P112: Predicting patient admission from the emergency department using triage administrative data
Open accessAbstract
Introduction: Emergency department (ED) over-crowding and increased wait times are a growing problem. Many interventions have been proposed to decrease patient length of stay and increase patient flow. Early disposition planning is one method to accomplish this goal. In this study we developed statistical models to predict patient admission based on ED administrative data. The objective of this study was to predict patient admission early in the visit with goal of preparation of the acute care bed and other resources. Methods: Retrospective administrative ED data from the Thunder Bay Regional Health Sciences Centre was obtained for the period May 2014 to April 2015. Data were divided into training and testing groups with 80% of data used to train the statistical models. Logistic regression models were developed using administrative variables (i.e., age, sex, mode of arrival, and triage level). Model accuracy was evaluated using sensitivity, specificity, and area under the curve measures. To predict hourly bed requirements, the probability of admission was summed to calculate a pooled bed requirement estimate. The estimated hourly bed requirement was then compared to the historical hourly demand. Results: The logistic regression models had a sensitivity of 23%, specificity of 97%, and an area under the curve of 0.78. Although, admission prediction for a particular individual was satisfactory, the hourly pooled probabilities showed better results. The predicted hourly bed requirements were close to historical demand for beds when compared. Conclusion: I have shown that the number of acute care beds required on an hourly basis can be predicted using triage administrative data. Early admission bed planning would allow resources to be managed more effectively. In addition, during periods of hospital over capacity, managers would be able to prioritize transfers and discharges based on early estimates of ED demand for beds.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Most prior models predicting hospital admission at ED triage include only information collected at triage such as demographics, vital signs, chief complaint, nursing notes, and early diagnostics.
“Most models only include information collected at triage such as demographics, vital signs, chief complaint, nursing notes, and early diagnostics [11,14–19]”
From Predicting hospital admission at emergency department triage using machine learning (2018) · cites this paper as [18]
Logistic regression and Naive Bayes are commonly used, with few studies using more complex algorithms like random-forests, artificial neural networks, and support vector machines.
“Logistic regression and Naive Bayes are commonly used [9,11,16,18–22], with few studies using more complex algorithms like random-forests, artificial neural networks, and support vector machines [12,15,17].”
From Predicting hospital admission at emergency department triage using machine learning (2018) · cites this paper as [18]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cited by
Sorted by citations
Predicting hospital admission at emergency department triage using machine learning
Hong, W. S., Haimovich, A. D., & Taylor, R. A. (2018) · PLOS ONE · doi:10.1371/journal.pone.0201016 · Cited by 326 · see citing works
Predicting Hospital Admissions to Reduce Crowding in the Emergency Departments
Cusidó, J., Comalrena, J., Alavi, H., & Llunas, L. (2022) · Applied Sciences · doi:10.3390/app122110764 · Cited by 21 · see citing works
- Authors
- Savage, D. W., Weaver, B., & Wood, D.
- Affiliations
- NOSM University (CA)
- Corresponding author
- Savage, D.W.
- Venue
- CJEM
- Published
- 2017-05
- Volume
- 19
- Issue
- S1
- Pages
- S116
- ISSN
- 1481-8035 (ISSN-L)
- 1481-8043
- OpenAlex
- W2615695224
- Cited by
- 2
- References
- 0
- Citations by year
- 2022: 1 · 2018: 1
- Type
- conference abstract
- Language
- en
- Open access
- bronze
- doi.org
- Locations
- Canadian Journal of Emergency Medicine (publishedVersion)
- Topics
- Health Sciences › Medicine › Emergency Medicine › Emergency and Acute Care Studies
- Health Sciences › Health Professions › Emergency Medical Services › Healthcare Operations and Scheduling Optimization
- Health Sciences › Health Professions › Health Information Management › Artificial Intelligence in Healthcare
- Keywords
- emergency department overcrowding, patient flow, hospital bed management, emergency department waiting times, logistic regression prediction model
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
