ABSTRACT
At the onset of the COVID‐19 pandemic, hospitals were in dire need of data‐driven analytics to provide support for critical, expensive, and complex decisions. Yet, the majority of analytics being developed were targeted at 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, data‐limited environment, such as a novel pandemic. The product of this research is a workload prediction and decision support tool to provide mission‐critical, actionable information for individual hospitals. Our framework forecasts time‐varying patient workload and demand for critical resources by integrating 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. Both components employ adaptive tuning to account for hospital‐dependent, time‐varying parameters that provide consistently accurate predictions by dynamically learning the impact of latent changes in system dynamics. Our decision support system is designed to be portable and easily implementable across hospital data systems for expeditious expansion and deployment. This work was contextually grounded in close collaboration with IU Health, the largest health system in Indiana, which has 18 hospitals serving over one million residents. Our initial prototype was implemented in April 2020 and has supported managerial decisions, from the operational to the strategic, across multiple functionalities at IU Health.
ABSTRACT
At the onset of the COVID-19 pandemic, hospitals were in dire need of data-driven analytics to provide support for critical, expensive, and complex decisions. Yet, the majority of analytics being developed were targeted at 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, data-limited environment, such as a novel pandemic. The product of this research is a workload prediction and decision support tool to provide mission-critical, actionable information for individual hospitals. Our framework forecasts time-varying patient workload and demand for critical resources by integrating 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. Both components employ adaptive tuning to account for hospital-dependent, time-varying parameters that provide consistently accurate predictions by dynamically learning the impact of latent changes in system dynamics. Our decision support system is designed to be portable and easily implementable across hospital data systems for expeditious expansion and deployment. This work was contextually grounded in close collaboration with IU Health, the largest health system in Indiana, which has 18 hospitals serving over one million residents. Our initial prototype was implemented in April 2020 and has supported managerial decisions, from the operational to the strategic, across multiple functionalities at IU Health. This article is protected by copyright. All rights reserved
ABSTRACT
Introduction When the hospital census is high, perioperative medical directors or operating room (OR) managers may need to consider postponing some surgical cases scheduled to be performed within the next three workdays. This scenario has arisen at hospitals in regions with large increases in admissions due to coronavirus disease 2019 (COVID-19). We compare summary measures for hospital length of stay (LOS) to guide the OR manager having to decide which cases may need to be postponed to ensure a sufficient reserve of available inpatient beds. Methods We studied the 1,201,815 ambulatory and 649,962 inpatient elective cases with a major therapeutic procedure performed during 2018 at all 412 non-federal hospitals in Florida. The data were sorted by the hospital, and then by procedure category. Statistical comparisons of LOS were made pairwise among all procedure categories with at least 100 cases at (the) each hospital, using the chi-square test (LOS ≤ 1 day versus LOS > 1 day), Student's t-test with unequal variances, and the Wilcoxon-Mann-Whitney test. The comparisons among the three tests then were repeated having sorted the data by procedure category and making statistical comparisons among all hospitals with at least 100 cases for the procedure category. Results Whether using a criterion for statistical significance of P < 0.05 or P < 0.01, and whether compared with Student's t-test with unequal variances or Wilcoxon-Mann-Whitney test, the chi-square test had greater odds (i.e., greater statistical power) to detect differences in LOS (all four with P < 0.0001 and all 95% lower confidence limits for odds ratios ≥ 3.00). The findings were consistent when the data, first sorted by procedure category and then by probability distributions of LOS, were compared between hospitals (all P < 0.0001 and the 95% lower confidence limits for odds ratio ≥ 3.72). Conclusions For purposes of comparing procedure categories pairwise at the same hospital, there was no loss of information by summarizing the probability distributions using single numbers, the percentages of cases among patients staying longer than overnight. This finding substantially simplifies the mathematics for constructing dashboards or summaries of OR information system data to help the perioperative OR manager or medical director decide which cases may need to be postponed, when the hospital census is high, to provide a sufficient reserve of inpatient hospital beds.