EUVIMEDEUVIMED entdecken
Multizentrische StudieRandomisierte kontrollierte Studie

Machine Learning‐Driven Identification of Distinct Persistent Atrial Fibrillation Phenotypes: A Cluster Analysis of DECAAF II

Charbel Noujaim, Han Feng, Ghassan Bidaoui iD, Chao Huang, Hadi Younes iD, Ala Assaf, Mario Mekhael iD, Nour Chouman, Chanho Lim, Eoin Donnellan, Ghaith Shamaileh, Abdel Hadi El Hajjar iD und 5 weitere

Journal of Cardiovascular Electrophysiology · 2025-02 · 36 (2) · 457-466

DOI: 10.1111/jce.16554 ↗

Kurz gefasst

Multizentrische Studie in der Zeitschrift Journal of Cardiovascular Electrophysiology, online erschienen am 23.12.2024. Verfasst von Charbel Noujaim und 16 weiteren Autor:innen. Beteiligte Einrichtung: Tulane University School of Medicine, Department of Cardiology, Tulane Research Innovation for Arrhythmia Discovery, New Orleans, Louisiana, USA. Hauptthemen laut MEDLINE: Atrial Fibrillation, Catheter Ablation, Decision Support Techniques, Machine Learning. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 26 Literaturangaben. Gefördert von: This research was supported by the Medtronic, Abbott Laboratories, Siemens, GE Foundation, Biosense Webster, and Boston Scientific Corporation., Medtronic.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Introduction

Catheter ablation of persistent atrial fibrillation yields sub‐optimal success rates partly due to the considerable heterogeneity within the patient population. Identifying distinct patient phenotypes based on post‐ablation prognosis could improve patient selection for additional therapies and optimize treatment strategies.

Methods

We studied all patients who underwent catheter ablation of persistent atrial fibrillation in the DECAAF II trial. Out of 44 participating centers, 25% were randomly chosen as a validation set. A Gradient Boosting Method determined essential features for arrhythmia recurrence prediction and the number of clusters was determined according to the average silhouette width. K‐medoids cluster analysis identified subgroups based on these features, and Kaplan–Meier curves were further compared among different clusters.

Results

Among 815 patients, 570 served as a training set and 245 as a validation set. Using the training set, the GBM model achieved an AUC of 0.874. K‐medoids cluster analysis used LA volume, BMI, baseline fibrosis, and age, resulting in two clusters. Cluster 1 patients were older, had higher baseline fibrosis, higher BMI, and greater LA volume compared to Cluster 2. Atrial arrhythmia recurrence rates were significantly higher in Cluster 1 (51.7% vs. 35.0%, p = 0.0002), and survival analysis showed a significant difference in primary recurrence outcomes (HR = 1.71, p < 0.0001). The validation set confirmed these findings.

Conclusion

Utilizing machine learning, we identified a high‐risk cluster for procedural failure in catheter ablation of persistent atrial fibrillation within the DECAAF II trial population. The primary differentiating factors of this high‐risk cluster include older age, high left atrial fibrosis, elevated BMI, and increased left atrial volume.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Atrial FibrillationCatheter AblationDecision Support TechniquesMachine LearningAgedFemaleHumansMaleMiddle AgedAction PotentialsCluster AnalysisHeart RatePhenotypePredictive Value of TestsRecurrenceReproducibility of ResultsRisk AssessmentRisk FactorsTime FactorsTreatment Outcome

Stichwörter der Autor:innen

atrial fibrillationcatheter ablationclinical

Autor:innen und Institutionen

  • Tulane University School of Medicine, Department of Cardiology, Tulane Research Innovation for Arrhythmia Discovery, New Orleans, Louisiana, USA.

ORCID-Profile: Ghassan Bidaoui, Hadi Younes, Mario Mekhael, Abdel Hadi El Hajjar, Nassir Marrouche, Omar Kreidieh

Förderung

  • This research was supported by the Medtronic, Abbott Laboratories, Siemens, GE Foundation, Biosense Webster, and Boston Scientific Corporation.
  • Medtronic

Zitieren

APA

Noujaim, C., Feng, H., Bidaoui, G., Huang, C., Younes, H., Assaf, A., Mekhael, M., Chouman, N., Lim, C., Donnellan, E., Shamaileh, G., El Hajjar, A. H., Nelson, D., Dhore, A., Li, D., Marrouche, N., & Kreidieh, O. (2025). Machine Learning‐Driven Identification of Distinct Persistent Atrial Fibrillation Phenotypes: A Cluster Analysis of DECAAF II. Journal of Cardiovascular Electrophysiology, 36(2), 457-466. https://doi.org/10.1111/jce.16554

Vancouver

Noujaim C, Feng H, Bidaoui G, Huang C, Younes H, Assaf A, et al. Machine Learning‐Driven Identification of Distinct Persistent Atrial Fibrillation Phenotypes: A Cluster Analysis of DECAAF II. Journal of Cardiovascular Electrophysiology. 2025;36(2):457-466. doi:10.1111/jce.16554

BibTeX
@article{Noujaim2025,
  author = {Noujaim, Charbel and Feng, Han and Bidaoui, Ghassan and Huang, Chao and Younes, Hadi and Assaf, Ala and Mekhael, Mario and Chouman, Nour and Lim, Chanho and Donnellan, Eoin and Shamaileh, Ghaith and El Hajjar, Abdel Hadi and Nelson, Daniel and Dhore, Aneesh and Li, Dan and Marrouche, Nassir and Kreidieh, Omar},
  title = {Machine Learning‐Driven Identification of Distinct Persistent Atrial Fibrillation Phenotypes: A Cluster Analysis of DECAAF II},
  journal = {Journal of Cardiovascular Electrophysiology},
  year = {2025},
  volume = {36},
  number = {2},
  pages = {457--466},
  doi = {10.1111/jce.16554}
}
Kostenlos starten →