Artificial Intelligence Guided Patient Selection for Atrial Fibrillation Catheter Ablation: Randomized Clinical Trial (AI-PAFA Trial)

Atrial fibrillation (AF) is a major cardiovascular disease with a prevalence of 1.7% of the total population in Korea, associated with 25% of ischemic stroke and 30% of heart failure, and is a major cardiovascular disease that doubles the risk of dementia. AF catheter ablation (AFCA) is an effective procedure that lowers the risk of heart failure mortality and cerebral infarction and improves cognitive or renal functions. However, the recurrence rate after the procedure is relatively high, especially in patients with long-standing persistent AF in which atrial remodeling has already progressed. Research on the prediction of treatment efficacy using artificial intelligence (AI) is being actively conducted around the world. We predicted the AFCA poor responders who will progress to permanent AF despite AFCA among a total of 3,372 patients included in the Yonsei AF Ablation cohort and the 2nd independent cohort with a long-term follow-up through AI with area under curve (AUC) 0.943. Therefore, in this prospective randomized clinical study, the difference between the patient selection for AFCA using AI algorithm and the clinical guidelines-based decision will be compared and evaluated in terms of long-term rhythm outcome.

Study Overview

• Status: Recruiting
• Conditions: Atrial Fibrillation
• Intervention / Treatment: Procedure: Artificial Intelligence-based atrial fibrillation catheter ablation; Procedure: Medical Therapy

Detailed Description

Study design

1. Prospective randomization (AI-based patient selection group vs. conventional guidelines-based patient selection group)
2. Target number of subjects 1000 patients (500 people in each group)
3. Rhythm follow-up schedule: 2012 ACC/AHA/ESC guidelines (basal, 3 months, then every 6 months Holter, ECG when symptomatic)
4. Anticoagulant therapy follows 2020 ESC guidelines.
5. Evaluation of all adverse events occurring in each group and comparative evaluation of hospitalization rates, major cardiovascular attacks, and mortality

Process of Patient Selection A guideline-based appropriate candidate for AFCA Randomization for AI-guide group vs. Clinical guideline-based group Poor responder selection by AI at the outpatient clinic AI-prediction outcomes should be noticed in AI-guided groups, but not in the clinical guideline-based group.

Recommendation of rate control for AI-predicted poor responders All-comer ablation in guideline-based group

Progress and rhythm/ECG tracking

1. Implemented according to 2012 American College of Cardiology(ACC)/American Heart Association(AHA)/Heart Rhythm Society(HRS) guidelines for AF management
2. Outpatient follow-up 1 to 2 weeks after the start of the procedure or drug treatment
3. Follow-up every 3 months after the procedure, and every 6 months thereafter
4. If the patient complains of arrhythmia symptoms, conduct an electrocardiogram at any time and follow the rhythm with a Holter or an event recorder.

• Study Type: Interventional
• Enrollment (Anticipated): 1000
• Phase: Not Applicable

Contacts and Locations

• Study Contact: Name: Hui-Nam Pak; Phone Number: 82-2-2228-8459; Email: hnpak@yuhs.ac

Study Locations

• Korea, Republic of
  • Seoul, Korea, Republic of
    • Recruiting
    • Severance Hospital, Yonsei University Health System
    • Contact: Hui-Nam Pak; Phone Number: v; Email: hnpak@yuhs.ac

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: 20 years to 80 years (Child, Adult, Older Adult)
• Accepts Healthy Volunteers: No

Description

Inclusion Criteria:

1. Left atrium size < 55 mm
2. AF recurred during the administration of antiarrhythmic drugs or that antiarrhythmic drugs intolerable patients
3. Patients eligible for anticoagulant therapy (to prevent thromboembolic events)

Exclusion Criteria:

