Using machine learning to improve treatment for atrial fibrillation
Official title: Machine Learning in Atrial Fibrillation
Run by Stanford University · NCT05371405 · Data updated 2026-11-12
This study is testing if using machine learning can help doctors better understand and treat atrial fibrillation by looking at patient data from those who have had ablation.
Quick facts
| Study type | Observational |
|---|---|
| Ages | 22 Years to 80 Years |
| Sex | All |
| Enrollment | 120 (estimated) |
| Sponsor | Stanford University Academic / other |
| Locations | 1 site (Stanford, California) |
| Status | Recruiting |
| Started | February 12, 2020 |
| Main results expected | December 2026 |
| Study ends | December 2027 |
| Registry record updated | November 14, 2025 |
| Trial ID | NCT05371405 on ClinicalTrials.gov |
Is this trial a fit for you?
✓Likely a good fit
Ideal candidates are patients undergoing ablation for paroxysmal or persistent atrial fibrillation who have failed or are intolerant to at least one anti-arrhythmic drug.
✕Probably not a fit
Patients with active coronary ischemia, decompensated heart failure, or other specified exclusion criteria may not benefit from this study.
A plain-English reading of the study's rules. Only the study team can confirm whether you qualify.
What this trial studies
This project investigates how machine learning can enhance the understanding and treatment of atrial fibrillation (AF) by analyzing physiological data and outcomes from patients undergoing ablation. The study aims to identify specific electrical and structural features that influence the success of AF ablation, utilizing a combination of computational techniques and clinical data. By recruiting 120 patients, the research will focus on three main objectives: analyzing electrograms to predict outcomes, assessing the acute response to ablation, and determining long-term success rates of the procedure. The findings could lead to more personalized treatment strategies for AF patients.
Why it matters
Potential benefit: If successful, this study could lead to more effective and personalized treatment options for patients with atrial fibrillation.
How similar studies have gone: Other studies have shown promise in using machine learning for similar applications in cardiac care, suggesting potential for success in this approach.
Who can join: the full rules
Show full inclusion / exclusion criteria
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 it's running
-
Stanford University
Stanford, California, United States Recruiting
Study contacts
- Study coordinator: Sanjiv Narayan, MD
- Email: sanjiv1@stanford.edu
- Phone: 650-724-1850
Similar studies
Other studies for the same condition or treatment. Recruiting studies are listed first.
-
Volta AI software in real-world AF ablation
A real-world observational study will test the latest Volta AF-Xplorer II AI software during atrial fibrillation ablation to see how safe and effective it is over 24 months.
-
Heart assessment to check repeat-stroke risk in people with atrial fibrillation
This project will test whether detailed heart examinations can find which people with atrial fibrillation who just had an ischemic stroke are at high risk of having another stroke.
-
Sensor-guided exercise program for people with atrial fibrillation
This program will test whether a Fitbit-based, personalized exercise plan can reduce symptoms and episode burden in people with paroxysmal atrial fibrillation.
-
Understanding brain and heart injuries after bleeding in the brain
This study looks at how bleeding in the brain affects both the brain and the heart in adults to better understand the connection between these injuries.
-
Comparing CT and DSA for selecting LAA occluder sizes in heart procedures
This study is testing whether using CT or DSA imaging helps doctors choose the right size of heart device for patients with atrial fibrillation who need a specific procedure.
-
Ablation of focal activation in atrial fibrillation
This study is testing a new method to find specific electrical signals that may be causing ongoing atrial fibrillation in patients, to see if targeting these signals can improve their treatment.
How to take part
- Review the eligibility criteria above with your treating physician.
- Check the official listing on ClinicalTrials.gov for the latest contact details and recruitment status.
- Contact the study coordinator or principal investigator to ask for pre-screening. Pre-screening is free and never obligates you to enroll.