ORAHS2024
Abstract Submission

187. Improving Emergency Department services scheduling through a hybrid Discrete Event Simulation and AI approach: an applied case study to the University Hospital of Bologna

Contributed abstract in session FA-5: Emergency Department /3, stream Regular talks.

Friday, 9:20-10:30
Room: Room S6

Authors (first author is the speaker)

1. Luca Zattoni
DEI, University of Bologna
2. Andrea Eusebi
DEI, University of Bologna
3. Cristiano Fabbri
DEI, University of Bologna
4. Marco Leonessi
IRCCS Azienda Ospedaliero Universitaria di Bologna
5. Enrico Malaguti
DEI, University of Bologna
6. Paolo Tubertini
IRCCS Azienda Ospedaliero Universitaria di Bologna

Abstract

Emergency Department (ED) plays a central role in many hospital contexts: with the aging of population and the increasing request for emergency services, the pressure on this structure and its staff has increased as well. While this represents a challenge, it's also an opportunity to highlight the potential impact of an effective quantitative-based decision making. Length of stay (LOS) is often used as a measure of the ED performance, reflecting the patient's experience. High LOS values might be considered as a symptom of overcrowding: this is one of the main problems in ED, as it could result in discomfort as well as aggravating patient conditions, and its causes usually lie in oversaturation of resources and inefficient services scheduling. In the scientific literature, simulation methods have been proved to be an effective tool to evaluate the ED dynamics, capable of considering the high variability in patients' emergency pathways, due to clinical criteria and required services. We propose a decision support framework, using a hybrid Discrete Event Simulation and Deep Learning paradigm, that aims to prevent overcrowding through dynamic queue management. By exploiting both structured and textual patient data, a predictive model is used to estimate the pathways development. This can be given as an input to the simulation replicating the behaviour of the system, so as to evaluate different policies for scheduling the required services, while considering patients' priorities.

Keywords

Status: accepted


Back to the list of papers