IDEAL Study: Blinded RCT for the Impact of AI Model for Cerebral Aneurysms Detection on Patients' Diagnosis and Outcomes (IDEAL)

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 study (IEDAL study) intends to prospectively enroll more than 6800 patients who will undergo head CT angiography (CTA) scanning in the outpatient clinic. It will be carried out in 25 hospitals in more than 10 provinces in China. The patient's head CTA images will be randomly assigned to the True-AI and Sham-AI group with a ratio of 1:1, and the patients and radiologists are unaware of the allocation. The primary outcomes are sensitivity and specificity of detecting intracranial aneurysms. The secondary outcomes focus on the prognosis and outcomes of the patients.

Study Overview

• Status: Not yet recruiting
• Conditions: Intracranial Aneurysm; Deep Learning; CT Angiography; Double Bind Interaction
• Intervention / Treatment: Device: True-AI-integrated intracranial aneurysms diagnosis strategy; Device: Sham-AI-integrated intracranial aneurysms diagnosis strategy

Detailed Description

A multicenter, prospective, double-blind, randomized controlled trial will be conducted (IDEAL study). Patients who are scheduled to undergo cranial CT angiography (CTA) scanning will be randomly divided into two groups with a ratio of 1:1, one of the group will be assigned to True-AI aided intracranial aneurysms diagnosis strategy (True-AI group) and the other will be assigned to Sham-AI aided intracranial aneurysms diagnosis strategy (Sham-AI group, which has a sensitivity close to 0% and a similar specificity to True-AI). The primary outcomes are diagnostic sensitivity and specificity of detecting aneurysms. Secondary endpoints include other diagnostic performance indexes for intracranial aneurysms; diagnostic performances for other intracranial lesions for intracranial arterial stenosis, occlusion, and intracranial tumors; detection rates of intracranial lesions according to Radiology Reports; workload of head CTA interpretation; resource use; treatment-related indexes during patient follow-up (e.g. clinical follow-up, hospitalization, rate of patients undergoing DSA); life quality; outcomes of aneurysm-related events; repeat head CTA or MRA at 12-month follow; cost-effectiveness analysis between intervention and control arm to evaluate the short- and longterm influence of AI system to the routine practice and patients' prognosis and outcomes.

• Study Type: Interventional
• Enrollment (Estimated): 6800
• Phase: Not Applicable

Contacts and Locations

• Study Contact: Name: Longjiang Zhang, MD; Phone Number: +8613405833176; Email: kevinzhlj@163.com

Study Locations

• China
  • Jiangsu
    • Nanjing, Jiangsu, China, 210018
      • Research Institute Of Medical Imaging Jinling Hospital

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: Adult; Older Adult
• Accepts Healthy Volunteers: Yes

Description

Inclusion Criteria:

• Patients in the outpatient setting who are scheduled to undergo head CTA scanning in 25 hospitals in more than 10 provinces in China.

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.

Study Plan

How is the study designed?

Design Details

• Primary Purpose: Diagnostic
• Allocation: Randomized
• Interventional Model: Parallel Assignment
• Masking: Quadruple

Number of Arms

2

Arms and Interventions

Participant Group / Arm	Intervention / Treatment
Experimental: True-AI-integrated intracranial aneurysms diagnosis strategy; For patients who underwent head CTA and assigned to True-AI group, they will be diagnosed by a radiologist who are aided by the True-AI-integrated intracranial aneurysms diagnosis strategy.	Device: True-AI-integrated intracranial aneurysms diagnosis strategy; The True-AI deep-learning based model for intracranial aneurysms detection had a patient-wise sensitivity, lesion-wise sensitivity and specificity of 0.96, 0.87, and 0.80 in the internal validation dataset.
Sham Comparator: Sham-AI-integrated intracranial aneurysms diagnosis strategy; For patients who underwent head CTA and assigned to Sham-AI group, they will be diagnosed by a radiologist who are aided by the Sham-AI-integrated intracranial aneurysms diagnosis strategy. To mimic the True-AI, the Sham-AI had a sensitivity close to 0% and a similar specificity to the True-AI.	Device: Sham-AI-integrated intracranial aneurysms diagnosis strategy; The Sham-AI deep-learning based model for intracranial aneurysms detection is designed to have a sensitivity close to 0% and a similar specificity to the True-AI. In the internal validation dataset, the Sham-AI had a patient-wise sensitivity, lesion-wise sensitivity, specificity of 0.02, 0.01, and 0.80, respectively.

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
To compare diagnostic sensitivity of intracrnial aneurysms between intervention and control arm.	The proportion of examinations in which at least one aneurysm is discovered and indicated among groundtruth aneurysms.	6 months.
To compare diagnostic specificity of intracrnial aneurysms between intervention and control arm.	The proportion of examinations in which no aneurysms are spotted by the reader among groundtruth non-aneurysms.	6 months.

