NCT05371405 · Stanford University
Machine Learning in Atrial Fibrillation
What this study is about
Atrial fibrillation is a serious public health issue that affects over 5 million Americans (Miyazaka, Circulation 2006) in whom it may cause skipped beats, dizziness, stroke and even death. Therapy for AF is currently suboptimal, in part because AF represents several disease states of which few have been delineated or used to successfully guide management.
View original scientific description
Atrial fibrillation is a serious public health issue that affects over 5 million Americans (Miyazaka, Circulation 2006) in whom it may cause skipped beats, dizziness, stroke and even death. Therapy for AF is currently suboptimal, in part because AF represents several disease states of which few have been delineated or used to successfully guide management. This study seeks to clarify this delineation of AF types using machine learning (ML).
Primary outcome measures
Machine Learning Prediction of Ablation Outcome
Time frame: 1 year.
To compare success of AF ablation in each patient at 1 year (defined as absence of AF or atrial tachycardia on outpatient monitoring) to predicted success by the machine learning algorithm developed in this project. The outcome compares observed success at 1 year (Yes, No) to (a) a binary predictor and (b) a continuous variable of success from the algorithm. The machine learning algorithm is trained on clinical and electrophysiological data to predict if certain lesion sets will or will not be successful.
Who can participate
This study lists these criteria on ClinicalTrials.gov. A study coordinator reviews eligibility during screening — this page does not determine whether you qualify.
Inclusion criteria
- undergoing ablation at Stanford of (a) paroxysmal AF (self-terminates \< 7 days), or (b) persistent AF (requires cardioversion to terminate).
- Per our clinical practice and guidelines (Calkins et al, Heart Rhythm 2012), patients will have failed or be intolerant of ≥ 1 anti-arrhythmic drug.
Exclusion criteria
- active coronary ischemia or decompensated heart failure
- atrial or ventricular clot on trans-esophageal echocardiography
- pregnancy (to minimize fluoroscopic exposure)
- inability or unwillingness to provide informed consent
- rheumatic valve disease (results in a unique AF phenotype)
- thrombotic disease or venous filters
Where
- Stanford, California
Related conditions & keywords
Frequently asked questions
What is a clinical trial?
A clinical trial is a research study that tests new medical treatments, drugs, devices, or procedures to determine their safety and effectiveness. Trials are carefully designed and monitored to protect participants while advancing medical knowledge.
Is it safe to participate?
Clinical trials follow strict safety guidelines and ethical standards. Trials must be reviewed and approved, and participants are closely monitored by medical professionals throughout the study. You can withdraw at any time if you choose.
Will I be compensated?
Many clinical trials offer compensation for your time, travel expenses, and inconvenience. The specific compensation varies by study and will be discussed during the screening process. All study-related medical care is typically provided at no cost to participants.
Will I receive a placebo instead of treatment?
When effective treatment exists, participants typically receive either the standard treatment plus the study intervention, or the standard treatment plus placebo. You would not be denied effective care. Placebos are primarily used when no proven treatment is available, or in addition to standard care. Your trial consent form will clearly explain what treatments you may receive.
Can I leave a trial if I change my mind?
Absolutely. Participation in clinical trials is completely voluntary. You have the right to withdraw from the study at any time, for any reason, without penalty or loss of benefits to which you are otherwise entitled.
How long does a clinical trial last?
Trial duration varies widely depending on the study design and purpose. Some trials last just a few weeks, while others may continue for months or years. The study coordinator will provide specific timeline information during your screening call.
Data: ClinicalTrials.gov · synced Nov 14, 2025 · Source of record for eligibility and locations