Risk Prediction Model for Cerebrovascular Events in Carotid Artery Stenosis

Deep Learning-based Risk Prediction Model for Cerebrovascular Events in Patients With Carotid Artery Stenosis

Atherosclerotic carotid artery stenosis is a major cause of stroke, and early identification of high-risk patients combined with surgical intervention can significantly reduce stroke risk. Currently, stroke risk assessment in patients with carotid artery stenosis primarily relies on imaging indicators such as plaque morphology, composition, and degree of stenosis, with less emphasis on indicators directly related to inflammation, hemodynamics, and plaque instability. Certain circulating metabolites are closely linked to plaque progression and are direct risk factors for stroke. However, there is a lack of stroke risk prediction models for patients with carotid stenosis that incorporate these indicators, and the ability to identify high-risk patients needs improvement.

This study proposes using deep learning technology to integrate multidimensional data from plaque imaging, fluid dynamics, circulating metabolomics, and proteomics to construct an accurate prediction model for cerebrovascular events in patients with carotid artery stenosis. Additionally, it aims to explore markers of plaque instability characteristics based on plaque pathology. The study is expected to provide a basis for identifying high-risk patients with carotid artery stenosis, thereby laying the foundation for reducing stroke risk and improving long-term patient outcomes.

Study Overview

• Status: Enrolling by invitation
• Conditions: Carotid Stenosis
• Intervention / Treatment: Diagnostic test: Plasma; Diagnostic test: carotid high-resolution magnetic resonance imaging

• Study Type: Observational
• Enrollment (Estimated): 300

Contacts and Locations

Study Locations

• China
  • Beijing
    • Beijing, Beijing, China, 100070
      • Beijing Tiantan Hospital

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: Child; Adult; Older Adult
• Accepts Healthy Volunteers: No

• Sampling Method: Non-Probability Sample

Study Population

All patients who met the enrollment criteria at Beijing Tiantan Hospital.

Description

Inclusion Criteria:

• Patients diagnosed with atherosclerotic carotid stenosis;
• Those who signed informed consent and volunteered to participate in this study.

Exclusion Criteria:

• Patients with combined severe stenosis of intracranial arteries;
• Patients with combined cardiogenic embolism, vasculitis, entrapment aneurysm and other related cerebral infarction;
• Combination of tumors, rheumatic immune system diseases, hematologic diseases and other diseases that change blood metabolism and proteomic characteristics;
• There are contraindications to magnetic resonance scanning and allergy to gadolinium contrast agent;
• Inability to cooperate in completing the relevant examinations.

Study Plan

How is the study designed?

Number of groups / cohorts

2

Cohorts and Interventions

Group / Cohort	Intervention / Treatment
high risk; Patients with cerebrovascular events within six months, including i. cerebral infarction in the middle cerebral artery territory on the side of carotid stenosis; ii. transient ischemic attack symptoms (including motor and sensory) in the hemisphere on the side of stenosis; and iii. transient amaurosis on the side of stenosis. This indicates an unstable condition and such patients are defined as high-risk carotid stenosis patients.	Diagnostic test: Plasma; Plasma levels of metabolites and some proteins will be further determined; Diagnostic test: carotid high-resolution magnetic resonance imaging; Define plaque composition and morphological characteristics
low risk; Patients without cerebrovascular events within six months are defined as low-risk carotid stenosis patients.	Diagnostic test: Plasma; Plasma levels of metabolites and some proteins will be further determined; Diagnostic test: carotid high-resolution magnetic resonance imaging; Define plaque composition and morphological characteristics

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Number of Patients with Cerebrovascular Events	Patients will be categorized as having a cerebrovascular event if they meet one of the following indicators: i. cerebral infarction in the middle cerebral artery territory on the side of carotid stenosis; ii. transient ischemic attack symptoms (including motor and sensory) in the hemisphere on the side of stenosis; and iii. transient amaurosis on the side of stenosis.	Within six months from the date of consultation

Collaborators and Investigators

• Sponsor: Beijing Tiantan Hospital
• Collaborators: Beijing Neurosurgical Institute
• Investigators: Principal Investigator: Yan Zhang, MD, Beijing Neurosurgical Institution

Study record dates

Study Major Dates

• Study Start (Actual): April 15, 2024
• Primary Completion (Estimated): October 31, 2026
• Study Completion (Estimated): December 31, 2026

Study Registration Dates

• First Submitted: June 5, 2024
• First Submitted That Met QC Criteria: June 5, 2024
• First Posted (Actual): June 11, 2024

Study Record Updates

• Last Update Posted (Actual): June 13, 2024
• Last Update Submitted That Met QC Criteria: June 11, 2024
• Last Verified: June 1, 2024

More Information

Terms related to this study

• Keywords: stroke; carotid stenosis; Risk prediction model; Deep-learning
• Additional Relevant MeSH Terms: Cardiovascular Diseases; Vascular Diseases; Cerebrovascular Disorders; Brain Diseases; Central Nervous System Diseases; Nervous System Diseases; Arterial Occlusive Diseases; Pathological Conditions, Anatomical; Carotid Artery Diseases; Carotid Stenosis; Constriction, Pathologic
• Other Study ID Numbers: KY2024-070-02; 2024-2-1072 (Other Identifier: Capitals Funds for Health Improvement and Research)

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: NO

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No