Predicting daily visits to a walk-in clinic and emergency department using calendar and weather data

We studied the association between calendar and weather variables and daily unscheduled patient volume in a walk-in clinic and emergency department. Calendar variables (season, week of month, day of week, holidays, and federal check-delivery days) and weather variables (high temperature and snowfall) forecasted clinic volume, explaining 84% of daily variance and 44% of weekday variance. Staffing according to predicted volume could have decreased overstaffing from 59% to 15% of days, but would have increased understaffing from 2% to 18% of days. Models using calendar and weather data that forecast local utilization may help to schedule staffing for walk-in clinics and emergency departments more efficiently.