Using AI to predict atrial fibrillation recurrence

Development and Validation of an Atrial Fibrillation Recurrence Model Based on Large Language Models: A Retrospective, Multicenter Study

Observational The Fourth Affiliated Hospital of Zhejiang University School of Medicine · NCT06977516

This study is testing a new way to use AI to help doctors predict if atrial fibrillation will come back after treatment, so they can better manage their patients.

Quick facts

Study typeObservational
Enrollment3000 (estimated)
Ages18 Years to 90 Years
SexAll
SponsorThe Fourth Affiliated Hospital of Zhejiang University School of Medicine Academic / other
Locations5 sites (Kunming, Yunnan and 4 other locations)
Trial IDNCT06977516 on ClinicalTrials.gov

What this trial studies

This study aims to develop a risk prediction model for atrial fibrillation (AF) recurrence by utilizing large language model (LLM) technology to analyze various textual data, including clinical characteristics and procedural records. By leveraging deep learning capabilities, the model seeks to provide actionable insights for electrophysiologists managing patients who have undergone catheter ablation for AF. The research will retrospectively collect data from multiple treatment centers to enhance the predictive accuracy of AF recurrence outcomes.

Who should consider this trial

Good fit: Ideal candidates for this study are patients diagnosed with atrial fibrillation who have undergone their first catheter ablation between January 2016 and December 2023.

Not a fit: Patients who may not benefit from this study include those undergoing repeated AF ablation procedures or those with incomplete follow-up data.

Why it matters

Potential benefit: If successful, this model could significantly improve the management and treatment outcomes for patients with atrial fibrillation by providing tailored risk assessments.

How similar studies have performed: While the application of large language models in medical risk prediction is novel, other studies have shown success in using advanced data analysis techniques for similar purposes.

Eligibility criteria

Show full inclusion / exclusion criteria
Inclusion Criteria:

We plan to retrospectively collect data from five atrial fibrillation treatment centers, including The Fourth Affiliated Hospital of Zhejiang University School of Medicine, Taizhou Hospital of Zhejiang Province, The Affiliated Hospital of Yunnan University, Jinhua People's Hospital, and Beilun District People's Hospital, for patients diagnosed with atrial fibrillation who underwent their first catheter ablation between January 2016 and December 2023.

Exclusion Criteria:

1. Patients undergoing repeated AF ablation procedures;
2. AF patients with incomplete follow-up data;
3. AF patients lacking preoperative laboratory tests or key textual modality results (echocardiography, ambulatory ECG);
4. Patients with comorbid conditions including acute myocardial infarction, valvular heart disease, malignant tumors, or hyperthyroidism, and those with AF recurrence within 3 months post-ablation.

Where this trial is running

Kunming, Yunnan and 4 other locations

Study contacts

How to participate

  1. Review the eligibility criteria above with your treating physician.
  2. Visit the official trial page on ClinicalTrials.gov for the most current contact information and recruitment status.
  3. Contact the listed study coordinator or principal investigator to request pre-screening. Pre-screening is free and never obligates you to enroll.
Conditions Atrial Fibrillation RecurrenceLarge Language ModelDeep LearningCatheter Ablation
Last reviewed 2026-06-09 by the Find a Trial editorial team. Information on this page is for educational purposes and is not medical advice. Always consult qualified healthcare professionals about clinical trial participation.