EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Dynamic Risk Assessment for the Development of Persistent Atrial Fibrillation Using Statistical and Machine Learning Approaches

Alexei Nakonechnyi iD, Shaul Geliaks iD, Ilan Goldenberg, Dillon J Dzikowicz iD, Emre Aktas, Susan Schleede, Scott McNitt, Agam Purohit, Burr W Hall, Spencer Z Rosero, David Z Huang, Amole O Ojo iD und 3 weitere

Annals of Noninvasive Electrocardiology · 2026

DOI: 10.1111/anec.70229 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Annals of Noninvasive Electrocardiology, 2026. Verfasst von Alexei Nakonechnyi und 14 weiteren Autor:innen. Beteiligte Einrichtung: University of Rochester Medical Center, Rochester, New York, USA. Hauptthemen laut MEDLINE: Atrial Fibrillation, Machine Learning, Defibrillators, Implantable, Electrocardiography. Die Arbeit nennt 15 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Cardiac implantable electronic devices (CIEDs) frequently detect brief, often subclinical atrial fibrillation (AF), but their value for predicting progression to persistent AF remains uncertain. Statistical and machine learning (ML) approaches may enable dynamic risk stratification using this longitudinal device data.

Objective

To develop a risk stratification model using clinical and CIED‐derived AF burden measured over a rolling 6‐month window to predict progression to persistent AF.

Methods

We analyzed continuous CIED data from 1985 patients without prior persistent AF implanted between 2016 and 2024 at a tertiary medical center. AF burden and clinical variables were summarized using overlapping 6‐month rolling windows to estimate 1‐year risk of persistent AF. Associations were evaluated using Kaplan–Meier and Cox proportional hazards models. A gradient‐boosted decision tree model (XGBoost) was used to predict progression.

Results

During a mean follow‐up of 1192 days, 874 patients (44%) developed paroxysmal AF, of whom 257 (29%) progressed to persistent AF after a mean of 813 days. Patients with no AF or < 1 h/day of AF in the prior 6 months had > 97% 1‐year freedom from persistent AF, whereas those with > 8 h/day had a 63% progression rate. Higher AF burden was strongly associated with progression (maximum HR 8.66, p < 0.001). The ML model demonstrated high predictive performance (sensitivity 99.4%, specificity 95.7%).

Conclusion

CIED‐detected AF burden is strongly associated with progression to persistent AF. ML‐based analysis of 6‐month device data enables accurate, point‐in‐time risk stratification to support earlier and more targeted clinical management.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Atrial FibrillationMachine LearningDefibrillators, ImplantableElectrocardiographyHumansRisk AssessmentFemaleMaleAgedDisease ProgressionPredictive Learning ModelsPrediction AlgorithmsMiddle AgedRetrospective Studies

Stichwörter der Autor:innen

atrial fibrillationcardiac implantable electronic devicesdisease progressionmachine learningprediction modelrisk assessment

Autor:innen und Institutionen

  • University of Rochester Medical Center, Rochester, New York, USA.

ORCID-Profile: Alexei Nakonechnyi, Shaul Geliaks, Dillon J Dzikowicz, Amole O Ojo, Wojciech Zareba, Michael Christof, Mehmet K Aktas

Zitieren

APA

Nakonechnyi, A., Geliaks, S., Goldenberg, I., Dzikowicz, D. J., Aktas, E., Schleede, S., McNitt, S., Purohit, A., Hall, B. W., Rosero, S. Z., Huang, D. Z., Ojo, A. O., Zareba, W., Christof, M., & Aktas, M. K. (2026). Dynamic Risk Assessment for the Development of Persistent Atrial Fibrillation Using Statistical and Machine Learning Approaches. Annals of Noninvasive Electrocardiology. https://doi.org/10.1111/anec.70229

Vancouver

Nakonechnyi A, Geliaks S, Goldenberg I, Dzikowicz DJ, Aktas E, Schleede S, et al. Dynamic Risk Assessment for the Development of Persistent Atrial Fibrillation Using Statistical and Machine Learning Approaches. Annals of Noninvasive Electrocardiology. 2026. doi:10.1111/anec.70229

BibTeX
@article{Nakonechnyi2026,
  author = {Nakonechnyi, Alexei and Geliaks, Shaul and Goldenberg, Ilan and Dzikowicz, Dillon J and Aktas, Emre and Schleede, Susan and McNitt, Scott and Purohit, Agam and Hall, Burr W and Rosero, Spencer Z and Huang, David Z and Ojo, Amole O and Zareba, Wojciech and Christof, Michael and Aktas, Mehmet K},
  title = {Dynamic Risk Assessment for the Development of Persistent Atrial Fibrillation Using Statistical and Machine Learning Approaches},
  journal = {Annals of Noninvasive Electrocardiology},
  year = {2026},
  doi = {10.1111/anec.70229}
}
Kostenlos starten →