EURO 2025 Leeds
Abstract Submission

3139. An Artificial Intelligence and Simulation Framework for Upgrading Capability Management of Radiology Departments in Seasonal Respiratory Diseases

Invited abstract in session MD-13: Pandemics and epidemics, stream OR in Healthcare (ORAHS).

Monday, 14:30-16:00
Room: Clarendon SR 1.01

Authors (first author is the speaker)

1. Alexandros Konios
Nottingham Trent University
2. Miguel Ortíz-Barrios
Universidad de la Costa CUC
3. Sajid Siraj
Leeds University Business School, University of Leeds

Abstract

The seasonal escalation of respiratory illnesses, such as influenza and COVID-19, presents recurring challenges in managing critical healthcare resources. In response, Artificial Intelligence (AI) and simulation technologies are increasingly being used to enhance operational readiness, particularly in radiology units. AI systems excel at integrating vast, real-time datasets to predict patient loads and radiology equipment shortages with high precision (Ali, 2024). Simulation-based technologies can further amplify the AI potential by allowing stakeholders to construct digital replicas—or "digital twins"—of radiology systems. These models enable planners to test various policy scenarios, evaluate surge responses, and optimise workflows. By dynamically adjusting to real-world developments, these integrated AI-simulation frameworks provide the agility and foresight required to manage resource-intensive respiratory conditions, transforming reactive responses into proactive cost-efficient healthcare planning.
This paper integrates AI and Discrete-Event Simulation (DES) to effectively manage radiology equipment capacity during Respiratory Disease Seasons (RDSs). First, we developed an Xtreme Gradient Boost (XGBoost) to predict the radiology unit requirements considering sociodemographic and clinical factors.

Keywords

Status: accepted

Back to the list of papers