A clinical decision-support system (CDSS) used with patients with acute ischemic stroke decreased the incidence of new vascular events at three months, researchers have reported.
The tool “offers a more efficient and scalable method for improving stroke care and prognosis, with the added benefits of lower cost and greater sustainability,” noted a team led by senior author Zixiao Li, MD, PhD, of Beijing Tiantan Hospital in China. The group’s findings were published March 20 in the BMJ.
Stroke is a major cause of disability and death around the world, and China bears a heavy burden, with more than three million new strokes per year, the investigators wrote. Although AI in healthcare has gained “widespread attention, especially in assisting with disease diagnosis, treatment, prognosis, and enhancing clinical decision-making,” AI tools for stroke have not been carefully tested.
“CDSS may provide a new way to facilitate clinical decision-making and consequently care quality and clinical outcomes in patients with ischaemic cerebrovascular disease,” the group wrote.
Li and colleagues analyzed data from the GOLDEN BRIDGE II trial, including information from 77 hospitals and 21,603 patients with acute ischaemic stroke. Patients were admitted within seven days after symptom onset between January 2021 and June 2023. Of these 77 hospitals, 38 were randomly assigned to an intervention group (11,054 patients) and 39 to a control group (10,549 patients). The intervention group received stroke CDSS support, which consisted of AI-assisted imaging analysis, classification of stroke causes, and treatment recommendations. Hospitals in the control group offered usual care without aid from the CDSS.
The study’s primary outcome was a new vascular event (that is, a composite of ischemic or hemorrhagic stroke, myocardial infarction, or vascular death) within three months after initial symptom onset. Secondary outcomes included this composite measure as well as performance measures for acute ischemic stroke care quality, a new vascular event at six and 12 months, disability assessment (modified Rankin Scale score of 3 to 6 [moderate disability to death]), and all-cause mortality at three, six, and 12 months. The group also tracked safety outcomes such as moderate or severe bleeding events and all bleeding events at three, six, and 12 months.
Li’s team reported the following:
- New vascular events at three months occurred in 2.9% of patients in the intervention group compared with 3.9% in the control group (adjusted hazard ratio [AHR] of 0.74, p = 0.01).
- Patients in the intervention group were more likely to have a higher composite measure (91.4% vs. 89.8%, AHR of 1.21, p < 0.001).
- Incidence of new vascular events was lower in the intervention group at 12 months (4% vs. 5.5%, AHR of 0.73, p = 0.02).
- The team found no significant differences in disability and all-cause mortality, and moderate or severe bleeding, and all bleeding did not differ between the two groups.
The study findings could translate to better care for stroke patients, according to the researchers.
“The stroke CDSS offers a promising approach to providing high-quality care for patients with acute ischemic stroke admitted to hospital, particularly for resource-constrained regions with a heavy burden of cerebrovascular diseases like China,” they concluded.
Access the full study here.