Verification study of AI-based prediction algorithm for the prediction of paroxysmal atrial fibrillatio
Not Applicable
- Conditions
- Diseases of the circulatory system
- Registration Number
- KCT0008004
- Lead Sponsor
- Ewha Womans University Medical Center
- Brief Summary
Not available
- Detailed Description
Not available
Recruitment & Eligibility
- Status
- ot yet recruiting
- Sex
- All
- Target Recruitment
- 650
Inclusion Criteria
This study is conducted with consent from patients 18 years of age or older admitting to the hospital or visiting hospital with symptoms of arrhythmia at outpatient clinic.
Exclusion Criteria
Patients with pacemakers, implanted defibrillators, or other implantable electrical devices were excluded. Pregnant woman, lactating woman were also excluded. Patients who died within 2 weeks were excluded. Patients have current symptoms or a history of skin cancer, rash, skin disease, keloid disease, or injury were excluded.
Study & Design
- Study Type
- Observational Study
- Study Design
- Not specified
- Primary Outcome Measures
Name Time Method Atrial fibrillation
- Secondary Outcome Measures
Name Time Method ot appicable
Related Research Topics
Explore scientific publications, clinical data analysis, treatment approaches, and expert-compiled information related to the mechanisms and outcomes of this trial. Click any topic for comprehensive research insights.
What machine learning features in KCT0008004 correlate with paroxysmal atrial fibrillation pathophysiology mechanisms?
How does AI-based AFib prediction in KCT0008004 compare to standard ECG monitoring in sensitivity and specificity?
Which cardiac biomarkers or genetic variants are integrated into the KCT0008004 AI algorithm for patient risk stratification?
What are the false positive/negative rates of AI AFib prediction in KCT0008004 and their clinical management implications?
How does Ewha Womans University's AI model in KCT0008004 align with existing wearable ECG technologies like Apple Watch AFib detection?