EUVIMEDEUVIMED entdecken
Crossref

The Sydney Triage to Admission Risk Tool With Artificial Intelligence ( START ‐ AI ): Prediction of Inpatient Admission From Emergency Departments Using Ensemble Machine Learning

Michael Dinh, Elizabeth Corbett iD, Eliot Salmon iD, Saleem Ahmed Khan, Nicholas Moore, Sreenadh Brahmapuram, Radhika Seimon, Naomi Derrick, Saartje Berendsen Russell, Thuy Truc Ngo, Irena Koprinska

Emergency Medicine Australasia · 2026

DOI: 10.1111/1742-6723.70240 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Emergency Medicine Australasia, 2026. Verfasst von Michael Dinh und 10 weiteren Autor:innen. Beteiligte Einrichtung: RPA Green Light Institute, Sydney Local Health District, Sydney, New South Wales, Australia. Hauptthemen laut MEDLINE: Triage, Machine Learning, Artificial Intelligence, Patient Admission. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 25 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Objective

Use artificial intelligence (AI) to extend the Sydney triage to admission risk tool (START) and improve prediction of emergency department (ED) patient disposition.

Methods

The study was conducted at an inner‐city tertiary referral hospital ED. Adult (age ≥ 16 years) presentations from 1 January 2023 to 30 June 2025 were included. Participants were excluded if dead on ED arrival or left ED prior to completing treatment. The primary outcome was admission to an inpatient ward. A sequential ensemble modelling approach was used. To predict patient disposition, the original START was combined (stacked) with vital signs, blood results and CT imaging orders using a gradient boosting decision tree algorithm (XGBoost) and a pre‐trained transformer model for clinical free text.

Results

162,915 cases were analysed with 27.31% overall inpatient admission rate. The final stacked meta‐XGBoost model had an area under receiver operating curve (AUROC) of 0.88 (95% CI: 0.88, 0.89) with overall weighted accuracy of 0.84 (95% CI: 0.84, 0.85) and F1 score of 0.83 (95% CI: 0.83, 0.84) in the testing dataset. The model was adequately calibrated with R 2 of 0.92 (95% CI: 0.67, 0.99) with a drop‐off in correlation at the highest predicted probability ranges (> 0.80). After classifying inpatient stays < 24 h as potential discharges, a sensitivity analysis demonstrated AUROC for the final model of 0.89 (95% CI: 0.88, 0.89).

Conclusions

An ensemble machine learning model was developed to accurately predict patient disposition from ED using structured and unstructured data. Prototype development and prospective evaluation of START‐AI are required to assess model performance in clinical settings.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

TriageMachine LearningArtificial IntelligencePatient AdmissionHospitalizationHumansFemaleMaleEmergency Service, HospitalAdultMiddle AgedRisk AssessmentBoosting Machine Learning AlgorithmsAgedEmergency Room VisitsPredictive Learning ModelsPrediction AlgorithmsROC Curve

Stichwörter der Autor:innen

artificial intelligencedispositionemergency departmentensemble machine learning

Autor:innen und Institutionen

  • RPA Green Light Institute, Sydney Local Health District, Sydney, New South Wales, Australia.
  • Emergency Department, Royal Prince Alfred Hospital, Sydney Local Health District, Sydney, New South Wales, Australia.
  • Digital Health and Innovation, Sydney Local Health District, Sydney, New South Wales, Australia.
  • Emergency Department, Campbelltown Hospital, Sydney South West Local Health District, Sydney, New South Wales, Australia.
  • Macarthur Clinic School, Western Sydney University, Sydney, New South Wales, Australia.
  • School of Computer Science, Faculty of Engineering, The University of Sydney, Sydney, New South Wales, Australia.

ORCID-Profile: Elizabeth Corbett, Eliot Salmon

Zitieren

APA

Dinh, M., Corbett, E., Salmon, E., Ahmed Khan, S., Moore, N., Brahmapuram, S., Seimon, R., Derrick, N., Berendsen Russell, S., Ngo, T. T., & Koprinska, I. (2026). The Sydney Triage to Admission Risk Tool With Artificial Intelligence ( START ‐ AI ): Prediction of Inpatient Admission From Emergency Departments Using Ensemble Machine Learning. Emergency Medicine Australasia. https://doi.org/10.1111/1742-6723.70240

Vancouver

Dinh M, Corbett E, Salmon E, Ahmed Khan S, Moore N, Brahmapuram S, et al. The Sydney Triage to Admission Risk Tool With Artificial Intelligence ( START ‐ AI ): Prediction of Inpatient Admission From Emergency Departments Using Ensemble Machine Learning. Emergency Medicine Australasia. 2026. doi:10.1111/1742-6723.70240

BibTeX
@article{Dinh2026,
  author = {Dinh, Michael and Corbett, Elizabeth and Salmon, Eliot and Ahmed Khan, Saleem and Moore, Nicholas and Brahmapuram, Sreenadh and Seimon, Radhika and Derrick, Naomi and Berendsen Russell, Saartje and Ngo, Thuy Truc and Koprinska, Irena},
  title = {The Sydney Triage to Admission Risk Tool With Artificial Intelligence ( START ‐ AI ): Prediction of Inpatient Admission From Emergency Departments Using Ensemble Machine Learning},
  journal = {Emergency Medicine Australasia},
  year = {2026},
  doi = {10.1111/1742-6723.70240}
}
Kostenlos starten →