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

Key Points

• The study aims to develop and evaluate an ensemble machine learning model for predicting patient admission from emergency departments.
• Developed an ensemble machine learning model using both structured and unstructured data.
• Conducted prototype development for the START-AI tool.
• Planned prospective evaluation to assess model performance in clinical settings.
• The model accurately predicts patient disposition from emergency departments.
• Prototype evaluation is necessary to confirm its effectiveness in real-world clinical environments.