Katie J Walker1, Jirayus Jiarpakdee2, Anne Loupis3, Chakkrit Tantithamthavorn2, Keith Joe4, Michael Ben-Meir5, Hamed Akhlaghi6, Jennie Hutton7, Wei Wang8, Michael Stephenson9, Gabriel Blecher10, Paul Buntine11, Amy Sweeny12, Burak Turhan13. 1. Cabrini Emergency Department, Malvern, Melbourne, Victoria, Australia; Cabrini Institute, Malvern, Melbourne, Victoria, Australia; Casey Emergency Department, Berwick, Melbourne, Victoria, Australia; School of Clinical Sciences at Monash Health, Monash University, Clayton, Melbourne, Victoria, Australia. Electronic address: katie_walker01@yahoo.com.au. 2. Department of Software Systems and Cybersecurity, Monash University, Clayton, Melbourne, Victoria, Australia. 3. Cabrini Institute, Malvern, Melbourne, Victoria, Australia; School of Clinical Sciences at Monash Health, Monash University, Clayton, Melbourne, Victoria, Australia. 4. Cabrini Emergency Department, Malvern, Melbourne, Victoria, Australia; Monash Art, Design and Architecture, Monash University, Caulfield, Melbourne, Victoria, Australia. 5. Cabrini Emergency Department, Malvern, Melbourne, Victoria, Australia; School of Public Health and Preventive Medicine, Monash University, Melbourne, Victoria, Australia. 6. Emergency Department, St Vincent's Hospital, Fitzroy, Melbourne, Victoria, Australia. 7. Emergency Department, St Vincent's Hospital, Fitzroy, Melbourne, Victoria, Australia; Medicine, Dentistry and Health Sciences, University of Melbourne, Parkville, Melbourne, Victoria, Australia. 8. Cabrini Institute, Malvern, Melbourne, Victoria, Australia; Faculty of Medicine, Nursing and Health Sciences, Monash University, Melbourne, Victoria, Australia. 9. Ambulance Victoria, Doncaster, Melbourne, Victoria, Australia; Department of Epidemiology and Preventive Medicine, Monash University, Melbourne, Victoria, Australia; Department of Community Emergency Health and Paramedic Practice, Frankston, Melbourne, Victoria, Australia. 10. Cabrini Emergency Department, Malvern, Melbourne, Victoria, Australia; School of Clinical Sciences at Monash Health, Monash University, Clayton, Melbourne, Victoria, Australia; Monash Medical Centre, Emergency Department, Clayton, Melbourne, Victoria, Australia. 11. Emergency Department, Box Hill Hospital, Eastern Health, Box Hill, Melbourne, Victoria, Australia; Eastern Health Clinical School, Monash University, Box Hill, Melbourne, Victoria, Australia. 12. Emergency Department, Gold Coast University Hospital, Southport, Queensland, Australia; Faculty of Health Sciences and Medicine, Bond University, Robina, Queensland, Australia. 13. Faculty of Information Technology and Electrical Engineering, University of Oulu, Oulu, Finland.
Abstract
STUDY OBJECTIVE: To derive and internally and externally validate machine-learning models to predict emergency ambulance patient door-to-off-stretcher wait times that are applicable to a wide variety of emergency departments. METHODS: Nine emergency departments provided 3 years (2017 to 2019) of retrospective administrative data from Australia. Descriptive and exploratory analyses were undertaken on the datasets. Statistical and machine-learning models were developed to predict wait times at each site and were internally and externally validated. RESULTS: There were 421,894 episodes analyzed, and median site off-load times varied from 13 (interquartile range [IQR], 9 to 20) to 29 (IQR, 16 to 48) minutes. The global site prediction model median absolute errors were 11.7 minutes (95% confidence interval [CI], 11.7 to 11.8) using linear regression and 12.8 minutes (95% CI, 12.7 to 12.9) using elastic net. The individual site model prediction median absolute errors varied from the most accurate at 6.3 minutes (95% CI, 6.2 to 6.4) to the least accurate at 16.1 minutes (95% CI, 15.8 to 16.3). The model technique performance was the same for linear regression, random forests, elastic net, and rolling average. The important variables were the last k-patient average waits, triage category, and patient age. The global model performed at the lower end of the accuracy range compared with models for the individual sites but was within tolerable limits. CONCLUSION: Electronic emergency demographic and flow information can be used to estimate emergency ambulance patient off-stretcher times. Models can be built with reasonable accuracy for multiple hospitals using a small number of point-of-care variables.
STUDY OBJECTIVE: To derive and internally and externally validate machine-learning models to predict emergency ambulance patient door-to-off-stretcher wait times that are applicable to a wide variety of emergency departments. METHODS: Nine emergency departments provided 3 years (2017 to 2019) of retrospective administrative data from Australia. Descriptive and exploratory analyses were undertaken on the datasets. Statistical and machine-learning models were developed to predict wait times at each site and were internally and externally validated. RESULTS: There were 421,894 episodes analyzed, and median site off-load times varied from 13 (interquartile range [IQR], 9 to 20) to 29 (IQR, 16 to 48) minutes. The global site prediction model median absolute errors were 11.7 minutes (95% confidence interval [CI], 11.7 to 11.8) using linear regression and 12.8 minutes (95% CI, 12.7 to 12.9) using elastic net. The individual site model prediction median absolute errors varied from the most accurate at 6.3 minutes (95% CI, 6.2 to 6.4) to the least accurate at 16.1 minutes (95% CI, 15.8 to 16.3). The model technique performance was the same for linear regression, random forests, elastic net, and rolling average. The important variables were the last k-patient average waits, triage category, and patient age. The global model performed at the lower end of the accuracy range compared with models for the individual sites but was within tolerable limits. CONCLUSION: Electronic emergency demographic and flow information can be used to estimate emergency ambulance patient off-stretcher times. Models can be built with reasonable accuracy for multiple hospitals using a small number of point-of-care variables.
Authors: Luke P Dawson; Emily Andrew; Michael Stephenson; Ziad Nehme; Jason Bloom; Shelley Cox; David Anderson; Jeffrey Lefkovits; Andrew J Taylor; David Kaye; Karen Smith; Dion Stub Journal: Med J Aust Date: 2022-06-23 Impact factor: 12.776