PreventionTreatment New AI model can pinpoint stroke timing, leading to better patient outcomes

New AI software can read the brain scans of patients who have had a stroke to more accurately pinpoint when it happened and help doctors work out whether it can be successfully treated.

The research was funded by the NIHR for the purpose of NHS benefit, as well as by Imperial’s Centre for Doctoral Training for AI in Healthcare, and the Graham-Dixon Charitable Trust.

Standard treatments only work in the very earliest stages of a stroke and may cause other damage if used too late, so knowing when the stroke started is important. It is hoped that the new technology will ultimately enable faster and more accurate emergency treatment of patients in hospitals.

The software has been developed through research led by consultant neurologist, Dr Paul Bentley, a key member of the NIHR Imperial BRC Brain Sciences Theme. It addresses two of the most difficult challenges in assessing stroke patients – identifying the onset time of the stroke and whether the damage can be reversed. The software has been found to be twice as accurate as the current method, which is a visual review of the scan by doctors.

A stroke occurs when the blood supply to part of the brain is blocked or reduced, preventing brain tissue from getting oxygen and nutrients. Brain cells then start to die quickly and these areas appear dark on CT scans.

Currently, patients who arrive at the hospital with a suspected stroke immediately undergo a CT scan, which doctors review visually to assess how dark the affected areas, called lesions, in the brain are. Darker lesions mean the stroke has progressed further. From this they make an estimate of when the stroke happened and whether it may be reversible. This information is then used to make treatment decisions.

As time progresses, some treatments become ineffective or may even cause more problems. However, some strokes start while the patient is asleep and some patients may have difficulties communicating because of the stroke symptoms, making estimating when the stroke started very difficult.

All brains are unique and this also makes it very hard to predict with accuracy when the stroke started. Even if doctors know an approximate chronological start time, an individual’s blood flow or blood vessel structure may mean the stroke is progressing more quickly or slowly than average.

Dr Paul Bentley, who is part of Imperial College London’s department of Brain Sciences, led the research study. He said: “For the majority of strokes caused by a blood clot, if a patient is within 4.5 hours of the stroke happening, he or she is eligible for both medical and surgical treatments.  Up to six hours, the patient is also eligible for a surgical treatment, but after this time point, deciding whether these treatments might be beneficial becomes tricky, as more cases become irreversible. So it’s essential for doctors to know both the initial onset time, as well as whether a stroke could be reversed.”

The AI algorithm was developed in partnership with Professor Daniel Rueckert (Imperial College London and Technical University of Munich) and Edinburgh University. The model was trained on a dataset of 800 brain scans where the stroke time was known. As well as automatically extracting the relevant area from the brain scan, the algorithm reads and analyses the identified lesions, producing a time estimate.

When it was tested on almost 2000 different patients, including patients from Imperial College Healthcare NHS Trust, which hosts one of eight Hyper Acute Stroke Units in London, researchers found the AI software was twice as accurate as using a standard visual method.

They believe this is because it includes additional features from the scans, such as texture, and accounts for variations within the lesions and background. It wasn’t only good at estimating the chronological time of the stroke, but also the biological age of the lesions and so provides doctors with information about whether the stroke may be reversible.

Dr Bentley explained: “Having this information at their fingertips will help doctors to make emergency decisions about what treatments should be undertaken in stroke patients. Not only is our software twice as accurate at time-reading as current best practice, but it can be fully automated once a stroke becomes visible on a scan.”

Lead author Dr Adam Marcus said: “We estimate that up to 50% more stroke patients could be treated appropriately with treatments because of our method. We aim to deploy our software in the NHS, possibly by integrating with existing AI-analytic software that is already in use in hospital Trusts.”