AI-Based System to Guide Stroke Treatment Decisions Reduces Chances of New Vascular Events

44 million stroke-related deaths globally in 2021. Rapid and accurate evaluation and treatment decisions are crucial in such cases to restore blood flow and reduce brain damage. Now, an artificial intelligence (AI) system designed to assist in making treatment decisions for stroke patients has shown promise. It has improved the quality of stroke care and reduced the incidence of recurrent strokes, heart attacks, and vascular deaths among stroke survivors within three months after experiencing a stroke.

In a research study conducted across hospitals in China, researchers at Capital Medical University (Beijing, China) compared the effectiveness of AI-based evaluation and treatment for ischemic stroke patients with standard care provided by stroke teams. The findings, presented at the International Stroke Conference 2024 held by the American Stroke Association (Dallas, TX, USA), revealed that ischemic stroke survivors who received AI-based care recommendations experienced fewer recurrent strokes, heart attacks, or vascular deaths within three months compared to those who received traditional stroke treatment.

The clinical trial, named GOLDEN BRIDGE II, involved 77 hospitals in China. These hospitals were randomly assigned to provide diagnosis and treatment for ischemic stroke patients based either on AI system recommendations or on assessments and recommendations by the hospitals' stroke care teams. The AI system used in the trial combined participants' brain imaging scans, interpreted by AI, with established clinical knowledge for stroke diagnosis, classification, and guideline-recommended treatment and strategies for preventing secondary strokes. The study, which included over 20,000 participants, measured the number of vascular events – such as ischemic and hemorrhagic strokes, heart attacks, or vascular-related deaths – during a three-month follow-up period after the initial ischemic stroke.

The use of the AI-based clinical decision support system was found to reduce the risk of new vascular events by 25.6% in the three months following the initial stroke. This approach also enhanced the quality of stroke care, with patients more likely to receive treatment in line with medical guidelines. After three months, participants treated in AI-supported hospitals experienced fewer total vascular events compared to those receiving standard post-stroke evaluation and treatment (2.9% vs. 3.9%). No significant differences in physical disability levels were observed between the two groups when assessed using the modified Rankin Scale Score, a tool for determining disability levels in stroke patients.

“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 study author Zixiao Li, M.D., Ph.D. “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.”

Related Links:
Capital Medical University
American Stroke Association