Predicting stroke risk in patients with chronic intracranial arterial occlusion using advanced imaging techniques

Developing and Validating a Prediction Model for Bidirectional Stroke Risk in Chronic Intracranial Arterial Occlusion Based on Multimodal CT Radiomic Features of Key Brain Regions.

This study is trying to see if a new computer model can help predict stroke risk in patients with blocked brain arteries who don't have any symptoms.

Quick facts

• Study type: Observational
• Enrollment: 1000 (estimated)
• Ages: 18 Years to 80 Years
• Sex: All
• Sponsor: Beijing Hospital (Government)
• Locations: 2 sites (Beijing, Beijing and 1 other locations)
• Trial ID: NCT06066593 on ClinicalTrials.gov

What this trial studies

This project aims to develop a machine learning-based model to assess long-term stroke risk in asymptomatic patients with chronic intracranial arterial occlusion. It will utilize multimodal CT scans to create a deep learning segmentation model for key brain regions, including the basal ganglia and lobes of the brain. The study will involve training the model on retrospective data and validating it with prospective data to ensure accuracy in predicting both ischemic and hemorrhagic stroke risks. The research seeks to enhance the understanding of neuroimaging features related to stroke in this patient population.

Who should consider this trial

Good fit: Ideal candidates include asymptomatic patients aged 18 to 80 diagnosed with chronic intracranial arterial occlusion.

Not a fit: Patients with acute intracranial arterial occlusive disease or a history of ischemic or hemorrhagic stroke may not benefit from this study.

Why it matters

Potential benefit: If successful, this study could provide a more accurate prediction of stroke risk, allowing for better patient management and preventive strategies.

How similar studies have performed: While the use of machine learning in neuroimaging is a growing field, this specific approach to predicting stroke risk in chronic intracranial arterial occlusion is relatively novel.

Eligibility criteria

Inclusion Criteria:

* Diagnosed with chronic intracranial arterial occlusion.
* Asymptomatic or with a history of only transient ischemic attacks (TIAs).
* The age of the patient falls within the range of 18 to 80 years old.
* Willing to undergo both perfusion CT scans and magnetic resonance imaging (MRI).

Exclusion Criteria:

* Acute intracranial arterial occlusive disease.
* History of either ischemic or hemorrhagic stroke.
* Allergies to contrast agents or conditions such as claustrophobia that prevent completion of imaging data acquisition.

Where this trial is running

Beijing, Beijing and 1 other locations

• Beijing Tiantan Hospital — Beijing, Beijing, China (Recruiting)
• Beijing Hospital — Beijing, Beijing, China (Recruiting)

Study contacts

• Study coordinator: Shaosen Zhang, Doctor

Conditions Stroke, Ischemic; Stroke Hemorrhagic; Chronic intracranial arterial occlusion; Multimodal CT; Radiomics; Machine Learning; Deep Learning