This site is intended for UK healthcare professionals
Medscape UK Univadis Logo
Medscape UK Univadis Logo

Artificial Intelligence Triples Stroke Recovery

Editor's note: The headline of the story and a subheading have been edited

Use of new artificial intelligence (AI) technology has enabled the NHS to provide speedier diagnosis, and thus faster appropriate treatment, for more than 100,000 suspected stroke patients, the Department of Health and Social Care (DHSC) has reported. It said that the Brainomix e-Stroke system reduced average door 'in and out' time by more than an hour, and that this was associated with a tripling in the number of stroke patients recovering with no or only slight disability – defined as achieving functional independence.

Stroke affects 85,000 people in England every year. It is one of the most time-sensitive diagnoses in medicine, and cutting the time from presentation to diagnosis is potentially lifesaving, as well as increasing the chance of patients recovering to be able to perform daily activities.

'Real-time Interpretation of Brain Scans'

The e-stroke technology, developed in the UK, is a set of tools that use state-of-the-art AI algorithms to support clinicians by providing "real-time interpretation of brain scans to help guide treatment and transfer decisions for stroke patients, allowing more patients to get the right treatment, in the right place, at the right time", according to the software developers.

It allows stroke specialists to access scans and images remotely and securely, and supports clinicians working across integrated stroke delivery networks, which bring together specialists from all parts of the stroke pathway to ensure more people who experience a stroke receive high-quality specialist care, from pre-hospital, through to early supported discharge, community specialist stroke-skilled rehabilitation and life after stroke.

It was first introduced to the NHS in March 2020 at the Royal Berkshire Hospital, where a pilot study compared thrombectomy referrals fortwo periods, patients admitted from January 2019 to February 2020, before e-Stroke's implementation, versus those admitted from March 2020 to April 2021, after e-Stroke's implementation.

Results of the study, presented in October 2021 to the 13th World Stroke Congress, showeda significant reduction in overall door-in-door-out time, from 140 minutes down to 79 minutes, an improvement of over 60 minutes. The study also showed that three times as many patients – 48% versus 16% - achieved functional independence following the adoption of e-Stroke.

Faster Treatment Decisions and Improved Outcomes

Study presenter Dr Kiruba Nagaratnam, consultant in stroke and general medicine at the Royal Berks, said that the AI system helped the stroke team to identify large vessel occlusions faster, enabling the referral and transfer process to be initiated sooner. "Brainomix's software has allowed us to deliver a more efficient pathway, make faster treatment decisions, and achieve better outcomes for our patients," he said.

The DHSC noted that the "ground-breaking diagnosis and treatment tools" not only help to improve patient outcomes but also free up valuable clinician time. The system received funding from the first round of the Government's 'AI in Health and Care Awards', backed by £123 million and run by the National Institute for Health Research (NIHR), the Accelerated Access Collaboration at NHS England, and the NHS AI Lab. The awards support accelerating the testing and evaluation of cutting-edge technologies that have the potential for the greatest patient and clinician benefit.

The award funding enabled more than 111,000 suspected stroke patients across 5 stroke networks in England to benefit from the system, supporting the detection of over 4500 large vessel occlusions in stroke patients. In total Brainomix e-Stroke is now deployed at sites spanning 11 stroke networks across the country.

System now a 'Cornerstone' of Integrated Stroke Delivery Networks

Riaz Rahman, vice president healthcare global, Brainomix, said: "The Brainomix e-Stroke platform has fast become a cornerstone of integrated stroke delivery networks' ability to deliver best in class stroke care. We have collated multiple examples of hard evidence, spanning several networks, confirming the use of e-Stroke helps deliver more consistent treatment decisions and faster patient transfers. This is vitally important in a highly time sensitive pathway.

"Having successfully deployed the system at pace and scale across the NHS, we have seen in some regions the tripling of post-operative patient functional scores and more than double the access to life saving mechanical thrombectomy treatment."

Health and Social Care Secretary Steve Barclay said: "AI has the potential to transform our NHS – delivering faster, more accurate diagnoses and making sure patients can get the treatment they need, when they need it.

'Incredible Example' of the Power of AI

"Brainomix is an incredible example of how this can be achieved, using the power of AI to shave lifesaving minutes off one of the most time-sensitive diagnoses in medicine, meaning patients get the treatment they need faster.

"I am immensely proud the AI Awards continues to harness this innovation, empowering researchers across the country to deliver ground breaking new technologies which will transform our health and care system."

Dr Timothy Ferris, NHS England director of transformation, said: "Every minute saved during the initial hospital assessment of people with stroke-like symptoms can dramatically improve a patient's chance of leaving hospital in good health.

"The NHS is harnessing the potential that AI has to support expert staff in delivering life-changing care for patients with a range of needs, and through the AI in Health and Care awards we are testing, evaluating and supporting the most promising technologies which could transform the way we deliver care."