AI-Driven CTA Reconstruction for Intracranial LVO

NCT06645405 | Recruiting DMC

• 1 other identifier: SMART-AI
• Study Type: interventional
• Target: 174
• Locations: 1 country
• Sites: 2

Brief Summary

Acute ischemic stroke (AIS) caused by intracranial large vessel occlusion (LVO) in the anterior circulation significantly contributes to stroke-related disability and mortality. Recent randomized controlled trials have demonstrated substantial benefits of endovascular thrombectomy (EVT) when patients are appropriately triaged beforehand. However, accurately orienting the 'missed segment' during EVT remains challenging. Guide-wires often fail to navigate through the occlusion or are mistakenly directed into the small tranches or even cause vessel rupture. To address this clinical need, the investigators developed an artificial intelligence (AI) algorithm to automate the reconstruction of CT angiography (CTA), focusing on the occluded LVO segment. To evaluate the clinical utility of this AI algorithm, the investigators propose a prospective, stepped-wedge cluster-randomized study to determine whether integrating our AI algorithm into AIS care flow can reduce the time for first pass of the thrombus by improving the visualization of the occluded segment on CTA. Physicians will assess patient eligibility for thrombectomy, and all selected patients will receive standard care according to current guidelines. This approach is expected to enhance patient treatment outcomes for endovascular thrombectomy by leveraging readily available data.

Conditions

Acute Ischemic Stroke; Artificial Intelligence (AI); Endovascular Thrombectomy; CT Angiography

Outcome Measures

Primary Outcomes (1)

• AFAT

  The time from target angiography to the initiation of first thrombectomy attempt (angiography-to-first-attempt time \[AFAT\])

  Immediately after EVT

Secondary Outcomes (8)

• PRT

  Immediately after EVT

• IPT

  Immediately after EVT

• IRT

  Immediately after EVT

• The rate of successful flow restoration immediately after EVT

  Immediately after EVT

• The rate of symptomatic intracerebral hemorrhage within 24 hours post-EVT

  24 hours post-EVT

Study Arms (2)

Control

NO INTERVENTION

No AI reconstruction

AI software

EXPERIMENTAL

An AI approach will be used for automated segmentation and reconstruction of CTA for intracranial LVO. Physicians begin to receive reconstructions and have the authority to view AI-activated images. Diagnosis and treatment decisions will be based on the clinical evaluation and review of the images by the treating physician, as per routine standard of care.

Behavioral: AI algorithm

Interventions

AI algorithm BEHAVIORAL

Artificial intelligence algorithms in the automated reconstruction of intracranial large vessel occlusion (LVO)

Also known as: AI approach

AI software

Eligibility Criteria

• Age: 18 Years - 95 Years
• Sex: all
• Healthy Volunteers: No
• Age Groups: Adult (18-64), Older Adult (65+)

You may qualify if:

• Male or Female, 18 years of age or older.
• Patients who present with signs and/or symptoms concerning acute ischemic stroke.
• Patients who undergo noncontrast CT and CT angiography imaging.
• Patients determined to have an intracranial large vessel occlusion (including the internal carotid artery, middle cerebral artery M1 segment, and M2 segment), and eligible for endovascular treatment.

You may not qualify if:

• \) CT imaging with severe motion artifacts.

Sponsors & Collaborators

• Shanghai Jiao Tong University Affiliated Sixth People's Hospital: lead

Study Sites (2)

Shanghai Sixth People's Hospital

Shanghai, Shanghai Municipality, 200233, China

ACTIVE NOT RECRUITING

Shanghai Sixth People's Hospital

Shanghai, 200023, China

RECRUITING

MeSH Terms

Conditions

Ischemic Stroke

Condition Hierarchy (Ancestors)

Stroke; Cerebrovascular Disorders; Brain Diseases; Central Nervous System Diseases; Nervous System Diseases; Vascular Diseases; Cardiovascular Diseases

Central Study Contacts

Yueqi Zhu

CONTACT

+86-21-66301136; zhuyueqi@hotmail.com

Study Design

• Study Type: interventional
• Phase: not applicable
• Allocation: RANDOMIZED
• Masking: NONE
• Purpose: SUPPORTIVE CARE
• Intervention Model: SEQUENTIAL
• Sponsor Type: OTHER
• Responsible Party: PRINCIPAL INVESTIGATOR
• PI Title: MD

Study Record Dates

• First Submitted: October 9, 2024
• First Posted: October 16, 2024
• Study Start: October 20, 2024
• Primary Completion: December 31, 2025
• Study Completion: December 31, 2025
• Last Updated: October 16, 2024

Record last verified: 2024-10

Locations

CN (2)