AI analysis of ECGs to predict atrial fibrillation risk in ESUS patients with an implantable cardiac monitor.
Official title: Predicting Atrial Fibrillation in Patients With Post-implantable Cardiac Monitor Implementation : A Prospective, Long-term Follow-up Study Using Comprehensive AI ECG Analysis : Multicenter Prospective Study
Run by Inha University Hospital · NCT07347691 · Data updated 2026-11-12
This project tests whether an AI tool called SmartECG-AF can use a routine 12-lead ECG to predict which ESUS patients with an implantable cardiac monitor will develop atrial fibrillation.
Quick facts
| Study type | Observational |
|---|---|
| Ages | 30 Years and up |
| Sex | All |
| Enrollment | 92 (estimated) |
| Sponsor | Inha University Hospital Academic / other |
| Locations | 5 sites (Ansan and 4 other locations) |
| Status | Recruiting |
| Started | November 19, 2025 |
| Main results expected | May 2027 |
| Study ends | May 2028 |
| Registry record updated | January 16, 2026 |
| Trial ID | NCT07347691 on ClinicalTrials.gov |
Is this trial a fit for you?
✓Likely a good fit
Ideal candidates are adults (≥30 years) with ESUS who have undergone or are scheduled for ICM implantation, have a sinus-rhythm 12-lead ECG within two weeks of implant, and can provide informed consent.
✕Probably not a fit
Patients with a prior diagnosis of AF, nonfunctional ICMs, or ECGs that are too noisy or incompatible with the AI algorithm are unlikely to benefit from this approach.
A plain-English reading of the study's rules. Only the study team can confirm whether you qualify.
What this trial studies
This multicenter prospective observational study applies the SmartECG-AF deep learning algorithm to baseline 12-lead ECGs from patients with Embolic Stroke of Undetermined Source who have an implantable cardiac monitor (ICM). Patients will be classified by the AI score into a High Risk group and a Low-to-Intermediate Risk control group and then followed longitudinally using ICM recordings. The primary analysis compares time-to-first ICM-detected atrial fibrillation event between risk groups, and secondary analyses examine the relationship between AI-predicted risk and major adverse cardiovascular events (MACE). The study aims to validate whether AI-guided ECG risk stratification can identify occult AF and inform post-ESUS monitoring strategies.
Why it matters
Potential benefit: If successful, this could help identify ESUS patients at high risk of hidden AF so clinicians can target monitoring or treatment earlier to reduce recurrent strokes.
How similar studies have gone: Previous research has shown AI ECG algorithms can detect signatures associated with paroxysmal AF and predict future AF in other populations, but applying and validating this approach specifically in ESUS patients with ICMs remains novel.
Who can join: the full rules
Show full inclusion / exclusion criteria
Inclusion Criteria: * Patients aged 30 years or older. * Patients diagnosed with Embolic Stroke of Undetermined Source (ESUS) who have undergone or are scheduled for Implantable Cardiac Monitor (ICM) implantation. * Patients who have undergone at least one 12-lead ECG examination within 2 weeks before or after the date of ICM implantation. * Patients maintaining Sinus Rhythm on ECG at the time of enrollment. * Patients who have voluntarily signed the informed consent form. Exclusion Criteria: * Patients diagnosed with Atrial Fibrillation (AF) at least once prior to the date of enrollment. * Patients whose ICM battery status is at Elective Replacement Interval (ERI), making recording impossible. * Patients whose ECGs cannot be analyzed by the AI algorithm (SmartECG-AF) due to severe artifacts or noise, or are incompatible with digital analysis.
Where it's running
-
Korea University Ansan Hospital
Ansan, South Korea Recruiting -
Inha University Hospital
Incheon, South Korea Recruiting -
Jeju National University Hospital
Jeju City, South Korea Recruiting -
Korea University Guro Hospital
Seoul, South Korea Recruiting -
Ajou University Hospital
Suwon, South Korea Recruiting
Study contacts
- Principal investigator: Yong-Soo Baek, MD, PhD — Inha University Hospital
- Study coordinator: Yong-Soo Baek, MD, PhD
- Email: existsoo@inha.ac.kr
- Phone: +82-32-890-2200
Similar studies
Other studies for the same condition or treatment. Recruiting studies are listed first.
-
PFO closure versus blood thinners to prevent repeat stroke in older adults
This study will test whether closing a patent foramen ovale or taking direct oral anticoagulants better prevents repeat strokes in adults over 60 with PFO-related embolic stroke.
-
Using a MEMO wearable patch to find atrial fibrillation after an unexplained stroke
This trial will try a wearable single-lead ECG patch (MEMO Patch) to find previously missed atrial fibrillation in adults who had an embolic stroke of unknown cause.
-
Left atrial function in people with unexplained (cryptogenic) stroke.
This will see if lower left atrial strain on a heart ultrasound is linked to unexplained (cryptogenic) stroke and to higher risk of another stroke in adults who had a stroke without a known cause.
-
High-coverage carotid stent versus medical treatment to prevent embolism from symptomatic non-stenotic carotid disease (SyNC)
This trial will test whether placing a high‑coverage carotid stent, compared with medical therapy alone, reduces repeat embolic events in people who recently had symptoms from low‑grade (10–49%) carotid plaques with high‑risk features.
-
Investigating the effects of Empagliflozin on heart function after unexplained strokes
This study is testing if the medication Empagliflozin can help improve heart function and prevent future strokes in people who have had unexplained strokes.
-
Identifying New Cancer After Ischemic Stroke in High-Risk Patients
This study is trying to see if people who had an ischemic stroke and have high D-dimer levels are more likely to be diagnosed with hidden cancer within a year.
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.