Improving patient length-of-stay in emergency department through dynamic resource allocation policies

In this work, we consider the problem of allocating doctors in the ambulatory area of a hospital's emergency department (ED) based on a set of policies. Traditional staffing methods are static, hence do not react well to surges in patient demands. We study strategies that intelligently adjust the number of doctors based on current and historical information about the patient arrival. Our main contribution is our proposed data-driven online approach that performs adaptive allocation by utilizing historical as well as current arrivals by running symbiotic simulation in real-time. We build a simulation prototype that models ED process that is close to real-world with time-varying demand and re-entrant patients. The experimental results show that our approach allows the ED to better cope with demand surges and to meet a service level desired by the hospital.