Evaluating the Accuracy of Emergency Department Triage Nurses in Predicting Patient Admissions: retrospective, large-sample evidence from a community ED
Accepted for Publication at Western Journal of Emergency Medicine, 2025
Note: This is a preprint of an article that has been accepted for publication in the Western Journal of Emergency Medicine. The final version will be available in the near future.
For presentation at the 24th International Conference on Emergency Medicine (ICEM) in Montreal, Canada, May 2025.
Abstract
Objective: Emergency department (ED) flow could be improved with quicker disposition decisions. One possible way to expedite decisions is for triage nurses to make predictions about whether patients require admission to hospital. The information contained in these predictions could be useful for disposition planning and for physician decision making. Previous studies make use of prospective designs that introduce Hawthorne effects and have demonstrated mixed evidence on whether triage nurse predictions are accurate. We examined the accuracy of triage nurse predictions for patient admission in a southeastern Ontario ED site.
Methods: We examined a retrospective sample of 134,891 visits to an ED in Ontario from March 2019 to July 2024. Triage nurses made predictions about admission to hospital for these visits, from which we estimated measures of specificity, sensitivity, positive predictive value, negative predictive value, accuracy, and $F_1$ scores.
Results: Of 134,891 visits, 13.7% resulted in hospital admission. We found the accuracy of the nurses in predicting admission to be 85.8% (95CI: 85.7, 86.1), while overall sensitivity was 36.6% (95CI: 35.9, 37.3) and specificity was 93.7% (95CI: 93.5, 93.8). The positive predictive value of admission was 47.9% (95CI: 47.1, 48.7) and the negative predictive value of admission was 90.3% (95CI: 90.1, 90.5). F1 scores were 0.415. These results were relatively stable over time, though there was notable variation in prediction ability between nurses. We also report that some presenting conditions have relatively higher prediction accuracy than others and that as overall case severity increases, sensitivity increases and specificity decreases.
Conclusions: These results suggest that although nursing staff predictions are insufficient to streamline disposition decisions completely, they could be useful in expediting certain decisions related to hospital admission and resource requirement, improving flow in EDs.