This site has been optimized to work with modern browsers and does not fully support your version of Internet Explorer.

Thames Valley hospitals coordinate England’s first AI-enabled stroke network

Brainomix software on smartphoneSix NHS trusts serving more than three million people have come together to harness state-of-the-art technology to help clinicians make the right decisions so that more patients recover following stroke.

High quality CT brain scans are being shared quickly and securely within and between hospitals using imaging software which incorporates artificial intelligence (AI). As well as supporting clinical decision-making, the new system is also helping to overcome disruption caused by Covid-19.

The e-Stroke Suite technology is now live in hospitals in Aylesbury, High Wycombe, Milton Keynes, Northampton, Oxford, Reading and Swindon which have established the first integrated regional stroke network of its type in the country in line with a key NHS priority.

Previously, CT brain scans had to be reviewed by a specialist in limited locations. Now they can be seen within a few minutes of being processed – anywhere, any time – and advice given immediately. Reducing the time between the patient arriving in hospital and being referred for treatment is crucial in securing full recovery after having a stroke.

The rapid transfer of high-quality images enables a more coordinated and swift response in identifying whether a patient would benefit from a mechanical thrombectomy (MT), a procedure to remove a blockage in a large blood vessel in the brain which can cause a severe stroke. The NHS Long Term Plan identifies stroke as a clinical priority. It aims to increase use of thrombectomy so that hundreds more people are able to regain their independence following a stroke.

Within the Thames Valley, Oxford University Hospitals NHS Foundation Trust (OUH) provides specialist stroke care for patients requiring MT. Currently 30-50 patients undergo MT each year in Oxford. Across the Thames Valley it is estimated that 300-400 patients per year could benefit from MT.

The innovative decision support tool helps clinicians to rapidly and accurately decide the type and severity of stroke and the most appropriate treatment. Initially introduced before the pandemic, it has demonstrated added benefits in recent months by enabling new ways of working in a world disrupted by Covid-19. For example, if one hospital is overburdened with Covid-19 another within the regional network can help out by interpreting brain scans without delay.

The e-Stroke Suite technology is developed by Brainomix, an Oxford-based company spun out of the University of Oxford in 2010.

Dr Phil Mathieson, clinical lead for stroke at OUH, said: “We are delighted to be the first stroke network in the country to use an AI decision aid in the management of our patients with stroke.

“This will assist us in the rapid identification of patients who may benefit from a mechanical thrombectomy. As all of our referring hospitals will be using the e-Stroke Suite, this removes the barrier of delays in accessing the necessary imaging to make these time-critical decisions.

“It also futureproofs us as we look to use more advanced imaging techniques to expand the number of patients with a stroke that may be helped by the thrombectomy procedure. I am confident that this development will help improve outcomes for patients in the Thames Valley.”

Dr Gabriel Yiin, consultant neurologist at Great Western Hospitals NHS Foundation Trust, said: “The software will greatly improve our local thrombectomy pathway, and could potentially improve stroke outcomes and reduce the burden on social care in future.”

Dr Kiruba Nagaratnam, clinical lead for stroke medicine at the Royal Berkshire NHS Foundation Trust, said: “The time window for thrombectomy is up to six hours from symptom onset and every hour we delay this treatment, the benefit goes down by 5%. Using Brainomix’s AI-driven imaging support software I can now see the images within two minutes of them being processed. I can look at the scans, and then give specialist advice immediately advising treatment. The immediate benefit is that you reduce the hospital stay, but I think most of the cost saving is going to come from the long-term benefits by reducing the amount of social care required.”

Dr Matthew Burn, clinical lead for stroke at Buckinghamshire Healthcare NHS Trust and the Thames Valley Strategic Clinical Network, said: “We are very pleased to be adopting the Brainomix technology for our stroke patients. This is the first AI platform to be used for imaging within the Trust. All stroke patients having a CT brain scan or CT angiogram will have an AI report which will be very helpful to the stroke teams on call who need to make treatment decisions within minutes, and before the radiologists have reviewed the scans.

“The platform also allows the scans and AI reports to be viewed on a mobile phone, and shared instantaneously with other stroke centres in the network thereby facilitating the rapid transfer of selected patients for time-sensitive clot-removal (thrombectomy) procedures in Oxford and Charing Cross.”

Riaz Rahman, VP healthcare global at Brainomix, said: “By providing physicians with transformative technology, they are able to make quicker and more effective decisions to improve patient outcomes.”

The Oxford Academic Health Science Network (Oxford AHSN) has helped to establish the system in the Thames Valley and with the National Consortium of Intelligent Medical Imaging (NCIMI) is supporting the technology’s introduction at more than 20 further hospitals in the South East. NCIMI is a national centre of excellence for medical imaging and AI and supports network of NHS hospitals, clinical leaders and industry experts to develop and deploy AI in medical imaging, supported by Innovate UK.

Dr Guy Rooney, the Oxford AHSN’s medical director, said: “The e-Stroke Suite is a valuable resource in a world disrupted by the Covid-19 pandemic. It aids clinical decision-making by facilitating the rapid and secure transfer of high quality images to new settings, speeding up accurate diagnosis and treatment related to stroke.”

Professor Gary Ford, CEO of the Oxford AHSN and a stroke physician at OUH, said: “We have a once-in-a-generation opportunity with mechanical thrombectomy for acute ischaemic stroke to alter the miserable prognosis for the most devastating form of stroke, with substantial benefits for individuals and for wider health and social care.”

NCIMI CEO Dr Claire Bloomfield said: “We are delighted to support world-leading companies like Brainomix in bringing AI into the NHS to improve care – they are at the vanguard and we hope will help open the doors for further solutions to be deployed using AI to improve care.”

Case study:

A 70-year-old male with a suspected acute stroke was brought in by ambulance to the Royal Berkshire Hospital (RBH) in Reading on a Sunday during the Covid-19 pandemic. Examination indicated a severe stroke. The stroke specialist nurse alerted the consultant team. A consultant picked up the call immediately and reviewed the AI-processed images on the Brainomix app. The decision was made immediately to initiate intravenous thrombolysis and a direct referral was made to the neuroscience centre for mechanical thrombectomy in Oxford. Pseudonymised images were shared via the Brainomix app. A decision to transfer the patient was made using these images while traditional image transfer was awaited. The patient underwent mechanical thrombectomy with excellent outcome. He was transferred back to RBH on the same day for ongoing care and discharged home three days later fully independent. The patient received a high standard of care and achieved an excellent outcome.