Please use this identifier to cite or link to this item: http://hdl.handle.net/11054/3200
Title: Predicting the emergency department patient journey using a machine learning approach.
Author: Kovoor, Joshua
Carmichael, Gavin J.
Stretton, B.
Gupta, A. K.
Kleinig, O. S.
Ittimani, M.
Fabian, J.
Tan, S.
Ng, J. S.
Sateakeerthy, S.
Booth, A.
Beath, Alexander
Kefalianos, John
Jacob, Mathew O.
Ahmed, S.
Chan, W.
Kovoor, P.
Gluck, S.
Gilbert, T.
Malycha, J.
Reddi, B. A.
Padbury, R. T.
Trochsler, M. I.
Maddern, G. J.
Chew, D. P.
Zannettino, A. C.
Liew, D.
Beltrame, J. F.
O’Callaghan, P. G.
Papendick, C.
Bacchi, S.
Issue Date: 2025
Publication Title: JMIR AI
Volume: 4
Abstract: We aimed to evaluate the performance of various ML models in predicting three key outcomes in ED patients’ journeys: prolonged ED length of stay (LOS ≥8 h), chest x-ray (CXR) utilization, and inpatient admissions. We analyzed data from 50,000 ED visits at two major public metropolitan hospitals in South Australia and tested XGBoost (extreme gradient boosting), random forest, and logistic regression models. Our primary objective was to assess model accuracy in predicting the outcomes to support clinical decision-making and enhance operational efficiency.
URI: http://hdl.handle.net/11054/3200
DOI: https://ai.jmir.org/2025/1/e67321
Internal ID Number: 03139
Health Subject: ARTIFICIAL INTELLIGENCE
PREDICTION
MACHINE LEARNING
HOSPITAL RESOURCE MANAGEMENT
Type: Journal Article
Article
Appears in Collections:Research Output

Files in This Item:
There are no files associated with this item.


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.