Functional And STructural Assesment of the Heart by Artificial Intelligence-enabled Electrocardiogram for the Management of Atrial Fibrillation (FAST-AF)

The objective of this study is to evaluate whether an AI-ECG based screening strategy for detecting cardiac functional and structural abnormalities preserves clinical effectiveness and safety, compared with a conventional strategy of routine echocardiography in patients with AF, thereby demonstrating the non-inferiority of AI-ECG guided care.

Study Overview

• Status: Not yet recruiting
• Conditions: Atrial Fibrillation (AF)
• Intervention / Treatment: Diagnostic test: Transthoracic Echocardiography-Guided Assessment; Diagnostic test: Artificial intelligence-enabled electrocardiography

Detailed Description

Atrial fibrillation (AF) is the most common sustained cardiac arrhythmia, with its prevalence having more than doubled over the past decade. AF is associated with an increased risk of stroke, heart failure, and mortality, thereby imposing a substantial burden on both patients and healthcare systems. Accordingly, contemporary clinical guidelines emphasize accurate diagnosis and early, integrated management of AF. In this context, transthoracic echocardiography has become a standard diagnostic tool for the assessment of structural heart disease and cardiac function.

Despite being non-invasive and relatively low-cost, echocardiography is subject to several system-level limitations in routine clinical practice, including dependence on specialized equipment and trained personnel, scheduling delays, and inefficiencies related to repeated examinations. These constraints may create bottlenecks in the timely initiation and optimization of AF management.

In real-world practice, a considerable proportion of patients with AF undergo echocardiography primarily to confirm the absence of significant structural heart disease or impaired function. A uniform strategy of performing echocardiography in all patients with AF may not be optimal from the perspectives of patient convenience and healthcare resource utilization. Moreover, depending on healthcare system capacity, access to echocardiography may delay the timely selection of optimal AF management. Conversely, selectively performing echocardiography in patients with a higher likelihood of structural or functional cardiac abnormalities may allow for a more efficient, timely, and targeted diagnostic approach.

Artificial intelligence-enabled electrocardiography (AI-ECG) offers several practical advantages, including very short acquisition time, patients' convenience, substantially lower cost, and feasibility for repeated assessments during follow-up. AI-ECG may enable sensitive detection of changes in a patient's cardiac status over time. Positioning AI-ECG as an initial screening tool to identify patients with suspected structural or functional heart disease could facilitate a "screening-confirmation" diagnostic pathway, in which echocardiography is reserved for patients with abnormal or suspicious findings on AI-ECG. Such an approach has the potential to streamline initial and follow-up evaluations while maintaining patient safety.

• Study Type: Interventional
• Enrollment (Estimated): 1724
• Phase: Not Applicable

Contacts and Locations

• Study Contact: Name: Eue-Keun Choi, M.D. Ph.D.; Phone Number: 82-2-2072-0688; Email: choiek417@gmail.com

Study Locations

• South Korea
  • Seoul, South Korea
    • Seoul National University Hospital
    • Contact: Eue-Keun Choi, MD, PhD; Email: choiek17@snu.ac.kr

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: Adult; Older Adult
• Accepts Healthy Volunteers: No

Description

Inclusion Criteria:

1. AF documented by electrocardiography within the past 12 months

   • AF documented on a 12-lead electrocardiogram or recorded for ≥30 seconds on a single-lead or multi-lead electrocardiogram.
2. Patients for whom an initial or repeat transthoracic echocardiographic evaluation is clinically indicated.
3. A CHA₂DS₂-VA score of ≥2.
4. Aged ≥19 years at the time of enrollment and able to provide written informed consent voluntarily.

