Predicting Hospital Admissions at Emergency Department Triage Using Routine Administrative Data

Abstract

Objectives: To be able to predict, at the time of triage, whether a need for hospital admission exists for emergency department (ED) patients may constitute useful information that could contribute to systemwide hospital changes designed to improve ED throughput. The objective of this study was to develop and validate a predictive model to assess whether a patient is likely to require inpatient admission at the time of ED triage, using routine hospital administrative data.Methods: Data collected at the time of triage by nurses from patients who visited the ED in 2007 and 2008 were extracted from hospital administrative databases. Variables included were demographics (age, sex, and ethnic group), ED visit or hospital admission in the preceding 3 months, arrival mode, patient acuity category (PAC) of the ED visit, and coexisting chronic diseases (diabetes, hypertension, and dyslipidemia). Chi-square tests were used to study the association between the selected possible risk factors and the need for hospital admission. Logistic regression was applied to develop the prediction model. Data were split for derivation (60%) and validation (40%). Receiver operating characteristic curves and goodness-of-fit tests were applied to the validation data set to evaluate the model. Results:Of 317,581 ED patient visits, 30.2% resulted in immediate hospital admission. In the developed predictive model, age, PAC status, and arrival mode were most predictive of the need for immediate hospital inpatient admission. The c-statistic of the receiver operating characteristic (ROC) curve was 0.849 (95% confidence interval [CI] = 0.847 to 0.851). The goodness-of-fit test showed that the predicted patients' admission risks fit the patients' actual admission status well. Conclusions:A model for predicting the risk of immediate hospital admission at triage for all-cause ED patients was developed and validated using routinely collected hospital data. Early prediction of the need for hospital admission at the time of triage may help identify patients deserving of early admission planning and resource allocation and thus potentially reduce ED overcrowding.

Expanding emergency department capacity: a multisite study

“…Our admission rate was similar to that reported in a Canadian study 27 (38% admission rate of ambulance arrivals), but lower than that seen in a study undertaken in Singapore (59% admission rate for ambulance arrivals). 28 The Canadian study further revealed that people arriving to the ED via ambulance had admission odds 3.15-fold those of people arriving via other means. 27 These figures indicate that further identification of specific predictors of admission used to facilitate targeted service delivery and patient flow may be useful.…”

“…Regarding age, several studies have identified an admission rate of approximately 65% for people aged 65 years. 28,29 Within this demographic, higher odds of admission were related to increasing patient age, higher heart rate, lower blood pressure, lower triage score and several chief complaints, such as pneumonia and stroke. 29 Knowing that older people (particularly those arriving via ambulance) comprise a high proportion of and likelihood for admission, it is possible to use this and other predictive information, such as that offered by LaMantia et al, 29 to order an in-patient bed at the point of triage, thus avoiding delays in admission.…”

Design and evaluation of analytical tools for emergency department management based on machine learning techniques

“…Also, a system capable of accurately establishing the probabilities of inpatient admission (hospitalization) for every ED patient right after triage can help streamline operations and establish priorities for clinical personnel, bed managers and supporting personnel. Previous research had shown that clinical triage 1 personnel could not predict the need for inpatient admission with sufficient reliability [21][22][23], however, models with a manageable number of easily-obtainable variables and a simple procedure for calculating the probabilities of admission could be used to aid in this task [24][25][26]. In both cases (ED census forecasts and prediction of probabilities of inpatient admission from the ED) predictive models with varying degrees of sophistication can be developed.…”

“…Examples of these are the total number of pharmacy dispensations in primary care [24] for a given patient, or standardized chronic clinical conditions [25], which are not available in all EDs of specialized care hospitals in real time (or at all). Also, several models relied on variables which were highly specific to a country or a region [25,26], which made them impossible to apply in other regional settings.…”

“…This common representation provides no way of calculating the probability of event. On the other hand, the full regression formula, which is sometimes provided in appendices [25], most often requires laborious calculations. Nomograms are representations of logistic and Cox regression models that allow easy calculations of output probabilities.…”