September 16, 2025European Journal of Clinical InvestigationOpen Access

Machine learning‐based prediction of atrial fibrillation in patients with atrial high‐rate episodes

View Full Paper

Ask AI

Bookmark

Authors

AAAmir AskarinejadAhvaz Jundishapur University of Medical Sciences TBTommaso BucciUniversity of Liverpool NANiloofar AsgharzadehShaheed Rajaei Cardiovascular Medical and Research Center

Discussion

Member takes

Implication

Prospective study finds machine learning models can predict new-onset atrial fibrillation in patients with AHREs, suggesting improved risk assessment strategies.

Key Points

Machine learning predicts atrial fibrillation risk with an AUC of .857 in patients with atrial high-rate episodes.
The study found that 24% of patients developed atrial fibrillation after one year of follow-up, emphasizing the model's effectiveness.
Variables like left atrial enlargement, hypertension, diabetes, and age were significant predictors in the CatBoost machine learning model.
Further validation of the model in larger cohorts is necessary to enhance predictive accuracy for atrial fibrillation.

Cite This Study

Askarinejad et al. (2025) studied this question.

synapsesocial.com/papers/68d43b18713b0b5dfea7bb35 https://doi.org/10.1111/eci.70121

View Full Paper

Ask AI

Bookmark

Implication

Prospective study finds machine learning models can predict new-onset atrial fibrillation in patients with AHREs, suggesting improved risk assessment strategies.

Machine learning‐based prediction of atrial fibrillation in patients with atrial high‐rate episodes

Discussion

Member takes

Implication

Key Points

Cite This Study

Machine learning‐based prediction of atrial fibrillation in patients with atrial high‐rate episodes

Discussion

Member takes

Implication

Key Points

Cite This Study

Also Consider

Also Consider