Operations (Management) Warp Speed: Parsimonious Design for Rapid Deployment of Hospital Prediction and Decision Support Framework during a Pandemic
47 Pages Posted: 1 Apr 2021
Date Written: February 28, 2021
At the onset of the COVID-19 pandemic, hospitals were in dire need of data-driven analytics to provide support for critical, expensive, and challenging decisions. Yet, the majority of analytics being developed were targeted toward state- and national-level policy decisions, with little availability of actionable information to support tactical and operational decision making and execution at the hospital level. To fill this gap, we developed a multi-method framework leveraging a parsimonious design philosophy that allows for rapid deployment of high-impact predictive and prescriptive analytics in a time-sensitive, dynamic, limited data environment such as a novel pandemic. Our framework integrates disease progression models tailored to data availability during different stages of the pandemic with a stochastic network model of patient movements among units within individual hospitals to forecast time-varying patient workload and demand for critical resources. Both components employ adaptive tuning to account for hospital-dependent, time-varying parameters that provide consistently accurate predictions as changes in system dynamics are learned over time. The product of this research is a workload prediction and decision support framework customized to individual hospital that specifically targets actionable information based on hospital needs. Yet, by design, our framework is portable across hospital data-systems and easily implementable for expeditious expansion. This work was contextually grounded in close collaboration with IU Health, the largest health system in Indiana with 18 hospitals serving over 1 million residents. Since April 2020, we have implemented our framework to support decisions from operational to strategic made by multiple departments at IU Health as well as the executive leadership team during the course of the COVID-19 pandemic.
Keywords: COVID-19, pandemic, workload prediction, machine learning, stochastic model, queueing
Suggested Citation: Suggested Citation