Arrhythmias & electrophysiology

Leveraging AI-ECG Technology for Early Notification and Tracking of Atrial Fibrillation (AF) Development (LATENT): A Randomized Controlled Trial

CirculationPublished randomized controlled trial

Primary result · Composite of newly detected AF, AFl, or pre-AF atrial findingsResult — go to the resultOdds ratio 1.54 95% CI 1.01–2.37

Authors' conclusion

AI-ECG-guided monitoring resulted in a modest increase in the detection of new AF, AFl, or pre-AF atrial findings. However, these findings were fragile statistically and sensitive to reclassification of 1 event. LATENT (Leveraging AI-ECG Technology for Early Notification and Tracking of AF Development) demonstrates the clinical application of AI-ECG risk stratification to guide targeted rhythm surveillance, providing a foundation for larger trials evaluating its impact on patient outcomes.

Study context

Population
Adults 40 to 85 years of age without previous AF/atrial flutter (AFl)
Participants
14,665 adults
Comparison
AI-ECG-guided strategy vs usual care
  • Interventionn = 7,337
  • Controln = 7,328reference
Primary endpoint
Composite of:
  • Newly detected AF
  • AFl
  • Pre-AF atrial findings
Follow-up
Within 90 days
Methodological detailssingle-center, open-label
  • Single-center
  • Open-label

Primary result

As reported in the abstract

Composite of newly detected AF, AFl, or pre-AF atrial findings

Odds ratio

1.54

95% CI 1.01–2.37

P = 0.046

Events by treatment group

Interventionvs control
odds ratio 1.54 (95% CI 1.01–2.37); P = 0.046

Further findings

AF/AFl detection

Antiarrhythmic therapy initiation · 180 days

Classified as high risk by AI-ECG

Classified as high risk by AI-ECG

Of the 84 high-risk intervention participants, underwent monitoring
48 (57.1%)
Matched controls monitored
48

AF/AFl detection

Did not differ significantly

Antiarrhythmic therapy initiation · 180 days

Did not differ significantly

Primary composite outcome by baseline AI-ECG risk (subgroup)

High-risk participants, intervention vs control
32.1% versus 2.6%
Low-risk participants, intervention vs control
0.4% versus 0.5%
  • P interaction <0.001

Safety

Participant-reported monitoring-related adverse events, including skin reactions and discomfort

Original publication

Leveraging AI-ECG Technology for Early Notification and Tracking of AF Development (LATENT): A Randomized Controlled Trial. Circulation. Published 7 November 2026. doi:10.1161/circulationaha.126.083540

Composed by AI from the published abstract and checked against it. How Briefs are made →

Get them every week

New studies on this topic in My Week and in your Monday e-mail.

We e-mail you a sign-in link and a code. No password, no spam.