Effect of a clinical decision support system on stroke care quality and outcomes in patients with acute ischaemic stroke (GOLDEN BRIDGE II): cluster randomised clinical trial.

CDSS intervention significantly reduced new vascular events at three months compared to usual care.

• New vascular events at three months occurred in 2.9% (320/11,054) in the intervention group compared with 3.9% (416/10,549) in the control group.
• Adjusted hazard ratio 0.74, 95% CI 0.58 to 0.93, P=0.01.
• The CDSS intervention effect remained significant in the cluster level analysis (-0.01, -0.02 to -0.004, P=0.003).
• The primary outcome was a composite of ischaemic stroke, haemorrhagic stroke, myocardial infarction, and vascular death within three months after initial symptom onset.

CDSS intervention significantly improved stroke care quality as measured by the composite measure of evidence-based performance measures.

• Patients in the intervention group were more likely to have a higher composite measure: 91.4% (77,049/84,276) vs 89.8% (70,794/78,834).
• Adjusted odds ratio 1.21, 95% CI 1.17 to 1.26, P<0.001.
• The composite measure reflects evidence-based performance measures for acute ischaemic stroke care quality.

CDSS intervention significantly reduced new vascular events at 12 months.

• New vascular events at 12 months were 4.0% (440/11,054) in the intervention group vs 5.5% (576/10,549) in the control group.
• Adjusted hazard ratio 0.73, 95% CI 0.56 to 0.95, P=0.02.
• This finding supports a durable long-term benefit of the CDSS intervention.

No significant differences in disability or all-cause mortality were observed between the intervention and control groups.

• Disability was defined as modified Rankin Scale score 3-6.
• Disability and all-cause mortality were assessed at three, six, and 12 months.
• No significant differences were found in disability and all cause mortality at any time point.

Safety outcomes of moderate or severe bleeding and all bleeding events did not differ significantly between the two groups.

• Moderate or severe bleeding, and all bleeding were assessed at three, six, and 12 months.
• No significant differences were found between intervention and control groups for any bleeding outcomes.
• This indicates the CDSS intervention did not increase bleeding risk.

The trial enrolled 21,603 patients with acute ischaemic stroke across 77 hospitals in China using a cluster randomised design.

• 38 hospitals were randomised to the intervention group and 39 to the control group.
• 11,054 patients were enrolled in the intervention group and 10,549 in the control group.
• Patients were admitted within seven days after symptom onset.
• Enrollment occurred from January 2021 to June 2023.

The CDSS intervention included artificial intelligence assisted imaging analysis, classification of stroke causes, and evidence-based treatment recommendations.

• Hospitals in the intervention group received stroke CDSS support with these three components.
• Hospitals in the control group provided usual care.
• The system was designed to support evidence-based stroke management decisions.