Exclusion Criteria:

1. Transthoracic echocardiography performed within the past 6 months.
2. Ventricular rate ≥110 beats per minute during atrial fibrillation.
3. Atrial fibrillation due to a reversible cause.
4. New York Heart Association (NYHA) functional class IV or European Heart Rhythm Association (EHRA) class IV symptoms.
5. Known history of structural heart disease or clinical findings suggestive of structural heart disease based on medical history and physical examination. (e.g., presence of a cardiac murmur of Levine scale grade 3 or higher on auscultation, or murmurs suggestive of moderate to severe mitral stenosis, such as an opening snap or diastolic rumbling murmur).
6. Baseline electrocardiographic conduction abnormalities or significant electrocardiographic findings suggestive of clinically meaningful structural heart disease (e.g., Mobitz type II second-degree atrioventricular block, third-degree atrioventricular block, or QTc ≥480 ms).
7. History of prior cardiac surgery.
8. History of acute coronary syndrome or coronary revascularization within the past 90 days.
9. History of intracardiac thrombosis or systemic thromboembolism within the past 90 days.
10. History of transient ischemic attack, ischemic stroke, or intracranial hemorrhage within the past 90 days.
11. History of ventricular tachycardia or ventricular fibrillation.
12. Severe liver disease associated with coagulopathy (e.g., AST or ALT >3× the upper limit of normal, or total bilirubin >2× the upper limit of normal).
13. Severe chronic kidney disease (stage V), requiring or imminently requiring dialysis.
14. Contraindication to anticoagulation therapy.
15. Pregnancy, breastfeeding, or planning pregnancy during the study period.
16. Life expectancy of less than 1 year.
17. Current participation in another randomized clinical trial.

Study Plan

How is the study designed?

Design Details

• Primary Purpose: Treatment
• Allocation: Randomized
• Interventional Model: Parallel Assignment
• Masking: None (Open Label)

Number of Arms

2

Arms and Interventions

Participant Group / Arm	Intervention / Treatment
Active Comparator: Transthoracic Echocardiography-Guided Assessment Group (TTE group); Participants in this group will receive a standard-of-care evaluation. Cardiac function and structure will be evaluated using Transthoracic Echocardiography (TTE) regardless of ECG findings. Management (anticoagulation, rate/rhythm control) is initiated or adjusted based on TTE parameters. TTE is performed at least once annually during follow-up.	Diagnostic test: Transthoracic Echocardiography-Guided Assessment; Standard Transthoracic Echocardiography used to assess cardiac structure and function, serving as the reference standard for guiding clinical management in this study arm.
Experimental: AI-ECG-Guided Assessment Group (AI-ECG group); Participants in this group will undergo a conditional diagnostic strategy. Cardiac function and structure are initially screened using an AI-enabled ECG.; Predicted Normal: TTE is withheld. Management is based on clinical evaluation and AI-ECG results.; Predicted Abnormal: Verification TTE is performed. Management is guided by TTE findings. Safety Note: Protocol-defined rescue TTE is permitted at the investigator's discretion for worsening symptoms or prior to procedures (cardioversion, ablation), regardless of AI-ECG results.	Diagnostic test: Artificial intelligence-enabled electrocardiography; An artificial intelligence algorithm applied to standard 12-lead electrocardiography designed to predict cardiac structural or functional abnormalities. This tool guides the decision to perform or withhold downstream echocardiography.

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Composite of all-cause Mortality, Stroke, CV Hospitalization, and AAD-Related SAEs	Evaluation of the effectiveness of the strategy based on a composite endpoint comprising the following clinical events: All-cause mortality;; Stroke or systemic thromboembolism;; Hospitalization due to worsening heart failure or acute coronary syndrome;; Serious adverse events related to antiarrhythmic drug therapy. The endpoint is defined as the time to the first occurrence of any of these components.	up to 10 years

