Stroke patients in England are getting life-changing treatment more than an hour earlier thanks to a revolutionary “fast-track” AI tool, a major study has revealed.
The landmark analysis published inThe Lancet Digital Health shows around 15,000 patients directly benefitted from having their scans reviewed by the tech.
The AI tool — now rolled out by the NHS to a network of over 70 hospitals — helps doctors spot deadly clots in minutes, speeding up clinical decision making and helping get patients rushed to specialist stroke centres faster.
It means patients are more likely to be able to get a thrombectomy – a minimally invasive clot-removing procedure – faster, doubling their chances of regaining independence after a major stroke.
Hospitals using the Brainomix 360 Stroke imaging tool saw thrombectomy rates at participating sites double (from 2.3% to 4.6%), compared with smaller increases at hospitals not using the technology (1.6% to 2.6%).
This matters because thrombectomy is highly time-sensitive: every 20-minute delay in thrombectomy cuts the chance of full recovery by around 1%. Without the rapid scan reading and swift transfer to a specialist stroke centre, many patients arrive too late to benefit.
The platform analyses CT scans in real time, identifying key features of a major stroke within minutes. This is particularly valuable in hospitals without on-site neuroradiology expertise, where rapid interpretation is critical, and where the study found the biggest improvements in treatment rates and transfer times.
The technology forms part of a wider NHS programme that has introduced AI decision-support across every regularly admitting stroke service in England.
Stroke is one of the leading causes of death and disability in England, and every minute without treatment can destroy millions of brain cells. With around 80,000 strokes in England each year, the findings indicate that using AI to speed up diagnosis and decisions could help thousands more patients receive specialist treatment in time to improve their recovery.
Dr David Hargroves, NHS National Clinical Director for Stroke and co-author of this study said: “This landmark study confirms what we have already been seeing in daily practice: that stroke AI imaging is helping us deliver faster decision-making and better care for our patients.
“This technology supports clinicians to make rapid treatment decisions, which means more patients can receive life- and disability-saving treatments in time – giving them a better chance of returning to independent living.
“This publication provides robust, real-world evidence of the impact of AI in stroke care and shows why the NHS moved quickly to roll this technology out nationwide.”
Jean Hines, aged 83, was rushed to the Royal Berkshire Hospital on a weekend in August after collapsing at home and suffering a fractured collarbone.
A scan carried out immediately on arrival — supported by the Brainomix AI imaging tool — identified a major stroke and the need for urgent specialist treatment. Within just 25 minutes of reaching the emergency department, Jean was on her way by blue-light ambulance to the John Radcliffe Hospital in Oxford, where she underwent a successful mechanical thrombectomy.
Jean said: “I feel incredibly lucky. Everything happened so quickly and I know that made all the difference. When I was on the ward I saw people who had lost their speech or movement, and it really hit me how life-changing a stroke can be. I’m so grateful for the speed of the treatment — I know that’s why I wasn’t left with serious disabilities.”
“Physically, my recovery has been very good, but it was mentally very difficult. It was such a shock and it’s taking a while to come to terms with what has happened. But people keep telling me how well I look. I know things could have been so much worse if I hadn’t been treated as fast as I was.”
- 452,952 stroke patients were included in the national audit dataset
- 71,017 patients were treated at the 26 evaluation hospitals included in the patient-level analysis
- after AI implementation (Jan 2022 onwards), 15,377 patients had their scans reviewed using AI
- at evaluation sites, thrombectomy rates doubled from 2.3% → 4.6%
- at primary stroke centres, AI use was associated with a 64-minute reduction in door-in-door-out time
- patients reviewed with AI were more likely to receive thrombectomy and intravenous thrombolysis
- patients reviewed with AI were more likely to achieve a favourable functional outcome at discharge, with no increase 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.
