A Comparison of Time-Series Predictions for Healthcare Emergency Department Indicators and the Impact of COVID-19

Across the world, healthcare systems are under stress and this has been hugely exacerbated by COVID pandemic. Key Performance Indicators (KPIs), usually in form of time-series data, used to help manage that stress. Making reliable predictions these indicators, particularly for emergency departments (ED), can facilitate acute unit planning, enhance quality care optimise resources. This motivates models forecast relevant KPIs paper addresses need comparing Autoregressive Integrated Moving Average (ARIMA) method, a purely statistical model, Prophet, decomposable forecasting model based on trend, seasonality holidays variables, General Regression Neural Network (GRNN), machine learning model. The dataset analysed is formed four hourly valued indicators from UK hospital: Patients Department; Number Attendances; Unallocated with DTA (Decision Admit); Medically Fit Discharge. Typically, data exhibit regular patterns seasonal trends be impacted external factors such as weather or major incidents. pandemic an extreme instance latter behaviour sample changed dramatically. capacity quickly adapt changes crucial factor shows better results GRNN both accuracy reliability.