Back to search results

Machine Learning in Atrial Fibrillation

This observational study is looking at how machine learning (ML) can help doctors better understand and treat atrial fibrillation (AF), a condition causing irregular heartbeats. AF can lead to dizziness, stroke, and even death. The study aims to use ML to identify different types of AF and predict how well ablation (a procedure to correct irregular heartbeats) will work for individual patients. You may be able to join if you are between 22 and 80 years old, have paroxysmal AF (AF that stops on its own within 7 days) or persistent AF (AF that needs medical help to stop), and have not responded to or cannot tolerate at least one anti-arrhythmic drug. The main goal is to see if ML can predict the success of ablation after one year. The study is currently recruiting 120 participants.

Study design
This is an observational study that plans to include 120 participants. It is not a randomized trial and the phase is not specified.
What's involved
Participants will undergo their standard-of-care ablation procedure. The study will collect electrograms (electrical recordings of the heart) using a special catheter during the ablation.
Compensation
Not stated in the trial record.
Follow-up
The primary outcome, machine learning prediction of ablation outcome, will be measured at 1 year.

AI-generated from the public study record. Only the study team can confirm whether you're eligible — confirm details with them before making decisions.

NCT05371405

Machine Learning in Atrial Fibrillation

Recruiting
Not specifiedAges 22–80Observational
Stanford University
~120 participants
Updated 2025-11-14 on ClinicalTrials.gov

At a glance

Recruiting sites
1 of 1 listed site is recruiting right now
RecruitingSuspended, closed, or not yet open
What they're measuring
Machine Learning Prediction of Ablation Outcome
Measured over 1 year.

Conditions

Atrial Fibrillation
Arrhythmias, Cardiac

Explore related trials

Atrial Fibrillation

NCT05371405

Where you'd take part

This study runs at 1 site. They're the same protocol — you choose where, and that choice sets who your contact draft is addressed to.

  • Stanford University

    Stanford, Californiastudy coordinator listed

    Recruiting

Sites open and close at different times, so the status above is per site — it can differ from the study's overall status.

Who to contact

Sanjiv Narayan, MD
[email protected]
650-724-1850
Email the study team

Opens a ready-to-send draft in your own email app — review before sending.

Want this trial checked against your situation?

Add a private profile and we'll compare every criterion below against your situation — and tell you which ones are met, uncertain, or excluding.

Check eligibility for this trial ~2 min · HIPAA-protected · delete anytime
Eligibility criteria

Inclusion

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

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

What this trial measures

  • Machine Learning Prediction of Ablation Outcome1 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.