@Article{info:doi/10.2196/63765,
author="Acosta-Perez, Fernando
and Boutilier, Justin
and Zayas-Caban, Gabriel
and Adelaine, Sabrina
and Liao, Frank
and Patterson, Brian",
title="Toward Real-Time Discharge Volume Predictions in Multisite Health Care Systems: Longitudinal Observational Study",
journal="J Med Internet Res",
year="2025",
month="Apr",
day="30",
volume="27",
pages="e63765",
keywords="discharge; machine learning; predict; capacity management; discharge predictions; predictive modeling; emergency department; hospital admission; hospital data",
abstract="Background: Emergency department (ED) admissions are one of the most critical decisions made in health care, with 40{\%} of ED visits resulting in inpatient hospitalization for Medicare patients. A main challenge with the ED admissions process is the inability to move patients from the ED to an inpatient unit quickly. Identifying hospital discharge volume in advance may be valuable in helping hospitals determine capacity management mechanisms to reduce ED boarding, such as transferring low-complexity patients to neighboring hospitals. Although previous research has studied the prediction of discharges in the context of inpatient care, most of the work is on long-term predictions (ie, discharges within the next 24 to 48 hours) in single-site health care systems. In this study, we approach the problem of inpatient discharge prediction from a system-wide lens and evaluate the potential interactions between the two facilities in our partner multisite system to predict short-term discharge volume. Objective: The objective of this paper was to predict discharges from the general care units within a large tertiary teaching hospital network in the Midwest and evaluate the impact of external information from other hospitals on model performance. Methods: We conducted 2 experiments with 174,799 discharge records from 2 hospitals. In Experiment 1, we predicted the number of discharges across 2 time points (within the hour and the next 4 hours) using random forest (RF) and linear regression (LR) models. Models with access to internal hospital data (ie, system-agnostic) were compared with models with access to additional data from the other hospitals in the network (ie, system-aware). In Experiment 2, we evaluated the performance of an RF model to predict afternoon discharges (ie, 12 PM to 4 PM) 1 to 4 hours in advance. Results: In Experiment 1 and Hospital 1, RF and LR models performed equivalently, with R2 scores varying from 0.76 (hourly) to 0.89 (4 hours). In Hospital 2, the RF model performed best, with scores varying from 0.68 (hourly) to 0.84 (4 hours), while scores for LR models ranged from 0.63 to 0.80. There was no significant difference in performance between a system-aware approach and a system-agnostic one. In experiment 2, the mean absolute percentage error increased from 11{\%} to 16{\%} when predicting 4 hours in advance relative to zero hours in Hospital 1 and from 24{\%} to 35{\%} in Hospital 2. Conclusions: Short-term discharges in multisite hospital systems can be locally predicted with high accuracy, even when predicting hours in advance. ",
issn="1438-8871",
doi="10.2196/63765",
url="https://www.jmir.org/2025/1/e63765",
url="https://doi.org/10.2196/63765"
}