aceArtificial Intelligence Triage of Urgent Versus Non-Urgent CT Brain Findings to Support Expedited Emergency Department Disposition: A Retrospective Validation Study
Objective Evaluate the diagnostic accuracy of an artificial intelligence (AI) model for identifying urgent computed tomography brain (CTB) findings in consecutive emergency department (ED) patients and estimate the proportion eligible for expedited disposition. Methods We retrospectively analysed 3424 consecutive non-contrast CTB scans from adults presenting to a quaternary ED in 2024. The AI model (Harrison Enterprise CTB) classified each scan as "urgent" or "non-urgent." The reference standard was the index co…
Retrospective validation of Harrison Enterprise CTB on 3424 ED scans showed 98.3% NPV for urgent findings, with 64% of encounters identified as true negatives potentially eligible for expedited disposition and no remaining false negatives requiring urgent intervention during the index presentation.
The AI model missed 37 scans initially classified as urgent, yielding 85.4% sensitivity, with 13 remaining small or subtle urgent findings after post hoc re-adjudication.
Retrospective single-center design using radiologist report alone as reference, and post hoc false-negative re-adjudication by a single unblinded assessor with access to medical record, limits generalizability before prospective trial.
Evidence
- Peer-reviewedEmergency Medicine Australasia2026-10-01
How should this claim be treated?
Truvace Impact Record TRV-2026-1238, v1: “Artificial Intelligence Triage of Urgent Versus Non-Urgent CT Brain Findings to Support Expedited Emergency Department Disposition: A Retrospective Validation Study.” Truvace, 2026-10-01. /record/TRV-2026-1238 (accessed at citation time). sha256 653a20785412fa3d…
Calibration history
Every change to this record since certification, in the open. None yet — the reading has held since it entered the record.
Certified into the record
How to verify without trusting this page
Fetch the canonical text of any version from /api/record/TRV-2026-1238 and hash it yourself — for example shasum -a 256 on the saved canonical field. The result must equal content_hash, and each version’s text ends with prev:followed by the prior version’s hash (version 1 chains to 64 zeros). If a single character of any version had been altered since certification, the chain would not reproduce.