NHS AI tool doubles life-saving thrombectomy rates for stroke patients

Credit: peterschreiber.media

By Emma Wilkinson

A fast-track AI tool now rolled out to more than 70 hospitals has been shown to increase the number of stroke patients undergoing thrombectomy.

Evaluation of the Brainomix 360 Stroke imaging technology at 26 hospitals found rates of thrombectomy doubled from 2.3% to 4.6%, compared with a smaller rise of 1.6% to 2.6% at hospitals without the software.

Its use was associated with a 57% increased likelihood of endovascular thrombectomy compared with patients for whom the AI software was not used, say the study authors in The Lancet Digital Health.

The tool helps doctors spot deadly clots in minutes, speeding up clinical decision making and helping transfer patients to specialist stroke centres faster, NHS England said.

Researchers, who included the NHS national clinical director for stroke, concluded that the evaluation supports the routine use of AI imaging software in this group of patients.

Evidence has shown that every 20-minute delay in thrombectomy cuts the chance of full recovery by around 1%.

The Brainomix 360 Stroke imaging tool analyses CT scans in real time, identifying key features of a major stroke within minutes.

Researchers found that it reduced the delays in “door-in door-out time” at primary stroke centres where they are evaluated before being transferred to a specialised centre for the procedure by around an hour.

This improvement in speed for those who needed thrombectomy was “clinical meaningful”, they added.

Analysis showed the biggest improvements in treatment rates and transfer times in hospitals without on-site neuroradiology expertise.

It is the largest analysis of stroke AI imaging software to date, the researchers noted.

They also reported that improved clinical outcomes at discharge were consistent with higher treatment rates and shorter times to treatment, although longer term clinical outcomes were not available in the dataset.

Previous real-world studies of its use had looked at individual centres or networks.

Dr David Hargroves, NHS national clinical director for stroke and co-author 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.”

He added that the “robust, real-world evidence” showed why the NHS moved quickly to roll the technology out nationwide.

After AI implementation in January 2022, 15,377 patients had their scans reviewed using AI as part of an evaluation of its use.

It was rolled out to all stroke centres in England in summer 2024.

Reference: Lancet Digit Health DOI: 10.1016/j.landig.2025.100927

‌
‌
‌
‌
‌
‌