Study: AI-Based Recommendations Can Reduce Recurrent Strokes, Heart Attacks

Artificial intelligence (AI) recommendations resulted in fewer recurrent strokes, heart attacks, or vascular death within 3 months of a previous ischemic stroke.

Artificial intelligence (AI) recommendations resulted in fewer recurrent strokes, heart attacks, or vascular death within 3 months of a previous ischemic stroke, according to preliminary late-breaking data presented at the American Stroke Association’s International Stroke Conference 2024. The conference was held in Phoenix, Arizona from February 7 to February 9, 2024.

fizkes - stock.adobe.com

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

About The GOLDEN BRIDGE II Trial

Trial Name: An AI-Based CDSS for Integrated Management of Patients With Acute Ischemic Stroke

ClinicalTrial.gov ID: NCT04524624

Sponsor: Beijing Tiantan Hospital

Estimated Completion Date: June 2023

Investigators of the GOLDEN BRIDGE II (NCT04524624) clinical trial included 77 hospitals in China, which reported diagnoses and treatment for individuals with ischemic stroke. Data were collected from January 2021 and June 2023. The hospitals were randomly assigned either AI-based recommendations or recommendations from the patient’s care team. The AI system used brain imaging scans from patients, which were interpreted by AI with knowledge of stroke diagnosis, stroke classification, guideline-recommended treatment, and strategies to prevent a second stroke, according to the press release. Neurologists tested the AI-based clinical decisions before the study began. Stroke care quality was measured by recognized composite scores of performance measures, including 9 measures at the beginning of hospitalization and 5 at discharge, according to the press release.

A total of 21,603 individuals were included in the study, with approximately two-thirds male and a mean age of 67 years. There were 11,054 who received the AI treatment and 10,549 who received the usual care. Almost all individuals completed the 3-month follow-up, according to the press release. Investigators measured the number of ischemic strokes, hemorrhagic strokes, heart attacks, and vascular-related deaths.

“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,” Li said in the press release.

The investigators found that the AI-based decisions reduced the chances of new vascular events by approximately 25.6% during the 3-month period after initial stroke. Additionally, individuals were more likely to be treated with guideline-recommended therapy using the AI-based decisions, improving stroke care quality, according to the press release. Furthermore, at 3 months, individuals who were treated with AI-based decisions had fewer total vascular events compared to those receiving the standard of care at 2.9% and 3.9%, according to the results.

Investigators reported that there were no statistically significant different physical disability levels in either group at 3 months when using the Rankin Scale Score, which is used to determine the level of disability a patient experiences after a stroke.

“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. At the same time, we also hope that AI applications can be broadened to apply to other health conditions,” Li said in the press release.

Reference

AI-based system to guide stroke treatment decisions may help prevent another stroke. News release. EurekAlert. February 8, 2024. Accessed February 12, 2024. https://newsroom.heart.org/news/ai-based-system-to-guide-stroke-treatment-decisions-may-help-prevent-another-stroke