Predicting case volume from the accumulating elective operating room schedule facilitates staffing improvements

Area of Science:

• Healthcare Operations Research
• Surgical Workflow Optimization
• Predictive Analytics in Medicine

Background:

• Accurate operating room (OR) demand forecasting is challenging due to late scheduling, hindering timely staffing adjustments.
• The elective surgery schedule's potential for early demand prediction was investigated to facilitate proactive staffing.
• A hypothesis was formed that accumulating booking data could predict final case volume sufficiently in advance for staffing optimization.

Purpose of the Study:

• To develop and validate a predictive model for final operating room case volume using the accumulating elective schedule.
• To determine how far in advance accurate predictions of surgical case demand can be made.
• To assess the model's utility in enabling proactive staffing adjustments for nursing, ancillary, and anesthesia services.

Main Methods:

• A dataset of 146 surgical days was compiled, including 30 prior days of booking history for each.
• A prediction model was created by extrapolating the fraction of total cases booked daily and employing linear regression models for each of the preceding 30 days.
• Model predictions were validated against actual surgical case volumes.

Main Results:

• The elective surgery schedule averaged an accumulation of approximately three cases per day, with a final mean daily volume of 117 ± 12 cases.
• The predictive model accurately estimated final case counts within 8.27 cases up to 14 days before the surgery date.
• Within 7 days of the surgery date, the model predicted the case count within seven cases 80% of the time.
• Similar predictive performance was observed when the model was replicated at a smaller hospital.

Conclusions:

• The elective surgery schedule serves as a reliable predictor of final case volume several weeks prior to the surgical date.
• Implementing this predictive model allows for the early identification of high or low surgical volume days.
• Managers can proactively adjust staffing levels for nursing, ancillary services, and anesthesia to better match predicted demand, improving operational efficiency.