Illustration of a person holding their head in their hand with the brain highlighted in red and showing signs of ischemic stroke
Credit: Images

A study conducted by Chinese researchers has found that ischemic stroke survivors who received AI-based stroke care guidance had fewer recurrent strokes, heart attacks, or vascular death within three months, compared with people whose treatment was not guided by AI.

The study abstract was presented yesterday at the American Stroke Association’s International Stroke Conference 2024 in Phoenix, Arizona.

“This research showed that an artificial intelligence-based clinical decision support system for stroke care was effective and feasible in clinical settings in China and improved patient outcomes,” said lead author Zixiao Li, MD, PhD, chief physician, professor, and deputy director of neurology at Capital Medical University’s Beijing Tiantan Hospital, China. “This type of technology aids neurologists by facilitating the sharing of information between humans and AI, using their combined strengths.”

The clinical trial by Li and colleagues was conducted at 77 hospitals across China and were randomly assigned to deliver diagnosis and treatment for ischemic stroke patients either using an AI-based clinical decision support system or by recommendations from the hospital’s stroke care team. The AI-based stroke care system utilized patients’ brain scan images incorporating established clinical knowledge for stroke diagnosis, classification of the stroke, and post-stroke care guidelines for treatments and methods to avert a second stroke.

In total, the study enrolled more than 21,603 patients to track the number of post-stroke vascular events they experienced during a three-month follow up period. Vascular events include ischemic strokes, hemorrhagic strokes, heart attacks, or death do to one of these occurrences. Roughly one-third of the participants were women and the average age of patients was 67.

The number of patients receiving each treatment was roughly the same, with 11,054 receiving AI-based stroke care guidance, and 10,549 receiving care based on a neurologist’s assessment and recommendations. Neurologists in the hospitals employing the AI-based clinical decision support tool were trained on the system before the trial began.

Key findings of the study included:

  • AI-based clinical decision support system reduced the chances of new vascular events by 25.6% during the three-month period after the initial stroke.
  • AI guidance also improved stroke care quality with patients more likely to be treated with guideline-directed medical therapy.
  • At three months, participants treated at the hospitals using AI support experienced fewer total vascular events compared to people receiving standard post-stroke evaluation and treatment (2.9% vs 3.9%).
  • There were no statistically significant differences in physical disability levels between patients in either the AI-guided care or the standard care group at three months, as assessed using a modified Rankin Scale Score—a tool used to determine levels of disability in people who have experienced a stroke.

“The reduction in new vascular events is a significant finding because it shows that AI has the potential to make a real difference in stroke care and benefit this large population of stroke survivors,” said Li. “In the future, we hope to have more AI applications validated through clinical research and hope that the clinical decision support system can be expanded to include more aspects of stroke care, including reperfusion therapy and long-term secondary prevention, rehabilitation, and so on.”

One limitation of the study was that the hospitals and not patients were randomized for either the AI-based stroke care or standard care. This raises the question of variability in care patterns from hospital to hospital that may have impacted the results. The research team also noted that their research only followed patients for three months after their initial stroke, so new research should focus on following patients for longer periods to find whether these care improvements can be sustained.

Also of Interest