Fourth International Conference on Health Care Systems Engineering

Montreal, 30 May — 1 June 2019

Schedule Authors My Schedule

Emergency medical services

Jun 1, 2019 09:00 AM – 10:30 AM

Location: Room: Marcel Lacoste

3 Presentations

  • 09:00 AM - 09:30 AM

    Using a slotted queueing model to predict the efficacy of Physician absent Emergency Department for rural communities

    • Peter Vanberkel, presenter, Dalhousie University
    • Benjamin Wedge,
    • Alix Carter,
    • Ilze Ziedins,

    Nova Scotia has developed a novel way to manage Emergency Department (ED) patients in rural communities. Staffed by a paramedic and a registered nurse, and overseen by physician via telephone, Collaborative Emergency Centres (CECs) have replaced traditional physician-led EDs overnight. We modeled the performance of CECs using a slotted queuing model to determine how well they perform in larger communities. It is shown that a CEC's success is related to the proportion of demand for primary care appointments compared with the supply of primary care appointments. Furthermore, we show that larger communities employing CECs will experience diminishing returns.

  • 09:30 AM - 10:00 AM

    A Meta Algorithm For Reinforcement Learning: Emergency Medical Service Resource Prioritization Problem in an MCI as an example

    • Kyohong Shin, presenter, KAIST
    • Taesik Lee, KAIST

    We present a finite-horizon Markov Decision Process (MDP) model for a patient prioritization and hospital selection problem, which is a critical decision-making problem in emergency medical service operation. Solving this model requires reinforcement learning (RL) due to its large state space. We propose a novel approach with an aim to significantly enhance the scalability of RL algorithms. Our approach, which we call a State Partitioning and Action Network, SPartAN in short, is a meta-algorithm that offers a framework an RL algorithm can be incorporated into. In this approach, we partition the state space into smaller subspaces to construct a reliable action network in the downstream subspace. This action network is then used in a simulation to approximate values of the upstream subspace. Using temporal difference learning as an example RL algorithm, we show that SPartAN is able to reliably derive a high quality policy solution, thereby opening opportunities to solve many practical MDP models in healthcare system problem.

  • 10:00 AM - 10:30 AM

    A Realistic Simulation Model of Montreal Emergency Medical Services

    • Gabriel Lavoie, presenter, Polytechnique
    • Valérie Bélanger, CIRRELT, HEC Montréal
    • Nadia Lahrichi, Polytechnique Montréal
    • Luc de Montigny, Urgences-santé

    Emergency medical services (EMS) provide pre-hospital care and transportation to hospitals following an emergency call. Some EMS will also offer interhospital transportation services for patients. This paper presents a simulation model based on Urgences-sante, an EMS covering a population of 2.4 million persons in Quebec (Canada). The goal of the simulation tool is to produce a highly realistic model by considering several aspects of EMS often left out in the literature. Those aspects include break management, rerouting, complex priority system and ambulance specialization. The simulation tool allows us to evaluate the impact of new policies regarding some of those aspects on the overall performance of the system. Our results show that this detail-oriented approach can improve performance without requiring major modifications to the system.