The TEND (Tomorrow’s Expected Number of Discharges) Model Accurately Predicted the Number of Patients Who Were Discharged from the Hospital the Next Day
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 < 0.0001). 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.
© 2018 Society of Hospital Medicine
Hospitals typically allocate beds based on historical patient volumes. If funding decreases, hospitals will usually try to maximize resource utilization by allocating beds to attain occupancies close to 100% for significant periods of time. This will invariably cause days in which hospital occupancy exceeds capacity, at which time critical entry points (such as the emergency department and operating room) will become blocked. This creates significant concerns over the patient quality of care.
Hospital administrators have very few options when hospital occupancy exceeds 100%. They could postpone admissions for “planned” cases, bring in additional staff to increase capacity, or instigate additional methods to increase hospital discharges such as expanding care resources in the community. All options are costly, bothersome, or cannot be actioned immediately. The need for these options could be minimized by enabling hospital administrators to make more informed decisions regarding hospital bed management by knowing the likely number of discharges in the next 24 hours.
Predicting the number of people who will be discharged in the next day can be approached in several ways. One approach would be to calculate each patient’s expected length of stay and then use the variation around that estimate to calculate each day’s discharge probability. Several studies have attempted to model hospital length of stay using a broad assortment of methodologies, but a mechanism to accurately predict this outcome has been elusive1,2 (with Verburg et al.3 concluding in their study’s abstract that “…it is difficult to predict length of stay…”). A second approach would be to use survival analysis methods to generate each patient’s hazard of discharge over time, which could be directly converted to an expected daily risk of discharge. However, this approach is complicated by the concurrent need to include time-dependent covariates and consider the competing risk of death in hospital, which can complicate survival modeling.4,5 A third approach would be the implementation of a longitudinal analysis using marginal models to predict the daily probability of discharge,6 but this method quickly overwhelms computer resources when large datasets are present.
In this study, we decided to use nonparametric models to predict the daily number of hospital discharges. We first identified patient groups with distinct discharge patterns. We then calculated the conditional daily discharge probability of patients in each of these groups. Finally, these conditional daily discharge probabilities were then summed for each hospital day to generate the expected number of discharges in the next 24 hours. This paper details the methods we used to create our model and the accuracy of its predictions.
