Modelling and forecasting daily surgical case volume using time series analysis

Area of Science:

• Healthcare Operations Research
• Applied Statistics

Background:

• Hospitals face challenges in advance nursing staff scheduling due to unpredictable daily surgical case volumes.
• Surgical demand is influenced by patient needs, physician availability, and temporal fluctuations.

Purpose of the Study:

• To forecast daily surgical case volumes using time series analysis.
• To support robust staff scheduling and labor expense estimation in surgical centers.

Main Methods:

• Utilized historical surgical volume data from a Level 1 Trauma Centre.
• Developed and evaluated a statistical prediction model using Seasonal Autoregressive Integrated Moving Average (SARIMA) modeling.
• Applied time series analysis to predict short-term daily surgical demand.

Main Results:

• The SARIMA model provides accurate short-term forecasts of daily surgical demand.
• The model can estimate surgical case volumes 2-4 weeks in advance.
• Forecasts support more reliable and robust staff scheduling.

Conclusions:

• Time series analysis, specifically SARIMA modeling, is a valuable tool for predicting surgical case volumes.
• Accurate demand forecasting improves operational efficiency and staff management in surgical settings.
• This approach aids in optimizing resource allocation and reducing labor costs.