Clare Allison Parker1, Nan Liu2, Stella Xinzi Wu3, Yuzeng Shen4, Sean Shao Wei Lam5, Marcus Eng Hock Ong6. 1. Duke University School of Medicine, Durham, NC, United States of America. Electronic address: clare.parker@duke.edu. 2. Duke-NUS Medical School, National University of Singapore, Singapore; Health Services Research Centre, Singapore Health Services, Singapore. Electronic address: liu.nan@singhealth.com.sg. 3. Duke-NUS Medical School, National University of Singapore, Singapore. Electronic address: stella.wu@u.duke.nus.edu. 4. Department of Emergency Medicine, Singapore General Hospital, Singapore. Electronic address: shen.yuzeng@singhealth.com.sg. 5. Duke-NUS Medical School, National University of Singapore, Singapore; Health Services Research Centre, Singapore Health Services, Singapore. Electronic address: lam.shao.wei@singhealth.com.sg. 6. Duke-NUS Medical School, National University of Singapore, Singapore; Department of Emergency Medicine, Singapore General Hospital, Singapore. Electronic address: marcus.ong.e.h@singhealth.com.sg.
Abstract
BACKGROUND: Emergency department (ED) overcrowding is a growing international patient safety issue. A major contributor to overcrowding is long wait times for inpatient hospital admission. The objective of this study is to create a model that can predict a patient's need for hospital admission at the time of triage. METHODS: Retrospective observational study of electronic clinical records of all ED visits over ten years to a large urban hospital in Singapore. The data was randomly divided into a derivation set and a validation set. We used the derivation set to develop a logistic regression model that predicts probability of hospital admission for patients presenting to the ED. We tested the model on the validation set and evaluated the performance with receiver operating characteristic (ROC) curve analysis. RESULTS: A total of 1,232,016 visits were included for final analysis, of which 38.7% were admitted. Eight variables were included in the final model: age group, race, postal code, day of week, time of day, triage category, mode of arrival, and fever status. The model performed well on the validation set with an area under the curve of 0.825 (95% CI 0.824-0.827). Increasing age, increasing triage acuity, and mode of arrival via private patient transport were most predictive of the need for admission. CONCLUSIONS: We developed a model that accurately predicts admission for patients presenting to the ED using demographic, administrative, and clinical data routinely collected at triage. Implementation of the model into the electronic health record could help reduce the burden of overcrowding.
BACKGROUND: Emergency department (ED) overcrowding is a growing international patient safety issue. A major contributor to overcrowding is long wait times for inpatient hospital admission. The objective of this study is to create a model that can predict a patient's need for hospital admission at the time of triage. METHODS: Retrospective observational study of electronic clinical records of all ED visits over ten years to a large urban hospital in Singapore. The data was randomly divided into a derivation set and a validation set. We used the derivation set to develop a logistic regression model that predicts probability of hospital admission for patients presenting to the ED. We tested the model on the validation set and evaluated the performance with receiver operating characteristic (ROC) curve analysis. RESULTS: A total of 1,232,016 visits were included for final analysis, of which 38.7% were admitted. Eight variables were included in the final model: age group, race, postal code, day of week, time of day, triage category, mode of arrival, and fever status. The model performed well on the validation set with an area under the curve of 0.825 (95% CI 0.824-0.827). Increasing age, increasing triage acuity, and mode of arrival via private patient transport were most predictive of the need for admission. CONCLUSIONS: We developed a model that accurately predicts admission for patients presenting to the ED using demographic, administrative, and clinical data routinely collected at triage. Implementation of the model into the electronic health record could help reduce the burden of overcrowding.
Authors: Feng Xie; Nan Liu; Stella Xinzi Wu; Yukai Ang; Lian Leng Low; Andrew Fu Wah Ho; Sean Shao Wei Lam; David Bruce Matchar; Marcus Eng Hock Ong; Bibhas Chakraborty Journal: BMJ Open Date: 2019-09-26 Impact factor: 2.692
Authors: Marta Fernandes; Rúben Mendes; Susana M Vieira; Francisca Leite; Carlos Palos; Alistair Johnson; Stan Finkelstein; Steven Horng; Leo Anthony Celi Journal: PLoS One Date: 2020-03-03 Impact factor: 3.240
Authors: Marta Fernandes; Rúben Mendes; Susana M Vieira; Francisca Leite; Carlos Palos; Alistair Johnson; Stan Finkelstein; Steven Horng; Leo Anthony Celi Journal: PLoS One Date: 2020-04-02 Impact factor: 3.240
Authors: Joann G Elmore; Pin-Chieh Wang; Kathleen F Kerr; David L Schriger; Douglas E Morrison; Ron Brookmeyer; Michael A Pfeffer; Thomas H Payne; Judith S Currier Journal: J Med Internet Res Date: 2020-09-10 Impact factor: 5.428