Blinded Randomized Controlled Trial of Artificial Intelligence Guided Detection of Intracardiac Thrombus

Atrial Fibrillation Clinical Trial

Official title:

ICE Detector-RCT: Blinded, Randomized Controlled Trial of Electrophysiologist vs. Artificial Intelligence Detection of Intracardiac Thrombus

Clinical Trial Details — Status: Not yet recruiting

Administrative data

• NCT number: NCT06206187
• Other study ID #: ICE Detector-RCT
• Status: Not yet recruiting
• Phase: N/A
• Start date: January 5, 2024
• Est. completion date: December 31, 2025

Study information

• Verified date: January 2024
• Source: Shanghai Chest Hospital
• Contact: Shaohui Wu, PHD
• Phone: 15821960839
• Email: wushaohui18[@]163.com
• Is FDA regulated: No
• Study type: Interventional

Clinical Trial Summary

To determine whether an integrated AI decision support can save time and improve the accuracy of detection of intracardiac thrombus, the investigators are conducting a blinded, randomized controlled study of AI-guided detection of intracardiac thrombus to electrophysiologist judgment in preliminary readings of echocardiograms.

Recruitment information / eligibility

• Status: Not yet recruiting
• Enrollment: 1500
• Est. completion date: December 31, 2025
• Est. primary completion date: July 31, 2025
• Accepts healthy volunteers: Accepts Healthy Volunteers
• Gender: All
• Age group: 18 Years to 90 Years

Eligibility

Inclusion Criteria:

1. Aged 18-80 years.

2. Willing to sign informed consent.

3. Patients diagnosed with atrial fibrillation Paroxysmal AF and Persistent AF according to the latest clinical guidelines

Exclusion Criteria:

1. End-stage disease with a mean life expectancy less than 1 year

2. New York Heart Association (NYHA) class III or IV, or last known left ventricular ejection fraction less than 30%

3. Previous surgical or catheter ablation for AF

4. Bradycardia and presence of implanted ICD

5. Uncontrolled hypertension: Systolic blood pressure (SBP) >180 mmHg or diastolic blood pressure (DBP) > 110 mmHg

6. Patients with Cardiovascular events including acute myocardial infarction, any PCI, valvular cardiac surgical, or percutaneous procedure within the past 3 months

7. Women of childbearing potential who are, or plan to become, pregnant during the time of the study

8. Have been enrolled in an investigational study evaluating devices or drugs.

Related Conditions & MeSH terms

• Atrial Fibrillation

Intervention

Other:
• Automated detection of the intracardiac thrombus through deep learning
A deep learning model will identify the intracardiac thrombus. The AI model will produce an assessment of intracardiac thrombus using video based features.
• Electrophysiologist judgment of the intracardiac thrombus
Cardiac electrophysiologists use their own experience to determine whether there is intracardiac thrombus

Locations

Country	Name	City	State
China	Shanghai Chest Hospital	Shanghai	???

Sponsors (2)

Lead Sponsor	Collaborator
Shanghai Chest Hospital	Johnson & Johnson

Country where clinical trial is conducted

China, 

Outcome

Type	Measure	Description	Time frame	Safety issue
Primary	Degree of change from initial (AI vs EP doctor) assessment to final cardiologist assessment		10 Minutes
Secondary	Perioperative adverse event rates		10 Minutes