Academic emergency medicine : official journal of the Society for Academic Emergency Medicine
-
Owing to the large number of injury International Classification of Disease-9 revision (ICD-9) codes, it is not feasible to use standard regression methods to estimate the independent risk of death for each injury code. Bayesian logistic regression is a method that can select among a large numbers of predictors without loss of model performance. The purpose of this study was to develop a model for predicting in-hospital trauma deaths based on this method and to compare its performance with the ICD-9-based Injury Severity Score (ICISS). ⋯ A model that incorporates injury interactions had better predictive performance than one based only on individual injuries. A regression approach to predicting injury mortality based on injury ICD-9 codes yields models with better predictive performance than ICISS.
-
The objective was to develop methodology for predicting demand for emergency department (ED) services by characterizing ED arrivals. ⋯ At this facility, demand for ED services was well approximated by a Poisson regression model. The expected arrival rate is characterized by a small number of factors and does not depend on recent numbers of arrivals.
-
Emergency department (ED) length of stay (LOS) impacts patient satisfaction and overcrowding. Laboratory turnaround time (TAT) is a major determinant of ED LOS. The authors determined the impact of a Stat laboratory (Stat lab) on ED LOS. The authors hypothesized that a Stat lab would reduce ED LOS for admitted patients by 1 hour. ⋯ Introduction of a Stat lab dedicated to the ED within the central laboratory was associated with shorter laboratory TATs and shorter ED LOS for admitted patients, by approximately 1 hour.