Secondary Outcome Measures

Outcome Measure	Measure Description	Time Frame
To compare other diagnostic performances for intracranial aneurysms between intervention and control arm.	To compare accuracy, lesion-wise sensitivity, positive predictive value and negative predictive value for intracranial aneurysms between intervention and control arm.	6 months.
To compare diagnostic performances for other intracranial lesions between intervention and control arm.	The sensitivity, specificity, accuracy, positive predictive value and negative predictive value for intracranial arterial stenosis, occlusion, and intracranial tumors are compared between intervention and control arm.	6 months.
To compare detection rates of intracranial lesions according to Radiology Reports between intervention and control arm.	Detection rates of intracranial aneurysms, intracranial arterial stenosis, occlusion, and intracranial tumors according to Radiology Reports are compared between intervention and control arm.	6 months.
To assess the workload of head CT angiography interpretation.	Time of interpreting head CT angiography images, number of consensus meeting are compared between intervention and control arm.	6 months.
To assess resource use.	The number of care encounters (in-person) during follow-up, total number of outpatient encounters for aneurysm referral, total number of cerebral artery disease testing are compared between intervention and control arm.	At 3-month and 12-month follow-up.
Rate of patients of subsequent hospitalization during patient follow-up.	Rate of patients of subsequent hospitalization is compared between intervention and control arm.	At 3-month and 12-month follow-up.
In-hospital mortality rate during patient follow-up.	In-hospital mortality rate is compared between intervention and control arm.	At 3-month and 12-month follow-up.
Morbidity (modified Rankin Score ≥ 3) from intracranial haemorrhage or treatment during patient follow-up.	Morbidity (modified Rankin Score ≥ 3) from intracranial haemorrhage or treatment is compared between intervention and control arm.	At 3-month and 12-month follow-up.
Length of hospital stay during patient follow-up.	Length of hospital stay is compared between intervention and control arm.	At 3-month and 12-month follow-up.
Rate of hospitalization for intracranial aneurysms during patient follow-up.	Rate of hospitalization for intracranial aneurysms is compared between intervention and control arm.	At 3-month and 12-month follow-up.
Rate of patients undergoing digital subtraction angiography (DSA) during patient follow-up.	Rate of patients undergoing digital subtraction angiography (DSA) is compared between intervention and control arm.	At 3-month and 12-month follow-up.
Detection rate of intracranial aneurysms among digital subtraction angiographys (DSA) during patient follow-up.	Detection rate of intracranial aneurysms among digital subtraction angiographys (DSA) is compared between intervention and control arm.	At 3-month and 12-month follow-up.
Detection rate of no abnormality among digital subtraction angiographys (DSA) during patient follow-up.	Detection rate of no abnormality among digital subtraction angiographys (DSA) is compared between intervention and control arm.	At 3-month and 12-month follow-up.
Distribution of the methods for aneurysms management (conservative/coil/clip/others) during patient follow-up.	Distribution of the methods for aneurysms management (conservative/coil/clip/others) is compared between intervention and control arm.	At 3-month and 12-month follow-up.
Rates of aneurysm treatment related complications during patient follow-up.	Rate of aneurysm treatment related complications (intraoperative rupture, stroke, et al) is compared between intervention and control arm.	At 3-month and 12-month follow-up.
Rate of recurrence or residual of intracranial aneurysm after surgery during patient follow-up.	Rate of recurrence or residual of intracranial aneurysm after surgery is compared between intervention and control arm.	At 12-month follow-up.
Life quality assessed by EuroQol 5-Dimensional, 5-Level (EQ-5D-5L) during patient follow-up.	Life quality assessed by EuroQol 5-Dimensional, 5-Level (EQ-5D-5L) scores are compared between intervention and control arm, which ranges from 5 to 25, and higher scores mean a worse outcome.	At 3-month and 12-month follow-up.
Restrictions in daily activities assessed by Utrecht Scale for Evaluation of Rehabilitation-Participation (USER-P) scores during patient follow-up.	Restrictions in daily activities assessed by Utrecht Scale for Evaluation of Rehabilitation-Participation (USER-P) scores are compared between intervention and control arm.	At 3-month and 12-month follow-up.
Sleep quality assessed by Pittsburgh Sleep Quality Index (PSQI) during patient follow-up.	Sleep quality assessed by Pittsburgh Sleep Quality Index (PSQI) is compared between intervention and control arm, which ranges from 0 to 21, and higher scores mean a worse outcome.	At 3-month and 12-month follow-up.
Depression Screening assessed by Patient Health Questionnaire-9 (PHQ-9) scores during patient follow-up.	Depression Screening assessed by Patient Health Questionnaire-9 (PHQ-9) scores are compared between intervention and control arm, which ranges from 0 to 27, and higher scores mean a worse outcome.	At 3-month and 12-month follow-up.
Anxiety and depression assessed by Hospital Anxiety and Depression Scale (HADS) scores during patient follow-up.	Anxiety and depression assessed by Hospital Anxiety and Depression Scale (HADS) scores are compared between intervention and control arm, which ranges from 0 to 21, and higher scores mean a worse outcome.	At 3-month and 12-month follow-up.
General health assessed by Short-Form 36 Health Survey (SF-36) scores during patient follow-up.	General health assessed by Short-Form 36 Health Survey (SF-36) scores are compared between intervention and control arm.	At 3-month and 12-month follow-up.
Functional outcome assessed by Modified Rankin Scale (mRS) scores during patient follow-up.	Functional outcome assessed by Modified Rankin Scale (mRS) scores are compared between intervention and control arm, which ranges from 0 to 5, and higher scores mean a worse outcome.	At 3-month and 12-month follow-up.
All-cause mortality during patient follow-up.	All-cause mortality is compared between intervention and control arm.	At 3-month and 12-month follow-up.
Rate of aneurysm growth during patient follow-up.	Rate of aneurysm growth is compared between intervention and control arm.	At 12-month follow-up.
Rate of aneurysm rupture during patient follow-up.	Rate of aneurysm rupture is compared between intervention and control arm.	At 12-month follow-up.
Rate of subarachnoid hemorrhage (SAH) during patient follow-up.	Rate of subarachnoid hemorrhage (SAH) is compared between intervention and control arm.	At 3-month and 12-month follow-up.
Rate of other types of stroke (hemorrhagic stroke, ischemic stroke) during patient follow-up.	Rate of other types of stroke (hemorrhagic stroke, ischemic stroke) is compared between intervention and control arm.	At 3-month and 12-month follow-up.
Mortality of aneurysms-rupture during patient follow-up.	Mortality of aneurysms-rupture is compared between intervention and control arm.	At 3-month and 12-month follow-up.
Morphological change by head CTA or magnetic resonance angiography at the 12-month follow-up.	Morphological change by head CTA or magnetic resonance angiography is assessed.	At 12-month follow-up.

