AI imaging triage for the acute stroke pathway

Validated & replicableScaling upDeveloping evidence

Validated and packaged for replication by other organisations.

Interprets acute stroke imaging to support rapid identification of large-vessel occlusion and treatment eligibility, accelerating thrombectomy referral.

Plain-language summary

Choose an audience and generate a tailored summary on demand. The AI uses only what is on this page.

Clinical context

Clinical problem: Detect a condition
Point of care: Triage
Nature of AI output: An alert
Clinical specialty: Emergency medicine
Care setting: Emergency department
Patient population: Adults presenting with suspected acute ischaemic stroke undergoing CT/CT-angiography.
Intended use: Interprets acute stroke imaging to support rapid identification of large-vessel occlusion and treatment eligibility, accelerating thrombectomy referral.

Technology

AI technique: Deep learning, Computer vision
Input data: Medical imaging
Output type: Alert
Autonomy level: Informs a human (advisory)
Model provenance: Vendor proprietary
Model version: e-Stroke v11
Built on a general-purpose model: No

Deployment

Status: Scaling up
Country: United Kingdom
Deployment date: 1 September 2022
Sites: 8

Regulatory & governance

EU AI Act risk tier: High-risk
High-risk basis: Annex I — medical device
Medical device: Yes
EU MDR class: Class IIb
CE marking: CE marked
FDA status: 510(k) cleared
ISO 14971 risk class: Medium
GDPR processing basis: Public interest
GDPR DPIA: Completed
Data identifiability: Pseudonymised
Explainability method: Post-hoc
Human oversight model: Stroke physician confirms every imaging interpretation before a treatment decision.

NICE evidence standards

ESF tier: Tier C — treat / diagnose / calculate risk
Evidence category: Category 3

Performance summary

Headline metric: Time saved
Value: 60
Subgroup performance assessed: Yes
Known bias signals: —

Similar deployments

Looking for close matches in the Library…

Assurance Pack

Validation artefact produced by the AIH Lab review panel.

Criteria version: 2026.1
Result: PASSED
Issued: 1 March 2023
Panel chair: —

Evidence records

Studies and evaluations attached to this use case.

External validation
Sensitivity: 0.93
Population: Multi-site LVO cohort
Prospective observational
Time saved: 60
Population: Acute stroke pathway, door-to-thrombectomy (minutes)

Contributors

Deploying organisation: [demo] Oxford University Hospitals NHS FT · Hospital / health system · United Kingdom
AI vendor: [demo] Brainomix · United Kingdom
Product name: e-Stroke