Simulating Emergency Departments Using Generalized Petri Nets

Abstract : Emergency departments (ED) face significant challenges to deliver high quality and timely patient care while facing rising costs. Prediction models in healthcare are becoming a trend allowing healthcare institutions to better manage the flow of patients through the services. In this work, a Generalized Stochastic Petri net (GSPN) simulation engine is used as a simulator (and performance evaluation) and a waiting time prediction model for the ED of Troyes hospital in France. Compared to existing literature, this work puts more emphasis on using features on GSPN (time, hierarchy, concurrency, parallelism) to capture the complex nature of the system. A new concept of real-time estimation of waiting time is presented. We validated the simulation model with a gap less than 10% between real and simulated performances. To the best of our knowledges, this work is the first to use a GSPN model as a management and waiting time’s forecasting tool for emergency departments.