The Sydney Triage to Admission Risk Tool With Artificial Intelligence ( <scp>START</scp> ‐ <scp>AI</scp> ): Prediction of Inpatient Admission From Emergency Departments Using Ensemble Machine Learning
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.
Authors
- Elizabeth J. M. Corbett
- Saartje Berendsen Russell (ORCID: https://orcid.org/0000-0002-1380-8469)
- Michael Dinh (ORCID: https://orcid.org/0000-0002-0086-455X)
- Radhika V. Seimon (ORCID: https://orcid.org/0000-0002-3903-4801)
- Nicholas Moore (ORCID: https://orcid.org/0000-0002-7623-9697)
- Eliot DD Salmon (ORCID: https://orcid.org/0009-0004-6212-3898)
- Irena Koprinska (ORCID: https://orcid.org/0000-0001-9479-4187)
- Saleem Ahmed Khan
- Naomi Derrick
- Sreenadh Brahmapuram
- Thuy Truc Ngo
Institutions
- Camden and Campbelltown Hospitals (AU)
- The University of Sydney (AU)
- Royal Prince Alfred Hospital (AU)
- UNSW Sydney (AU)
- Sydney Local Health District (AU)
- Western Sydney University (AU)
Publication Details
- Journal
- Emergency Medicine Australasia
- Published
- 2026-03-08
- DOI
- https://doi.org/10.1111/1742-6723.70240
- Primary Topic
- Artificial Intelligence in Healthcare and Education
- Type
- article
- Field-Weighted Citation Impact
- 0.00