An Interactive Decision-Support Dashboard for Optimal Hospital Capacity Management

TL;DR

The paper tackles the problem of managing hospital capacity during unpredictable demand surges by presenting an interactive decision-support dashboard that combines real-time data, forecasting, and optimization. It adapts a robust mixed-integer optimization framework to support surge-level decisions and inter-hospital transfers, while providing a user-friendly interface designed through participatory design with hospital administrators. The tool was implemented and deployed in the Johns Hopkins Health System during the COVID-19 surge, demonstrating practical utility, rapid scenario analysis, and actionable insights for leadership. The work demonstrates how tightly integrated forecasting, optimization, and visualization can aid proactive capacity planning and is made broadly accessible through public code and documentation for broader adoption.

Abstract

Data-driven optimization models have the potential to significantly improve hospital capacity management, particularly during demand surges, when effective allocation of capacity is most critical and challenging. However, integrating models into existing processes in a way that provides value requires recognizing that hospital administrators are ultimately responsible for making capacity management decisions, and carefully building trustworthy and accessible tools for them. In this study, we develop an interactive, user-friendly, electronic dashboard for informing hospital capacity management decisions during surge periods. The dashboard integrates real-time hospital data, predictive analytics, and optimization models. It allows hospital administrators to interactively customize parameters, enabling them to explore a range of scenarios, and provides real-time updates on recommended optimal decisions. The dashboard was created through a participatory design process, involving hospital administrators in the development team to ensure practical utility, trustworthiness, transparency, explainability, and usability. We successfully deployed our dashboard within the Johns Hopkins Health System during the height of the COVID-19 pandemic, addressing the increased need for tools to inform hospital capacity management. It was used on a daily basis, with results regularly communicated to hospital leadership. This study demonstrates the practical application of a prospective, data-driven, interactive decision-support tool for hospital system capacity management.

Figures (11)

• Figure 1: The interactive capacity management dashboard has three main components: "Data Inputs", "Models", and "Dashboard". The input data (green) is collected through EHR and HIS and fed into behind-the-scenes models shown in purple (the forecasts and optimization models). The user interacts with the tool through the Dashboard component (red) -- the focus of this work --and can investigate and examine the outcomes including recommended decisions and impact on operations (orange).
• Figure 2: Overview of the project timeline with key phases and events. The timeline is overlayed over the total JHHS COVID-19 patient occupancy for context. An early version of the model was developed in April 2020. Initial work towards a dashboard catered to JHHS began in August 2020, with active development and use of the dashboard beginning in November 2020.
• Figure 3: User interface to interactively customize the modular optimization model and data inputs. The description and possible values for each option are listed in \ref{['tab:params']}. When a user presses "Update", the new customized optimization model runs on the backend and all visualizations are updated with the new results.
• Figure 4: Overview of hospital census and admissions with and without transfers. Figures are screenshots of the visualizations taken from the dashboard. (a) Shows the projected COVID-19 census over time for each hospital, both with (dark curves) and without (light curves) patient transfers/diversions for each hospital, along with capacity levels. (b) Displays the COVID-19 patient admissions over time, with and without the recommended transfers (dark and light curves, respectively).
• Figure 5: Screenshots of the visualizations for recommended hospital capacity and surge levels over time. (a) Highlights the surge level required for each hospital over time in a simplified way, which allows the hospitals to plan their surge capacity opening strategies. (b) Shows the required capacity for each hospital in more detail.