Predicting Inpatient Admissions From Emergency Department Triage Using Machine Learning: A Systematic Review

This study aimed to evaluate the quality of evidence for using machine learning models to predict inpatient admissions from emergency department triage data, ultimately aiming to improve patient flow management. A comprehensive literature search was conducted according to the PRISMA guidelines acros...

Full description

Saved in:
Bibliographic Details
Main Authors: Ethan L. Williams, MD, Daniel Huynh, MD, Mohamed Estai, MBBS, PhD, Toshi Sinha, PhD, Matthew Summerscales, MBBS, Yogesan Kanagasingam, PhD
Format: Article
Language:English
Published: Elsevier 2025-03-01
Series:Mayo Clinic Proceedings: Digital Health
Online Access:http://www.sciencedirect.com/science/article/pii/S2949761225000045
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850041586053808128
author Ethan L. Williams, MD
Daniel Huynh, MD
Mohamed Estai, MBBS, PhD
Toshi Sinha, PhD
Matthew Summerscales, MBBS
Yogesan Kanagasingam, PhD
author_facet Ethan L. Williams, MD
Daniel Huynh, MD
Mohamed Estai, MBBS, PhD
Toshi Sinha, PhD
Matthew Summerscales, MBBS
Yogesan Kanagasingam, PhD
author_sort Ethan L. Williams, MD
collection DOAJ
description This study aimed to evaluate the quality of evidence for using machine learning models to predict inpatient admissions from emergency department triage data, ultimately aiming to improve patient flow management. A comprehensive literature search was conducted according to the PRISMA guidelines across 5 databases, PubMed, Embase, Web of Science, Scopus, and CINAHL, on August 1, 2024, for English-language studies published between August 1, 2014, and August 1, 2024. This yielded 700 articles, of which 66 were screened in full, and 31 met the inclusion and exclusion criteria. Model quality was assessed using the PROBAST appraisal tool and a modified TRIPOD+AI framework, alongside reported model performance metrics. Seven studies demonstrated rigorous methodology and promising in silico performance, with an area under the receiver operating characteristic ranging from 0.81 to 0.93. However, further performance analysis was limited by heterogeneity in model development and an unclear-to-high risk of bias and applicability concerns in the remaining 24 articles, as evaluated by the PROBAST tool. The current literature demonstrates a good degree of in silico accuracy in predicting inpatient admission from triage data alone. Future research should emphasize transparent model development and reporting, temporal validation, concept drift analysis, exploration of emerging artificial intelligence techniques, and analysis of real-world patient flow metrics to comprehensively assess the usefulness of these models.
format Article
id doaj-art-474e97f0d9d74dbfb8ccfbb93db3d5f0
institution DOAJ
issn 2949-7612
language English
publishDate 2025-03-01
publisher Elsevier
record_format Article
series Mayo Clinic Proceedings: Digital Health
spelling doaj-art-474e97f0d9d74dbfb8ccfbb93db3d5f02025-08-20T02:55:45ZengElsevierMayo Clinic Proceedings: Digital Health2949-76122025-03-013110019710.1016/j.mcpdig.2025.100197Predicting Inpatient Admissions From Emergency Department Triage Using Machine Learning: A Systematic ReviewEthan L. Williams, MD0Daniel Huynh, MD1Mohamed Estai, MBBS, PhD2Toshi Sinha, PhD3Matthew Summerscales, MBBS4Yogesan Kanagasingam, PhD5School of Medicine, The University of Notre Dame, Fremantle, Western Australia, Australia; Emergency Department, St John of God Midland Public and Private Hospitals, Midland, Western Australia, Australia; Correspondence: Address to Ethan L. Williams, MD, School of Medicine, The University of Notre Dame, 21 Henry Street, Fremantle, Western Australia 6160, Australia.General Medicine Department, Royal North Shore Hospital, St Leonards, New South Wales, AustraliaSchool of Human Sciences, The University of Western Australia, Crawley, Western Australia, AustraliaSchool of Medicine, The University of Notre Dame, Fremantle, Western Australia, AustraliaEmergency Department, St John of God Midland Public and Private Hospitals, Midland, Western Australia, AustraliaSchool of Medicine, The University of Notre Dame, Fremantle, Western Australia, Australia; Emergency Department, St John of God Midland Public and Private Hospitals, Midland, Western Australia, AustraliaThis study aimed to evaluate the quality of evidence for using machine learning models to predict inpatient admissions from emergency department triage data, ultimately aiming to improve patient flow management. A comprehensive literature search was conducted according to the PRISMA guidelines across 5 databases, PubMed, Embase, Web of Science, Scopus, and CINAHL, on August 1, 2024, for English-language studies published between August 1, 2014, and August 1, 2024. This yielded 700 articles, of which 66 were screened in full, and 31 met the inclusion and exclusion criteria. Model quality was assessed using the PROBAST appraisal tool and a modified TRIPOD+AI framework, alongside reported model performance metrics. Seven studies demonstrated rigorous methodology and promising in silico performance, with an area under the receiver operating characteristic ranging from 0.81 to 0.93. However, further performance analysis was limited by heterogeneity in model development and an unclear-to-high risk of bias and applicability concerns in the remaining 24 articles, as evaluated by the PROBAST tool. The current literature demonstrates a good degree of in silico accuracy in predicting inpatient admission from triage data alone. Future research should emphasize transparent model development and reporting, temporal validation, concept drift analysis, exploration of emerging artificial intelligence techniques, and analysis of real-world patient flow metrics to comprehensively assess the usefulness of these models.http://www.sciencedirect.com/science/article/pii/S2949761225000045
spellingShingle Ethan L. Williams, MD
Daniel Huynh, MD
Mohamed Estai, MBBS, PhD
Toshi Sinha, PhD
Matthew Summerscales, MBBS
Yogesan Kanagasingam, PhD
Predicting Inpatient Admissions From Emergency Department Triage Using Machine Learning: A Systematic Review
Mayo Clinic Proceedings: Digital Health
title Predicting Inpatient Admissions From Emergency Department Triage Using Machine Learning: A Systematic Review
title_full Predicting Inpatient Admissions From Emergency Department Triage Using Machine Learning: A Systematic Review
title_fullStr Predicting Inpatient Admissions From Emergency Department Triage Using Machine Learning: A Systematic Review
title_full_unstemmed Predicting Inpatient Admissions From Emergency Department Triage Using Machine Learning: A Systematic Review
title_short Predicting Inpatient Admissions From Emergency Department Triage Using Machine Learning: A Systematic Review
title_sort predicting inpatient admissions from emergency department triage using machine learning a systematic review
url http://www.sciencedirect.com/science/article/pii/S2949761225000045
work_keys_str_mv AT ethanlwilliamsmd predictinginpatientadmissionsfromemergencydepartmenttriageusingmachinelearningasystematicreview
AT danielhuynhmd predictinginpatientadmissionsfromemergencydepartmenttriageusingmachinelearningasystematicreview
AT mohamedestaimbbsphd predictinginpatientadmissionsfromemergencydepartmenttriageusingmachinelearningasystematicreview
AT toshisinhaphd predictinginpatientadmissionsfromemergencydepartmenttriageusingmachinelearningasystematicreview
AT matthewsummerscalesmbbs predictinginpatientadmissionsfromemergencydepartmenttriageusingmachinelearningasystematicreview
AT yogesankanagasingamphd predictinginpatientadmissionsfromemergencydepartmenttriageusingmachinelearningasystematicreview