Blinded randomized test of an AI tool to find brain aneurysms on head CTA

Assessing the Impact of an Artificial Intelligence-Based Model for Intracranial Aneurysm Detection in CT Angiography on Patients' Diagnosis and Outcomes: The IDEAL Study - A Web-Based Multicenter, Double-Blinded Randomized Controlled Trial

This trial will test whether an AI tool that helps read head CT angiograms can improve detection of brain aneurysms in adults having CTA scans.

Quick facts

• Phase: Not applicable
• Study type: Interventional
• Enrollment: 6450 (estimated)
• Ages: 18 Years and up
• Sex: All
• Sponsor: Jinling Hospital, China (Academic / other)
• Locations: 21 sites (Hefei, Anhui and 20 other locations)
• Trial ID: NCT06118840 on ClinicalTrials.gov

What this trial studies

This is a multicenter, prospective, double-blind randomized trial enrolling more than 6,450 adults who undergo head CT angiography at 21 hospitals across more than 10 provinces in China. Patients' CTA images are randomized 1:1 to a True-AI–aided diagnostic workflow or a Sham-AI workflow (sham has near-zero sensitivity but similar specificity), with both patients and radiologists blinded to allocation. The primary outcomes are sensitivity and specificity for detecting intracranial aneurysms, and secondary outcomes include detection of other intracranial lesions, interpretive workload, downstream resource use and treatments, 12-month imaging follow-up, patient quality of life, aneurysm-related events, and cost-effectiveness. The trial is designed to measure both diagnostic performance and the short- and long-term impact of integrating AI into routine CTA practice.

Who should consider this trial

Good fit: Adults scheduled for head CTA at a participating site who can give informed consent and do not have CTA contraindications or very severe baseline disability are eligible.

Not a fit: People under 18, those with contraindications to CTA, patients with incomplete or poor-quality CTA images, or those with a modified Rankin Scale score >3 are excluded and would not receive benefit from this intervention.

Why it matters

Potential benefit: If successful, the AI approach could help clinicians detect more aneurysms earlier and reduce missed diagnoses, potentially improving treatment decisions and patient outcomes.

How similar studies have performed: Previous retrospective and observational studies have shown AI can improve aneurysm detection on CTA, but prospective double-blind randomized evaluations of clinical impact are uncommon.

Eligibility criteria

Inclusion Criteria:

* Adult inpatients and outpatients who are scheduled for head CTA scanning.

Exclusion Criteria:

* Age under 18 years.
* Patients with contraindications to CTA.
* Modified Rankin Scale (mRS) score \> 3.
* Refuse to sign informed consent.
* Participation in other clinical studies of intracranial aneurysms.
* Patients with failed head CTA scanning or incomplete image data, or poor image quality.

Where this trial is running

Hefei, Anhui and 20 other locations

• The First Affiliated Hospital of University of Science and Technology of China — Hefei, Anhui, China (Recruiting)
• The First Affiliated Hospital of Wannan Medical College — Wuhu, Anhui, China (Recruiting)
• Guizhou Provincial People's Hospital — Guiyang, Guizhou, China (Recruiting)
• First Affiliated Hospital of Zhengzhou University — Zhengzhou, Henan, China (Recruiting)
• Shiyan People's Hospital — Shiyan, Hubei, China (Recruiting)
• Research Institute Of Medical Imaging Jinling Hospital — Nanjing, Jiangsu, China (Recruiting)
• Affiliated Hospital of Xuzhou Medical University — Xuzhou, Jiangsu, China (Recruiting)
• The First Hospital of Jilin University — Changchun, Jilin, China (Recruiting)
• Shandong Provincial Hospital Affiliated to Shandong First Medical University — Jinan, Shandong, China (Recruiting)
• Yidu Central Hospital Affiliated to Shandong Second Medical University — Weifang, Shandong, China (Recruiting)
• The First Affiliated Hospital of Kunming Medical University — Kunming, Yunnan, China (Recruiting)
• Hainan General Hospital — Haikou, China (Recruiting)
• The First People's Hospital of Kashgar Region — Kashgar, China (Recruiting)
• University Second Hospital — Lanzhou, China (Recruiting)
• First People's Hospital of Lianyungang — Lianyungang, China (Recruiting)
• Ma'anshan People's Hospital — Ma’anshan, China (Recruiting)
• BenQ Medical Center, Affiliated BenQ Hospital of Medical School, Nanjing Medical University — Nanjing, China (Recruiting)
• Long Gang Central Hospital of Shenzhen — Shenzhen, China (Recruiting)
• The Affiliated Suqian First Hospital of Nanjing Medical University — Suqian, China (Recruiting)
• Tianjin Medical University General Hospital — Tianjin, China (Recruiting)
• General Hospital of Ningxia Medical University — Yinchuan, China (Recruiting)

Study contacts

• Principal investigator: Trial Manager — Jinling Hospital, Affiliated Hospital of Medical School, Nanjing University
• Study coordinator: Longjiang Zhang, MD

Conditions Intracranial Aneurysm; CT Angiography; Deep Learning; Double Bind Interaction