Other Outcome Measures

Outcome Measure	Measure Description	Time Frame
Patient-wise sensitivity and specificity at different centers, provinces, geography areas and levels of physician.	To compare diagnostic performances of patient-wise sensitivity and specificity for intracranial aneurysms between intervention and control arm in subgroups of different centers, provinces, geography areas and physician level.	6 months.
Subgroup analysis of different size (< 5 mm vs. ≥ 5 mm), locations of intracranial aneurysms.	To compare diagnostic performances for intracranial aneurysms between intervention and control arm in subgroups of different size (internal carotid artery vs. middle cerebral artery vs. anterior cerebral artery vs. posterior communication artery vs. anterior communication artery vs. vertebral basilar artery vs. others), locations (internal carotid artery vs. middle cerebral artery vs. anterior cerebral artery vs. posterior communication artery vs. anterior communication artery vs. vertebral basilar artery vs. others) of intracranial aneurysms.	6 months.
Subgroup analysis of different gender (male vs. female), age (≤ 54 years or. >54 years), subarachnoid hemorrhage status (with vs. without SAH) of patients	To compare diagnostic performances for intracranial aneurysms between intervention and control arm in subgroups of different gender (male vs. female), age (≤ 54 years or. >54 years), subarachnoid hemorrhage status (with vs. without SAH) of patients.	6 months.
Patient-wise sensitivity and specificity for patients with previous head digital subtraction angiography or surgery or not.	To compare diagnostic performances of patient-wise sensitivity and specificity for intracranial aneurysms between intervention and control arm in subgroups of patients with previous head angiography or surgery or not.	6 months.
Patient-wise sensitivity and specificity for patients with subsequent head digital subtraction angiography or surgery or not.	To compare diagnostic performances of patient-wise sensitivity and specificity for intracranial aneurysms between intervention and control arm in subgroups of patients with subsequent head angiography or surgery or not.	6 months.
Ethical safety outcomes.	The monthly reported detection rates of intracranial aneurysms, tumors, stenosis, and occlusive are calculated and compared with the reported detection rates in the previous 3 months during the trial.	6 months.
Learning curve of AI-augmented intracranial aneurysm diagnosis.	Dynamic changes in sensitivity and specificity of aneurysm diagnosis from the first 7-days through to the last 7-days of all center trials.	6 months.

Collaborators and Investigators

• Sponsor: Jinling Hospital, China
• Investigators: Principal Investigator: Trial Manager, Jinling Hospital, Affiliated Hospital of Medical School, Nanjing University

Study record dates

Study Major Dates

• Study Start (Estimated): December 1, 2023
• Primary Completion (Estimated): June 1, 2024
• Study Completion (Estimated): July 1, 2025

Study Registration Dates

• First Submitted: August 29, 2022
• First Submitted That Met QC Criteria: November 1, 2023
• First Posted (Actual): November 7, 2023

Study Record Updates

• Last Update Posted (Actual): November 7, 2023
• Last Update Submitted That Met QC Criteria: November 1, 2023
• Last Verified: November 1, 2023

More Information

Terms related to this study

• Additional Relevant MeSH Terms: Cardiovascular Diseases; Vascular Diseases; Cerebrovascular Disorders; Brain Diseases; Central Nervous System Diseases; Nervous System Diseases; Intracranial Arterial Diseases; Aneurysm; Intracranial Aneurysm
• Other Study ID Numbers: 2022NZKY-015-03

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