Canonical text (the exact bytes fingerprinted)

TRUVACE RECORD VERSION
record: TRV-2026-0307
version: 1
kind: certified
reason: Certified into the record
timestamp: 2026-07-20T08:46:27.151564Z
status: published
lens: trace
sector: health
headline: Artificial Intelligence-Based CTA Software for Real-World Detection of Large Vessel Occlusion in Acute Ischemic Stroke
dek: Background and purpose Artificial intelligence (AI)-based tools for CT angiography (CTA) have been introduced to support rapid detection of large vessel occlusion (LVO) in acute ischemic stroke. Although regulatory approval has relied mainly on controlled clinical studies, evidence from routine clinical practice remains limited. This study aimed to assess the real-world diagnostic performance and workflow impact of the Brainomix e-CTA software. Materials and methods We conducted a retrospective, single-center ob…
gain_title: In routine practice between May 2023 and May 2025, Brainomix e-CTA achieved 84% sensitivity and 95% specificity for LVO detection and reduced time to diagnostic conclusion for readers of different experience levels, with 94% sensitivity for ICA/proximal M1 occlusions.
problem_title: The same e-CTA tool showed progressively lower sensitivity for more distal occlusions, dropping to 73% for distal M1 with only moderate agreement with experts, and excluded non-target occlusions from primary analysis, requiring adjunctive rather than standalone use.
trace_subject: detection of large vessel occlusion in acute ischemic stroke using Brainomix e-CTA in consecutive patients undergoing multiphase CTA
gain_reading: In routine practice between May 2023 and May 2025, Brainomix e-CTA achieved 84% sensitivity and 95% specificity for LVO detection and reduced time to diagnostic conclusion for readers of different experience levels, with 94% sensitivity for ICA/proximal M1 occlusions.
gain_evidence: Overall LVO detection showed a sensitivity of 84%, specificity of 95%, and accuracy of 93%. | Brainomix e-CTA showed high diagnostic accuracy for proximal anterior-circulation LVO and reduced time to diagnostic conclusion. | AI assistance significantly reduced time to diagnostic conclusion across all reader profiles.
problem_reading: The same e-CTA tool showed progressively lower sensitivity for more distal occlusions, dropping to 73% for distal M1 with only moderate agreement with experts, and excluded non-target occlusions from primary analysis, requiring adjunctive rather than standalone use.
problem_evidence: Sensitivity was highest for ICA/proximal M1 occlusions (94%) and progressively decreased for intermediate (87%) and distal M1 occlusions (73%). | Agreement between AI output and expert interpretation was excellent for ICA/proximal M1 occlusions (κ = 0.91) and moderate for distal M1 occlusions (κ = 0.48). | lower sensitivity for distal M1 occlusions and the exclusion of non-target occlusions from the primary endpoint indicate that e-CTA should be used as an adjunctive workflow tool rather than as a standalone method for treatment decision-making.
quick_read: Between May 2023 and May 2025, researchers retrospectively evaluated 531 multiphase CTA examinations from consecutive patients with suspected acute ischemic stroke at a single center, comparing Brainomix e-CTA automated LVO detection to expert neuroradiologist interpretation.

The findings matter because high accuracy for proximal occlusions and faster reading times could support triage, but the observed drop to 73% sensitivity for distal M1 occlusions and exclusion of non-target occlusions means clinicians still need expert review and broader validation before relying on the tool alone.
limitation: Single-center retrospective design with pragmatic neuroradiologist reference standard, and primary endpoint excluded non-target occlusions, limiting generalizability and standalone use for treatment decisions.
tag: Model-prefilled trace
key_points: Retrospective single-center study of 531 CTA examinations in consecutive patients with suspected acute ischemic stroke from May 2023 to May 2025. | LVO was identified in 19% of cases by expert neuroradiologist reference standard. | Sensitivity varied by location: 94% for ICA/proximal M1, 87% for intermediate, 73% for distal M1 occlusions.
rundown: The study compared automated LVO detection using e-CTA against expert neuroradiologist interpretation as a pragmatic clinical reference standard, evaluating sensitivity, specificity, accuracy, and Cohen's kappa by occlusion location.

Time to diagnostic conclusion was compared with and without AI assistance across readers with different experience levels, showing reduction across all reader profiles by the publication date of July 10, 2026.
sources:
- peer_reviewed | European Neurology | https://doi.org/10.1159/000553264 | 2026-07-10
prev: 0000000000000000000000000000000000000000000000000000000000000000

sha256

4e04caafa0887f52ec4ed6999df82a6eb951ab0e7fc5dfb85ebed1a80fb80d18

previous

0000000000000000000000000000000000000000000000000000000000000000