A national study published in The Lancet Digital Health finds that a fast-track AI imaging tool is helping stroke patients reach specialist treatment more than an hour earlier, directly benefiting about 15,000 people. The analysis examines real-world use of the Brainomix 360 Stroke imaging system, now deployed across a network of more than 70 hospitals in England.
The Brainomix tool analyses CT scans in real time to detect signs of a major ischemic stroke and large vessel occlusion within minutes. By highlighting large clots quickly, it supports frontline clinicians to make faster transfer decisions to specialist thrombectomy centres, where a minimally invasive clot-removing procedure can be performed. Quicker access to thrombectomy and thrombolysis substantially increases the chance of regaining independence after a major stroke.
Key findings from the study include:
– At hospitals using the tool, thrombectomy rates doubled from 2.3% to 4.6% at participating sites, compared with a smaller rise from 1.6% to 2.6% at hospitals not using the technology.
– The largest gains occurred at hospitals without on-site neuroradiology expertise, where rapid image interpretation is most critical.
– At primary stroke centres, use of the AI system was associated with a 64-minute reduction in door-in-door-out time, enabling much faster transfer to specialist centres.
– Patients whose scans were reviewed with AI were more likely to receive thrombectomy and intravenous thrombolysis, and more likely to achieve a favourable functional outcome at discharge, with no increase in in-hospital mortality.
Time is critical: the study notes that every 20-minute delay in thrombectomy reduces the chance of full recovery by about 1%. With roughly 80,000 strokes in England each year, faster diagnosis and decision support from AI could help thousands more reach specialist treatment in time to improve outcomes.
Dr David Hargroves, NHS National Clinical Director for Stroke and a study co-author, said the findings supply robust, real-world evidence that stroke imaging AI speeds decision-making and improves care, helping clinicians deliver life- and disability-saving treatments to more patients and increasing the chances of returning to independent living.
Patient example: Jean Hines, 83, was taken to Royal Berkshire Hospital after collapsing. A scan reviewed with Brainomix identified a major stroke and the need for urgent specialist treatment. Within 25 minutes of arrival she was transferred by blue-light ambulance to the John Radcliffe Hospital in Oxford and underwent a successful mechanical thrombectomy. Jean credits the speed of care for her good recovery and said she felt “incredibly lucky” that rapid treatment prevented serious disability.
Study and rollout snapshot:
– 452,952 stroke patients included in the national audit dataset
– 71,017 patients treated at the 26 evaluation hospitals in the patient-level analysis
– After AI implementation (Jan 2022 onwards), 15,377 patients had their scans reviewed using AI
– Thrombectomy rates doubled at evaluation sites (2.3% to 4.6%)
– 64-minute reduction in door-in-door-out time at primary stroke centres using AI
– Increased rates of thrombectomy and thrombolysis, improved functional outcomes at discharge, no rise in in-hospital mortality
Study: Artificial intelligence imaging decision support for acute stroke treatment in England: a prospective observational study, Lancet Digital Health, 2025. AI decision-support tools were rolled out to all stroke centres in England in Summer 2024 as part of the national optimal stroke imaging pathway.
