+ EDUCATION Abstract This scoping review directs attention to artificial intelligence–mediated informal language learning…± HEALTH Artificial intelligence (AI) is increasingly being integrated into healthcare systems and has the potential t…± HEALTH Objective This article helps neurologists understand modern approaches to diagnosing obstructive sleep apnea,…± CLIMATE Antifouling paints often contain biocides designed to inhibit biological growth, and antifouling paint partic…+ EDUCATION Generative artificial intelligence (GenAI) tools are an increasingly common resource used in the classroom an…+ HEALTH Objective Compare the effectiveness of machine learning algorithms and traditional logistic regression in pre…± HEALTH Objective Given the pivotal role of imaging in diagnosing urological cancers, artificial intelligence (AI) ha…+ HEALTH Background Traumatic cervical spinal cord injury (TCSCI) often causes severe neurological dysfunction. Accura…
TruaceTracing the truth around AIWednesday, August 5, 2026
Subscribe
Health·G Space·Evidence-backed gain·Published 2026-08-01

The Sydney Triage to Admission Risk Tool With Artificial Intelligence (START-AI) to Support Decision Making in Emergency Departments: Model Explainability and Feature Importance Analysis

Objective Evaluate the importance of specific variables contributing to a recently reported Artificial Intelligence (AI) prediction model called Sydney Triage to Admission Risk Tool with Artificial Intelligence (START-AI) to predict inpatient admission from the Emergency Department (ED). Methods A model explainability analysis was undertaken using single-centre ED electronic medical record data over 2 years. The START-AI model, which comprises ensemble machine learning and a transformer-based algorithm to enhanc…

TRV-2026-0618Peer-reviewedPermanent record — cite & verify
The Sydney Triage to Admission Risk Tool With Artificial Intelligence (START-AI) to Support Decision Making in Emergency Departments: Model Explainability and Feature Importance Analysis

Hospital Universitari Doctor Peset, València 07 by 19Tarrestnom65. CC BY-SA 4.0 · https://creativecommons.org/licenses/by-sa/4.0

The quick read

In a single-centre study using two years of ED electronic records, investigators evaluated the Sydney Triage to Admission Risk Tool with Artificial Intelligence (START-AI) by adding features one by one and calculating permutation importance and SHAP values for inpatient admission prediction.

Understanding which inputs most improve AUROC matters for safe deployment, trust, and workflow integration in emergency care, but the analysis remains retrospective and single-centre, leaving prospective validation and impact on actual admission decisions uncertain.

Main points
  • Analysis used single-centre ED electronic medical record data over 2 years to re-run START-AI with sequential feature addition.
  • Largest stepwise AUROC gains came from triage comments, ED case history notes, any blood test result especially lactate and C-reactive protein, and any CT order.
  • Overall feature importance was highest for presence of any blood test result, START score, and C-reactive protein, while vital signs did not show stepwise AUROC increase.
Gain

START-AI improved prediction of inpatient admission from the emergency department from AUROC 0.78 to 0.90 when ensemble and transformer features were added.

The rundown

Researchers re-ran the START-AI model, which combines ensemble machine learning and a transformer-based algorithm, adding each feature sequentially and measuring change in AUROC and SHAP values.

The explainability results identified triage comments, case history notes, blood tests and CT orders as drivers of performance, informing how the tool can be further developed and deployed in clinical settings.

Sources

Reader signal

How should this claim be treated?

The debate