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

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

Status

Not yet recruiting

Phases

Study type

Interventional

Source

ClinicalTrials.gov

Registry ID

NCT06206187

Enrollment

1500

Registered

2024-01-16

Start date

2024-01-05

Completion date

2025-12-31

Last updated

2024-01-16

For informational purposes only — not medical advice. Sourced from public registries and may not reflect the latest updates. Terms

Conditions

Atrial Fibrillation

Brief 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.

Interventions

OTHERAutomated 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.

OTHERElectrophysiologist judgment of the intracardiac thrombus

Cardiac electrophysiologists use their own experience to determine whether there is intracardiac thrombus

Study design

Allocation

RANDOMIZED

Intervention model

PARALLEL

Primary purpose

DIAGNOSTIC

Masking

SINGLE (Outcomes Assessor)

Eligibility

Sex/Gender

ALL

Age

18 Years to 90 Years

Healthy volunteers

Yes

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.

Design outcomes

Primary

Measure	Time frame
Degree of change from initial (AI vs EP doctor) assessment to final cardiologist assessment	10 Minutes

Secondary

Measure	Time frame
Perioperative adverse event rates	10 Minutes

Countries

China

Contacts

Primary ContactShaohui Wu, PHD

wushaohui18@163.com15821960839

Outcome results

None listed

Source: ClinicalTrials.gov · Data processed: Feb 4, 2026