Scholarlink

Hospital systems have been dealing with a significant increase in patients due to various events, such as seasonal surges or health crises. Despite the high demand for care, hospitals, especially emergency departments (EDs), must provide medical treatment to all patients. However, this surge often results in longer patient stays and overcrowding in EDs. To alleviate this issue, hospital managers must predict patient arrivals, for assessing ED overcrowding and managing medical resources effectively (allocation, planning, utilization rates). For that, the ability to forecast the number of patients likely to arrive at EDs is crucial for resource management and triage process optimization. This article explores the use of time series prediction models, including ARIMA and XGBoost, to forecast the arrivals of patients in EDs. As such, to improve the accuracy of the model, we added the weather time to our features since there are some studies claim that weather and temperature can affect the emergence or transmission of seasonal diseases. The results show that these techniques can provide accurate forecasts, thereby aiding in the planning and rapid response of healthcare systems.

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

Forecasting Patient Arrivals in Emergency Departments Using Time Series Prediction Models: A Research at a Tunisian Emergency Department

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Yosra Jmal,
  • Slim Yaacoub

摘要

Hospital systems have been dealing with a significant increase in patients due to various events, such as seasonal surges or health crises. Despite the high demand for care, hospitals, especially emergency departments (EDs), must provide medical treatment to all patients. However, this surge often results in longer patient stays and overcrowding in EDs. To alleviate this issue, hospital managers must predict patient arrivals, for assessing ED overcrowding and managing medical resources effectively (allocation, planning, utilization rates). For that, the ability to forecast the number of patients likely to arrive at EDs is crucial for resource management and triage process optimization. This article explores the use of time series prediction models, including ARIMA and XGBoost, to forecast the arrivals of patients in EDs. As such, to improve the accuracy of the model, we added the weather time to our features since there are some studies claim that weather and temperature can affect the emergence or transmission of seasonal diseases. The results show that these techniques can provide accurate forecasts, thereby aiding in the planning and rapid response of healthcare systems.