An Optimization-based Framework to Dynamically Schedule Hospital Beds in a Pandemic

Emerging pandemics and peak infection periods can overwhelm healthcare systems, especially under limited resource availability such as hospital beds, ventilators, and ICU capacity. This strain may lead to elevated mortality rates and increased healthcare costs. In this paper, we present a novel optimization-based framework that dynamically schedules hospital beds to minimize total healthcare costs, primarily composed of patient rejection costs and associated logistical expenses, while operating under strict resource constraints. Our model accounts for multiple sources of bed supply, including standard hospital beds, in-situ hospital beds, and buffer beds, and incorporates flexible resource sharing to better accommodate patient demand. Recognizing the computational complexity of the resulting optimization model, we propose a reformulation that significantly reduces run-time. We also analyze key structural properties and derive optimal solutions under specific conditions. To account for demand uncertainty, we extend the framework by integrating an SEIRD model to simulate patient demand in future pandemics and to inform proactive bed scheduling. To evaluate the practical utility of our approach, we conduct a case study based on the COVID-19 pandemic in the Northern Virginia (NOVA) region. Our results demonstrate that the proposed framework can reduce total healthcare costs by more than 55%, highlighting its potential in guiding resource allocation and preparedness strategies during health crises.