Actively Recruiting
AI-Based Diagnostic Model Development for Branch Atheromatous Disease-Related Stroke Using Clinical and Imaging Data in Acute Ischemic Stroke Patients
Led by Peking Union Medical College Hospital · Updated on 2026-07-09
1602
Participants Needed
11
Research Sites
47 weeks
Total Duration
AI-Summary
What This Trial Is About
Branch atheromatous disease BAD-related stroke is a significant subtype of acute ischemic stroke affecting small penetrating arteries, often leading to early neurological worsening. Diagnosing BAD-related stroke early is difficult due to non-specific symptoms and the need for combined clinical and imaging assessment. This multicenter prospective observational study aims to develop and validate artificial intelligence AI models to improve early screening and diagnosis of BAD-related stroke by analyzing multiple clinical and imaging data sources. Participants with acute ischemic stroke will be enrolled within one week of symptom onset and receive routine clinical care as decided by their doctors. The study collects extensive data including demographics, neurological assessments, laboratory tests, heart and carotid ultrasounds, various brain imaging techniques, and treatment information. Participants will be classified into BAD-related stroke or non-BAD stroke cohorts by an independent committee based on predefined diagnostic criteria. The AI models will be developed and tested for their accuracy in identifying BAD-related stroke using both early clinical data and comprehensive imaging information. Throughout the study, participants will undergo standard clinical assessments and imaging as part of their usual care. Researchers will evaluate the AI models diagnostic accuracy by comparing model predictions to expert clinical-imaging diagnoses. The primary outcome is the overall diagnostic accuracy of the AI-assisted model within seven days of symptom onset. Secondary outcomes include accuracy of the early screening model using clinical data within 24 hours of admission. The study does not assign treatments patient care follows local guidelines and physician decisions. The study is expected to complete by the end of 2028.
CONDITIONS
Brief Title
Early Identification and Diagnosis of BAD-related Stroke
Research Team
S
Shengde Li, MD
Not the Right Trial for You?
Explore thousands of other clinical trials that might be a better match.
Sign up to get personalized trial recommendations delivered to your inbox.
Already have an account? Log in here