Forecasting Patient Census for HCMC
Data-driven Staffing for a Large Hospital
A Carlson Analytics Lab Client Project
For a major hospital and healthcare provider like Hennepin County Medical Center (HCMC), patient care is always top priority. The hospital and its clinics face enormous challenges in delivering complex medical services every day, and in many cases, the stakes could not be higher.
Nurse Staffing is a Complicated and Crucial Task
Pressures come on multiple fronts as HCMC strives to deliver care to patients and also remain financially healthy as an organization. For example, scheduling nurses to staff different care units and shifts is a complicated puzzle for hospital managers. Inadequate staffing could put patients at risk, but overstaffing wastes limited resources. Natural variation in the hospital census—the number of admitted patients needing care—adds to the challenge.
Robust Forecasting Models in a Powerful User Database
Students in the Carlson Analytics Lab worked with HCMC to more accurately forecast patient census across 17 different nursing units. The students built and tested dozens of models combining five years of historical patient census data with data on weather, population, and community events (e.g., professional sports schedules)—external factors that can affect patient counts.
The best performing models were incorporated into an interactive dashboard to help nurse managers make staffing decisions. Designed to align with the existing scheduling process, the dashboard allows managers to optimize nurse staffing to ensure both patient care and operational efficiency.