Previously submitted to: JMIR Medical Informatics (no longer under consideration since Jun 11, 2026)
Date Submitted: Jan 30, 2025
Open Peer Review Period: Feb 10, 2025 - Apr 7, 2025
(closed for review but you can still tweet)
NOTE: This is an unreviewed Preprint
Warning: This is a unreviewed preprint (What is a preprint?). Readers are warned that the document has not been peer-reviewed by expert/patient reviewers or an academic editor, may contain misleading claims, and is likely to undergo changes before final publication, if accepted, or may have been rejected/withdrawn (a note "no longer under consideration" will appear above).
Peer review me: Readers with interest and expertise are encouraged to sign up as peer-reviewer, if the paper is within an open peer-review period (in this case, a "Peer Review Me" button to sign up as reviewer is displayed above). All preprints currently open for review are listed here. Outside of the formal open peer-review period we encourage you to tweet about the preprint.
Citation: Please cite this preprint only for review purposes or for grant applications and CVs (if you are the author).
Final version: If our system detects a final peer-reviewed "version of record" (VoR) published in any journal, a link to that VoR will appear below. Readers are then encourage to cite the VoR instead of this preprint.
Settings: If you are the author, you can login and change the preprint display settings, but the preprint URL/DOI is supposed to be stable and citable, so it should not be removed once posted.
Submit: To post your own preprint, simply submit to any JMIR journal, and choose the appropriate settings to expose your submitted version as preprint.
Warning: This is an author submission that is not peer-reviewed or edited. Preprints - unless they show as "accepted" - should not be relied on to guide clinical practice or health-related behavior and should not be reported in news media as established information.
Machine Learning Approaches for Predicting Emergency Department Visits: A Scoping Review
ABSTRACT
Background:
Identifying individuals at-risk of initial or repeated emergency department (ED) presentations is critical for the resourcing of appropriate patient-centred alternative models of care. Multiple machine learning (ML) approaches and models have been used and tested globally to predict ED presentation risk among different patient cohorts with varying success.
Objective:
This scoping review aims to understand the evidence regarding the utility and performance of different ML applications in predicting ED and unplanned admissions.
Methods:
We systematically searched Embase and Medline using search terms for ED presentation, hospitalisation, risk prediction, and ML, and performed a grey literature search on Google.
Results:
Of 2,202 records identified, 70 met our inclusion criteria. Most ML models were categorised into one of the following categories: logistic regression (29), random forest (17), artificial neural networks (ANN) (8), naïve bayes (4), decision trees (8), and gradient boosting algorithms (6). Algorithm performance highly depended on the dataset used, the variety of inputs, and the outcomes measured. Logistic regression models performed best in predicting ED presentation when used on a single data source. When linking multiple data sources, ANN yielded higher predictive accuracy. However, several other models also self-reported good accuracy through cross-validation. We identified that despite the better predictability of complex ML algorithms, few have been implemented into everyday practice as simpler algorithms were more usable for clinicians. Gradient boosting-based algorithms presented with the best predictive performance of the algorithms considered. Although they show promise, most algorithms have not been implemented in clinical acute or primary care.
Conclusions:
This scoping review sheds light on the different ML approaches that have been used to predict initial and future ED presentations. Future research should focus on matching ML models to available data to enhance performance precision, and clinicians, consumers, and hospital managers should be consulted to aid implementation.
Citation
Request queued. Please wait while the file is being generated. It may take some time.
Copyright
© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.