Secondary Outcome Measures

Outcome Measure	Measure Description	Time Frame
All-cause mortality		up to 10 years
Stroke or systemic thromboembolism		up to 10 years
Heart failure worsening	Heart failure worsening: An outpatient heart failure episode requiring intravenous diuretic therapy or initiation or escalation of oral diuretics, or hospitalization for heart failure (defined as heart failure being the primary reason for admission or requiring treatment in a healthcare facility for ≥12 hours with intravenous diuretics).	up to 10 years
Hospitalization due to acute coronary syndrome		up to 10 years
Serious adverse events related to antiarrhythmic drug therapy	Serious adverse events related to antiarrhythmic drug therapy: Hypotension, symptomatic drug-induced bradycardia, atrioventricular block, drug-induced atrial flutter or atrial tachycardia, torsade de pointes, ventricular tachycardia, ventricular fibrillation, or syncope.	up to 10 years
Proportion of patients receiving rhythm control therapyc after the initial diagnosis of AF	Rhythm control therapy: Use of antiarrhythmic drugs, electrical cardioversion, or catheter ablation for AF.	up to 10 years
Time from initial diagnosis of AF to first rhythm control therapy	Rhythm control therapy: Use of antiarrhythmic drugs, electrical cardioversion, or catheter ablation for AF.	up to 10 years
Changes in oral anticoagulation from warfarin to a DOAC or vice versa, based on the reassessment of cardiac function and structure		up to 10 years
Changes in the class of antiarrhythmic drugs (AADs) prescribed, based on the reassessment of cardiac function and structure	i.e., modification of Class Ic AAD to Class III AAD. Changes in antiarrhythmic drug therapy due solely to inadequate AF rate or rhythm control are not included.	up to 10 years
Changes in heart failure medications resulting from reassessment of cardiac function and structure	Initiation, dose escalation, or dose reduction of heart failure medication classes including beta-blockers, mineralocorticoid receptor antagonists (MRAs), renin-angiotensin-aldosterone system (RAAS) inhibitors or angiotensin receptor-neprilysin inhibitors (ARNIs), sodium-glucose cotransporter 2 inhibitors (SGLT2i), or other agents (e.g., ivabradine, vericiguat, hydralazine/nitrate	up to 10 years
The proportion of patients maintaining sinus rhythm		up to 10 years
Quality of life assessed by European Quality of Life-5 Dimensions (EQ-5D) at baseline, 12 months, and 24 months	EQ-5D scores range from 0 to 100, with higher scores indicating better health status.	up to 10 years
NT-proBNP levels at baseline, 12 months, and 24 months		up to 10 years
Diagnostic performance of the AI-ECG algorithm for detecting cardiac functional and structural abnormalities	Assessment of the AI-ECG algorithm's ability to detect functional and structural cardiac abnormalities. Performance metrics will include Accuracy, Sensitivity, Specificity, Positive Predictive Value, and Negative Predictive Value.	up to 10 years
Investigator satisfaction with AI-ECG use at 12 months and 24 months reported by a self-reported questionnaire		up to 10 years

Collaborators and Investigators

• Sponsor: Seoul National University Hospital
• Collaborators: Medical AI
• Investigators: Principal Investigator: Eue-Keun Choi, M.D. Ph.D., Seoul National University Hospital

Study record dates

Study Major Dates

• Study Start (Estimated): May 1, 2026
• Primary Completion (Estimated): December 31, 2030
• Study Completion (Estimated): December 31, 2030

Study Registration Dates

• First Submitted: February 10, 2026
• First Submitted That Met QC Criteria: March 17, 2026
• First Posted (Actual): March 20, 2026

Study Record Updates

• Last Update Posted (Actual): March 23, 2026
• Last Update Submitted That Met QC Criteria: March 19, 2026
• Last Verified: March 1, 2026

More Information

Terms related to this study

• Keywords: atrial fibrillation; artificial intelligence; electrocardiogram; structural heart disease
• Additional Relevant MeSH Terms: Cardiovascular Diseases; Pathologic Processes; Heart Diseases; Arrhythmias, Cardiac; Pathological Conditions, Signs and Symptoms; Atrial Fibrillation
• Other Study ID Numbers: FAST-AF

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: UNDECIDED

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No