Dataset Information

AFA-Recur: an ESC EORP AFA-LT registry machine-learning web calculator predicting atrial fibrillation recurrence after ablation.

ABSTRACT:

Aims

Atrial fibrillation (AF) recurrence during the first year after catheter ablation remains common. Patient-specific prediction of arrhythmic recurrence would improve patient selection, and, potentially, avoid futile interventions. Available prediction algorithms, however, achieve unsatisfactory performance. Aim of the present study was to derive from ESC-EHRA Atrial Fibrillation Ablation Long-Term Registry (AFA-LT) a machine-learning scoring system based on pre-procedural, easily accessible clinical variables to predict the probability of 1-year arrhythmic recurrence after catheter ablation.

Methods and results

Patients were randomly split into a training (80%) and a testing cohort (20%). Four different supervised machine-learning models (decision tree, random forest, AdaBoost, and k-nearest neighbour) were developed on the training cohort and hyperparameters were tuned using 10-fold cross validation. The model with the best discriminative performance on the testing cohort (area under the curve-AUC) was selected and underwent further optimization, including re-calibration. A total of 3128 patients were included. The random forest model showed the best performance on the testing cohort; a 19-variable version achieved good discriminative performance [AUC 0.721, 95% confidence interval (CI) 0.680-0.764], outperforming existing scores (e.g. APPLE score: AUC 0.557, 95% CI 0.506-0.607). Platt scaling was used to calibrate the model. The final calibrated model was implemented in a web calculator, freely available at http://afarec.hpc4ai.unito.it/.

Conclusion

AFA-Recur, a machine-learning-based probability score predicting 1-year risk of recurrent atrial arrhythmia after AF ablation, achieved good predictive performance, significantly better than currently available tools. The calculator, freely available online, allows patient-specific predictions, favouring tailored therapeutic approaches for the individual patient.

SUBMITTER: Saglietto A

PROVIDER: S-EPMC10103564 | biostudies-literature | 2023 Feb

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

AFA-Recur: an ESC EORP AFA-LT registry machine-learning web calculator predicting atrial fibrillation recurrence after ablation.

Saglietto Andrea A Gaita Fiorenzo F Blomstrom-Lundqvist Carina C Arbelo Elena E Dagres Nikolaos N Brugada Josep J Maggioni Aldo Pietro AP Tavazzi Luigi L Kautzner Josef J De Ferrari Gaetano Maria GM Anselmino Matteo M

Europace : European pacing, arrhythmias, and cardiac electrophysiology : journal of the working groups on cardiac pacing, arrhythmias, and cardiac cellular electrophysiology of the European Society of Cardiology 20230201 1

<h4>Aims</h4>Atrial fibrillation (AF) recurrence during the first year after catheter ablation remains common. Patient-specific prediction of arrhythmic recurrence would improve patient selection, and, potentially, avoid futile interventions. Available prediction algorithms, however, achieve unsatisfactory performance. Aim of the present study was to derive from ESC-EHRA Atrial Fibrillation Ablation Long-Term Registry (AFA-LT) a machine-learning scoring system based on pre-procedural, easily acc ...[more]

PMID: 36006664

Similar Datasets

Project description:AimsWe sought to describe the clinical presentation, management, and 6-month outcomes in women with peripartum cardiomyopathy (PPCM) globally.Methods and resultsIn 2011, >100 national and affiliated member cardiac societies of the European Society of Cardiology (ESC) were contacted to contribute to a global registry on PPCM, under the auspices of the ESC EURObservational Research Programme. These societies were tasked with identifying centres who could participate in this registry. In low-income countries, e.g. Mozambique or Burkina Faso, where there are no national societies due to a shortage of cardiologists, we identified potential participants through abstracts and publications and encouraged participation into the study. Seven hundred and thirty-nine women were enrolled in 49 countries in Europe (33%), Africa (29%), Asia-Pacific (15%), and the Middle East (22%). Mean age was 31 ± 6 years, mean left ventricular ejection fraction (LVEF) was 31 ± 10%, and 10% had a previous pregnancy complicated by PPCM. Symptom-onset occurred most often within 1 month of delivery (44%). At diagnosis, 67% of patients had severe (NYHA III/IV) symptoms and 67% had a LVEF ≤35%. Fifteen percent received bromocriptine with significant regional variation (Europe 15%, Africa 26%, Asia-Pacific 8%, the Middle East 4%, P < 0.001). Follow-up was available for 598 (81%) women. Six-month mortality was 6% overall, lowest in Europe (4%), and highest in the Middle East (10%). Most deaths were due to heart failure (42%) or sudden (30%). Re-admission for any reason occurred in 10% (with just over half of these for heart failure) and thromboembolic events in 7%. Myocardial recovery (LVEF > 50%) occurred only in 46%, most commonly in Asia-Pacific (62%), and least commonly in the Middle East (25%). Neonatal death occurred in 5% with marked regional variation (Europe 2%, the Middle East 9%).ConclusionPeripartum cardiomyopathy is a global disease, but clinical presentation and outcomes vary by region. Just under half of women experience myocardial recovery. Peripartum cardiomyopathy is a disease with substantial maternal and neonatal morbidity and mortality.

Dataset Information

AFA-Recur: an ESC EORP AFA-LT registry machine-learning web calculator predicting atrial fibrillation recurrence after ablation.

Aims

Methods and results

Conclusion

Publications

AFA-Recur: an ESC EORP AFA-LT registry machine-learning web calculator predicting atrial fibrillation recurrence after ablation.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets