Scholarlink

Emergency Departments (EDs) are critical yet complex areas in healthcare, where optimizing staff configurations is essential to reduce patient waiting times and improve efficiency. This study presents a methodology that combines Agent-Based Simulation (ABS) with the Montecarlo Clustering Search Algorithm (MCSA) to address the combinatorial challenge of allocating medical staff—doctors, nurses, and technicians—based on patient arrival patterns and acuity levels. The optimization process is guided by Key Performance Indicators (KPIs), particularly patient Length of Stay (LoS), ensuring staff allocations align with real-time demand without affecting resources in other hospital areas. The integrated approach enables realistic modeling of ED operations while efficiently exploring large solution spaces. Unlike exhaustive methods, MCSA significantly reduces computational time, making it suitable for practical implementation in healthcare settings. The results show that the proposed framework can effectively identify staff configurations that enhance ED performance and support scalable, data-driven decision-making. This contributes to improved patient outcomes and operational balance in high-pressure environments.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Optimization of Emergency Department Staff Configuration Using Montecarlo Clustering Search Algorithm and ABM Simulation

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Maria Harita,
  • Alvaro Wong,
  • Dolores Rexachs,
  • Emilio Luque,
  • Eva Bruballa,
  • Francisco Epelde

摘要

Emergency Departments (EDs) are critical yet complex areas in healthcare, where optimizing staff configurations is essential to reduce patient waiting times and improve efficiency. This study presents a methodology that combines Agent-Based Simulation (ABS) with the Montecarlo Clustering Search Algorithm (MCSA) to address the combinatorial challenge of allocating medical staff—doctors, nurses, and technicians—based on patient arrival patterns and acuity levels. The optimization process is guided by Key Performance Indicators (KPIs), particularly patient Length of Stay (LoS), ensuring staff allocations align with real-time demand without affecting resources in other hospital areas. The integrated approach enables realistic modeling of ED operations while efficiently exploring large solution spaces. Unlike exhaustive methods, MCSA significantly reduces computational time, making it suitable for practical implementation in healthcare settings. The results show that the proposed framework can effectively identify staff configurations that enhance ED performance and support scalable, data-driven decision-making. This contributes to improved patient outcomes and operational balance in high-pressure environments.