Predictive analytics using a novel simulation application: Validation of an effective decision support tool for Emergency Department flow

Objectives: To develop a scalable software application that can predict the effects of operational decisions in a variety of emergency care environments. Validate the ability of the application's core simulation model to recreate and predict site-specific patient flow at both a large academic center and a freestanding ED. Evaluate the utility of the application for use by ED managers to inform operational decisions.

Methods: The application was developed through a public-private partnership between University of Florida Health and Roundtable Analytics, Inc., supported by a National Science Foundation Small Business Technology Transfer (STTR) grant. The core simulation model was parameterized using site-specific data and Monte Carlo studies were performed to validate its ability to predict the effects of management interventions at two EDs. At one ED, the medical director conducted simulation studies to evaluate the sustainability of the current operational strategy and predict the effects of specific interventions. After implementation, the fidelity of the model's predictions was evaluated.

Results: The application was successfully built and deployed at two qualitatively distinct EDs. When equipped with site-specific parameters, the model accurately recreated the each ED's throughput and faithfully predicted the effects of specific management interventions. One ED model also identified a point when increasing arrivals dictate that the current operational strategy will become less effective than an alternative strategy. As actual arrivals approached this point, decision-makers used the application to simulate a variety different interventions and incorporated this information in their decision to implement a new strategy. The observed outcomes resulting from this intervention fell within the range of predictions from the model. An online demonstration of this application is available at http://solutions.roundtableanalytics.com/Emergency-Department-Simulation/

Conclusion: This application overcomes technical barriers to entry that have kept simulation modeling out of the hands of key decision-makers. Using this technology, ED managers with no programming experience were able to conduct simulation studies customized to their ED. Moreover, the incorporation of these results by decision-makers had a direct positive impact on ED operations. The effective use of simulation modeling promises to replace inefficient trial-and-error approaches and become a useful and accessible tool for healthcare managers challenged to make operational decisions in environments of increasingly scarce resources.