicable, decision-theoretically grounded framework that connects epidemic signals to costed capac

 

Cover Image
Downloads
Published
08/15/2026
Issue
Vol. 2 No. 3 (2026): The science post
Section
Articles
License

Copyright (c) 2026 Sunday Sunday (Author)

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

How to Cite

Scalable Predictive Analytics for Hospital Resource Allocation and ICU Bed Capacity Optimization During National Public Health Emergencies in the U.S. (2026). The Science Post, 2(3). https://www.thesciencepostjournal.com/index.php/tsp/article/view/224