What happened
Canada's Drug Agency (CDA-AMC), formerly CADTH, published a health technology review of RapidAI for stroke detection in November 2024. Its reviewers searched the literature to July 2024 and graded their certainty in each result. Two cohort studies tested the software alongside clinicians. In one, at a single stroke center in the United States, CT angiography reports came 8.6 minutes sooner on average with Rapid LVO. The average turnaround fell from 30.6 to 22 minutes. A clinical expert judged the reduction clinically important, and the agency rated the evidence low certainty. Effects on door-to-intervention times, function and response to therapy were very uncertain. The reviewers identified no evidence on harms, deaths or cost-effectiveness. They placed both cohort studies at the highest level of risk of bias because neither adjusted for confounding. The study's authors, at the University of California, Irvine, compared 439 patients before the tool with 321 after it.
Sources
-
Peer-reviewed study, by the organization that used it.
Soun JE, Zolyan A, McLouth J, et al. Impact of an automated large vessel occlusion detection tool on clinical workflow and patient outcomes. Frontiers in Neurology 14:1179250, 25 May 2023. The authors work at the University of California, Irvine, where the tool was used. Pre-AI period December 2019 to June 2020, post-AI period December 2020 to June 2021.
Radiology CTA report TAT significantly improved post-AI (mean 30.58 min for pre-AI vs. 22 min for post-AI
-
Assessment report, by authors with no tie to the system.
Canada's Drug Agency (CDA-AMC). RapidAI for Stroke Detection: Main Report. Health Technology Review OP0556, Canadian Journal of Health Technologies 4(11), November 2024. Summary of Evidence, pp. 24-25, and Table 3.
Among patients presenting with acute ischemic stroke, CT angiography with Rapid LVO may reduce radiology-report turnaround time (1 study;73 ≤ 760 patients; low certainty) by 8.6 (standard deviation [SD] = 32.8) minutes, which was considered clinically important by the clinical expert we consulted.
Details
AI system
- Reported configuration
-
RAPID 4.9
- Workflow
-
Rapid LVO analyzed CT angiography images of patients with suspected acute ischemic stroke. Clinicians interpreted the images with the software's output.
Follow-up
- Conditions for replication
-
Clinicians interpret the images, with the software as a supporting tool. Patients undergo CT angiography for suspected acute stroke.
Entry details
- Sector
-
Healthcare (acute stroke care).
- Purpose
-
ISchemaView built Rapid LVO, part of the RapidAI platform, to detect suspected large-vessel occlusions on CT angiography for clinicians.
Not yet checked: model, provider, role, configuration, inputs and outputs, autonomy, human oversight, beneficiaries, reach, distribution and access, duration, every measurement question, every money question, ownership and control, dependencies, cross-border connections, geopolitical implications, replication attempts, availability, institutional decision, grounds, action and result, success criterion, every evidence question, observed or intended, alternative assessments, related entries, other identifiers, category mappings.
Cite this record
Peter H. Vartanian. (2026). Rapid LVO may cut stroke scan report times by 8.6 minutes (AIBD-0890). Artificial Intelligence Benefits Database, edition of 31 October 2026. https://petervartanian.xyz/aibd/records/AIBD-0890.html (archived at https://doi.org/10.7910/DVN/AADSII, version 4.0)