1. AF associated with severe cardiac anomalies or structural heart disease with hemodynamic influence
2. Patients who have difficulty in CT imaging using a contrast medium
3. Patients with active internal bleeding
4. Inappropriate anticoagulant therapy
5. Serious comorbidities
6. Patients expected to survive less than 1 year
7. People with drug or alcohol addiction
8. Those who cannot read the consent form (illiterate, foreigners, etc.)
9. Patients who are judged unsuitable for participation in clinical research by the judgment of other investigators

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
Experimental: Artificial Intelligence-based atrial fibrillation catheter ablation; catheter ablation	Procedure: Artificial Intelligence-based atrial fibrillation catheter ablation; Patient selection for Atrial Fibrillation Catheter Ablation(AFCA); AI-guided prediction for poor responder of AFCA in the outpatient clinic; Sharing information on the AI prediction with the patient and family member; AFCA after consent to the procedure; Pulmonary vein isolation and additional treatment for non-pulmonary vein triggers; Monitoring esophageal temperature; Evaluation of Procedure and ablation time, and complication afer procedure; Post-procedure rhythm follow-up is carried out according to the study design above.
Active Comparator: Medical Therapy; catheter ablation	Procedure: Medical Therapy; Patient selection for Atrial Fibrillation Catheter Ablation(AFCA); Decision for AFCA based on clinical guidelines and the experience of the attending physician; AFCA after consent to the procedure; Pulmonary vein isolation and additional treatment for non-pulmonary vein triggers; Monitoring esophageal temperature; Evaluation of Procedure and ablation time, and complication afer procedure

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
safety of Atrial Fibrillation Catheter Ablation(AFCA)	Safety Assessment: Incidence of procedure-related complications within 30 days of procedure (thoracotomy, cerebral infarction, pericardial effusion or pericardial tamponade, inguinal puncture site hematoma, and vascular complications)	Up to 5 years
Efficacy of Atrial Fibrillation Catheter Ablation(AFCA)	Efficacy evaluation: Clinical recurrence rate - Defined as AF or atrial tachycardia lasting over 30 seconds after 3 months of procedure. Rhythm monitoring based on 2012 ACC/AHA/HRS guidelines as described above. 24-hour Holter ECG monitoring will be performed at 2-3 month and every 6 months within 2 years of procedure, Holter every 1 year after 2 years of procedure and ECG and monitoring with a Holter or an event recorder will be performed at any time if the patient complains of symptoms	Up to 5 years

Secondary Outcome Measures

Outcome Measure	Time Frame
Comparison of procedure time, ablation time and hospitalization period	Immediate after procedure
Anti-arrhythmic drug or anticoagulation therapy related complication rate	1 week, 3, 6, 12, 18, 24, 36 months after procedure
number of electrical cardioversion after the procedure	1 week, 3, 6, 12, 18, 24, 36 months after procedure
Major cardiovascular event rate - Death, myocardial infarction, coronary angioplasty, and re-hospitalization for arrhythmia and heart failure	Immediate after procedure
Re-hospitalization rate of electrical cardioverson after the procedure	1 week, 3, 6, 12, 18, 24, 36 months after procedure

Collaborators and Investigators

• Sponsor: Yonsei University
• Investigators: Principal Investigator: Hui-Nam Pak, Severance Hospital, Yonsei University Health System

Study record dates

Study Major Dates

• Study Start (Actual): October 7, 2021
• Primary Completion (Anticipated): June 1, 2031
• Study Completion (Anticipated): June 1, 2031

Study Registration Dates

• First Submitted: July 19, 2021
• First Submitted That Met QC Criteria: August 9, 2021
• First Posted (Actual): August 10, 2021

Study Record Updates

• Last Update Posted (Actual): May 24, 2023
• Last Update Submitted That Met QC Criteria: May 22, 2023
• Last Verified: May 1, 2023

More Information

Terms related to this study

• Additional Relevant MeSH Terms: Pathologic Processes; Heart Diseases; Cardiovascular Diseases; Arrhythmias, Cardiac; Atrial Fibrillation
• Other Study ID Numbers: 4-2021-0608

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