What happened
e-Stroke, RapidAI and Viz analyze CT brain scans of people with suspected stroke, flag findings such as blocked large vessels and share images between hospitals. The National Institute for Health and Care Excellence (NICE) assessed them in guidance published on 23 January 2024. Its assessors found seven observational studies that compared time to treatment before and after centers adopted the software. In most of them, people reached thrombectomy or thrombolysis sooner afterward. In two later studies of e-Stroke, a larger share of stroke patients had a thrombectomy after the software arrived. The assessors judged that the studies were at high risk of bias, and other changes to stroke care happened at the same time. NICE concluded that it is unclear how much of the gain is due to the software. It allowed the three products in the NHS while evidence is generated and limited ten others to research. AI decision support was already live at 99 of 107 stroke units in England. The software must be used with review by a healthcare professional.
Sources
-
Assessment report, by authors with no tie to the system.
Some studies on 3 technologies (e-Stroke, RapidAI and Viz) in clinical practice suggest that people had faster or greater access to treatment after using the software, but it is unclear to what extent this is an effect of the software.
-
Assessment report, by authors with no tie to the system.
In the EAG's initial review there were 7 observational studies that compared time to treatment before and after implementing AI-derived software in clinical practice, assessing e-Stroke, RapidAI and Viz. Most of the studies suggested that time to treatment for people who had thrombectomy or thrombolysis had reduced after implementing the software.
Details
AI system
- Workflow
-
The software flagged findings on CT brain scans for review by a healthcare professional. The software sent scan images quickly between hospitals for remote review.
Follow-up
- Conditions for replication
-
Centers keep their existing scan reporting protocols. Shared images are of sufficient quality for remote review.
Entry details
- Sector
-
Healthcare (acute stroke care).
- Purpose
-
Brainomix, iSchemaView and Viz.ai built e-Stroke, RapidAI and Viz to analyze CT brain scans for signs of stroke and to speed treatment decisions.
Not yet checked: model, release, provider, role, configuration, inputs and outputs, autonomy, human oversight, AI contribution, 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). Faster stroke treatment followed e-Stroke, RapidAI and Viz (AIBD-0737). Artificial Intelligence Benefits Database, edition of 31 October 2026. https://petervartanian.xyz/aibd/records/AIBD-0737.html (archived at https://doi.org/10.7910/DVN/AADSII, version 4.0)