AI-ECG alerts to catch early atrial fibrillation risk
Official title: Leveraging AI-ECG Technology for Early Notification and Tracking of AF Development: a Randomized Control Trial
Run by National Defense Medical Center, Taiwan · NCT06847932 · Data updated 2026-11-12
This trial tests whether an AI-powered ECG alert can help doctors find people at high risk of developing atrial fibrillation so they can be given continuous heart-rhythm monitoring.
Quick facts
| Study type | Interventional |
|---|---|
| Ages | 40 Days to 85 Days |
| Sex | All |
| Enrollment | 14726 (estimated) |
| Sponsor | National Defense Medical Center, Taiwan Academic / other |
| Locations | 1 site (Taipei) |
| Status | Recruiting |
| Started | July 1, 2025 |
| Main results expected | July 1, 2026 |
| Study ends | October 1, 2026 |
| Registry record updated | November 19, 2025 |
| Trial ID | NCT06847932 on ClinicalTrials.gov |
Is this trial a fit for you?
✓Likely a good fit
Adults seen as inpatients or outpatients who have at least one ECG in the past year and do not have prior AF/AFL, prior AF/AFL ablation, implanted cardiac devices, rhythm-control antiarrhythmic drugs, or current indications for anticoagulation.
✕Probably not a fit
People with a prior or current diagnosis of AF/AFL, prior AF/AFL ablation, cardiac implantable devices, those already on rhythm-control medications, or those already requiring anticoagulation are unlikely to benefit from this screening-focused approach.
A plain-English reading of the study's rules. Only the study team can confirm whether you qualify.
What this trial studies
This interventional study uses an AI algorithm applied to routine ECGs to flag patients at high risk of new atrial fibrillation, atrial flutter, or significant atrial arrhythmias. Flagged patients are recommended for continuous cardiac rhythm monitoring to detect incident arrhythmias. Eligible participants are hospital inpatients or outpatients with at least one ECG in the prior year and without prior AF/AFL, prior ablation, implantable cardiac devices, rhythm-control drugs, or indications for anticoagulation. The trial is conducted at Tri-Service General Hospital in Taipei and tracks whether AI-guided alerts lead to earlier identification of AF/AFL compared with usual care pathways.
Why it matters
Potential benefit: If successful, this approach could enable earlier detection of atrial fibrillation and timely use of monitoring and treatment to reduce stroke risk.
How similar studies have gone: Previous studies have shown AI-ECG algorithms can predict future AF risk from routine ECGs, and while using AI alerts to direct continuous monitoring is relatively new, early pilot data are encouraging.
Who can join: the full rules
Show full inclusion / exclusion criteria
Inclusion Criteria: * Patients in the inpatient department or the outpatient department * Patients need to have at least one electrocardiogram within one year Exclusion Criteria: * Diagnosis of atrial fibrillation/atrial flutter * History of atrial fibrillation/atrial flutter catheter ablation * Patients with cardiac implantable electronic devices * Any documented electrocardiogram showed atrial fibrillation/atrial flutter and pacing rhythm * History of received rhythm control medications for atrial arrhythmia, including Class I and Class III antiarrhythmic drugs * Any reasons indicate for anti-coagulant agents, including vitamin K antagonist and non-vitamin K antagonist oral anticoagulant
Where it's running
-
Tri-Service General Hospital
Taipei, Taiwan Recruiting
Study contacts
- Principal investigator: Chin Lin, PhD — National Defense Medical Center
- Study coordinator: Chin Lin, PhD
- Email: xup6fup@mail.ndmctsgh.edu.tw
- Phone: +886-2-8792-3100 Ext. 18574
Similar studies
Other studies for the same condition or treatment. Recruiting studies are listed first.
-
AI-based cardiac analysis using 12-lead and 1-lead ECG
A clinician-facing pilot test to see if SmartECG-EF helps evaluate heart function using both 12-lead and single-lead ECGs in adults with heart conditions.
-
AI-assisted ECG to speed diagnosis and treatment of occlusion heart attacks under a pay-for-performance program
This project will test whether adding an AI tool that flags ECGs for occlusion heart attacks and linking those alerts to a pay-for-performance program helps emergency department patients who get ECGs get diagnosed and treated faster and with better outcomes.
-
Exercise program for patients after atrial fibrillation ablation
This study is testing whether a structured exercise program can help people who had atrial fibrillation ablation feel better and improve their heart health and quality of life.
-
AI-assisted whole-course management for safe medicine use in advanced solid tumors
A real-world study compares a smartphone-based digital management system with usual care to see if it reduces drug-related problems and healthcare needs for adults with advanced solid tumors receiving cancer therapy.
-
Pulsed Field vs Cryoballoon for Pulmonary Vein Isolation in Atrial Fibrillation
This trial tests whether pulsed field ablation can shorten the procedure for first-time PVI in AF patients compared with cryoballoon ablation, while keeping safety and effectiveness similar.
-
Pulsed Field Ablation vs Cryoablation for Atrial Fibrillation Under Deep Sedation
This trial tests whether pulsed field ablation (PFA) done under deep sedation works as well as cryoballoon ablation for treating atrial fibrillation, aiming to avoid general anesthesia.
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.