Premium
The TEND (Tomorrow's Expected Number of Discharges) Model Accurately Predicted the Number of Patients Who Were Discharged from the Hospital the Next Day
Author(s) -
Walraven Carl,
Forster Alan J.
Publication year - 2018
Publication title -
journal of hospital medicine
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.128
H-Index - 65
eISSN - 1553-5606
pISSN - 1553-5592
DOI - 10.12788/jhm.2802
Subject(s) - interquartile range , medicine , emergency medicine , covariate , hospital admission , statistics , mathematics
BACKGROUND Knowing the number of discharges that will occur is important for administrators when hospital occupancy is close to or exceeds 100%. This information will facilitate decision making such as whether to bring in extra staff, cancel planned surgery, or implement measures to increase the number of discharges. We derived and internally validated the TEND (Tomorrow's Expected Number of Discharges) model to predict the number of discharges from hospital in the next day. METHODS We identified all patients greater than 1 year of age admitted to a multisite academic hospital between 2013 and 2015. In derivation patients we applied survival‐tree methods to patient‐day covariates (patient age, sex, comorbidities, location, admission urgency, service, campus, and weekday) and identified risk strata having unique discharge patterns. Discharge probability in each risk strata for the previous 6 months was summed to calculate each day's expected number of discharges. RESULTS Our study included 192,859 admissions. The daily number of discharges varied extensively (median 139; interquartile range [IQR] 95‐160; range 39‐214). We identified 142 discharge risk strata. In the validation patients, the expected number of daily discharges strongly predicted the observed number of discharges (adjusted R2 = 89.2%; P < .0001). The relative difference between observed and expected number of discharges was small (median 1.4%; IQR ‐5.5% to 7.1%). CONCLUSION The TEND model accurately predicted the daily number of discharges using information typically available within hospital data warehouses. Further study is necessary to determine if this information improves hospital bed management.