Assessment of Time-Series Machine Learning Methods for Forecasting Hospital Discharge Volume

Key Points Question What is the performance of a new time-series machine learning method for predicting hospital discharge volume? Findings In this cohort study of daily hospital discharge volumes at 2 academic medical centers (101 867 patient discharges), predictors of discharge volume were well calibrated. These findings were achieved even with shorter training sets and infrequent retraining. Meaning These results appear to demonstrate the feasibility of deploying simple time-series methods to more precisely estimate hospital discharge volumes based on historical data, and may facilitate better matching of resources with clinical volume.