Brainomix flags Jean Hines's stroke; transferred in 25 minutes

AI system

System: Brainomix 360 Stroke
Model: Not assessed
Release: Not assessed
Application developer: Brainomix
Role: Not assessed
Configuration: Not assessed
Inputs and outputs: Not assessed
Autonomy: Not assessed
Workflow: AI stroke imaging with results available to the admitting team immediately after the scan. A regional transfer pathway from primary stroke center to a thrombectomy center.
Human oversight: Not assessed
Relation to AI: The AI-supported scan read identified the major stroke immediately on arrival, enabling a 25-minute door-in-door-out. The treatment itself (thrombectomy) was delivered by the Oxford team. The stroke would very likely have been diagnosed without AI. So the AI's contribution is the speed of decision and transfer. The Lancet Digital Health study (which has Brainomix co-authors alongside NHS lead authors) supports that at population level.
AI contribution: The AI-supported scan read identified the major stroke immediately on arrival, enabling a 25-minute door-in-door-out. The treatment itself (thrombectomy) was delivered by the Oxford team. The stroke would very likely have been diagnosed without AI. So the AI's contribution is the speed of decision and transfer. The Lancet Digital Health study (which has Brainomix co-authors alongside NHS lead authors) supports that at population level.

Studies: Not assessed
Study design: Not assessed
Measurement: Not assessed
Setting and sample: Not assessed
Measures: transferred in 25 minutes for successful thrombectomy
Comparison: thrombectomy rate at the same 26 hospitals before the software was implemented, with the 81 non-implementing hospitals as the background trend
Results: Reference: 2·3% (376 of 15 969 patients). Result: 4·6% (751 of 15 428 patients), a relative increase of 100%.
Additional value from AI: Not assessed
Limitations: Not assessed
Denominators: Not assessed
Materials for replication: Not assessed

Participants: Developer: Brainomix. Operator: NHS England / Royal Berkshire Hospital.
Jurisdictions: Benefit: Reading, United Kingdom. Developer: United Kingdom. Operator: United Kingdom.
Ownership and control: Not assessed
Dependencies: Not assessed
Cross-border connections: Not assessed
Geopolitical implications: Not assessed

Conditions for replication: Rapid ambulance transfer and an available thrombectomy team. Clinicians act on the AI-supported read without waiting for a separate specialist report.
Replication attempts: 1 follow-up entries. Benefit recurred: 1.
Later findings: 2 December 2025. Four months after the inferred date of Jean Hines's stroke, the Lancet Digital Health study reported the same software systematically implemented in 26 NHS hospitals and associated with doubled thrombectomy rates.
Availability: Not assessed
Institutional decision: Not assessed
Grounds: Not assessed
Action and result: Not assessed
Success criterion: Not assessed

Assessed benefits: People. Organizations.
Depth: People: 3. Organizations: 2.
Reasons: People: Rapid transfer enabled thrombectomy for a major stroke and she reports no serious disabilities. The AI's contribution was the time saved. Organizations: NHS England reports a 25-minute door-in-door-out for this patient against a 64-minute average reduction at primary stroke centers. It also reports a doubling of thrombectomy rates (2.3% to 4.6%) at participating sites.
Observed or intended: Not assessed
Rubric: Not assessed
Assessor and date: Not assessed
Alternative assessments: Not assessed
Fill: The deployer's account

Kind: Not assessed
Related entries: Not assessed
Field: Healthcare - acute stroke care. Hospital stroke imaging decision support.
Purpose: Brainomix 360 Stroke is built to analyze stroke imaging and support rapid treatment and transfer decisions, including selection for thrombectomy. This is its intended function.
Dates: Date basis unassessed: 2025 (precision unassessed). Updated: 21 October 2026.
Stage: Not assessed
Version: SHA-256: a9d99f6616f7…

Peer-reviewed study Developer

Nagaratnam K, Neuhaus AA, Fensome L, et al. (2025). Artificial intelligence imaging decision support for acute stroke treatment in England: a prospective observational study. The Lancet Digital Health 7(12):100927. Three Brainomix employees and the corresponding author (dual NHS/Brainomix affiliation) are among 21 authors; lead authors are NHS and University of Oxford.
Press release Deployer

NHS England (2025). 'Life-changing' AI support helping stroke patients get a second chance. NHS England news, 2 December 2025.