Detail
Article
Online article
FT
Medvik - BMC
  • Something wrong with this record ?

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

A. Saglietto, F. Gaita, C. Blomstrom-Lundqvist, E. Arbelo, N. Dagres, J. Brugada, AP. Maggioni, L. Tavazzi, J. Kautzner, GM. De Ferrari, M. Anselmino

. 2023 ; 25 (1) : 92-100. [pub] 2023Feb08

Language English Country England, Great Britain

Document type Journal Article

Persistent link   https://www.medvik.cz/link/bmc23004226

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.

References provided by Crossref.org

000      
00000naa a2200000 a 4500
001      
bmc23004226
003      
CZ-PrNML
005      
20230425141223.0
007      
ta
008      
230418s2023 enk f 000 0|eng||
009      
AR
024    7_
$a 10.1093/europace/euac145 $2 doi
035    __
$a (PubMed)36006664
040    __
$a ABA008 $b cze $d ABA008 $e AACR2
041    0_
$a eng
044    __
$a enk
100    1_
$a Saglietto, Andrea $u Division of Cardiology, Department of Medical Sciences, 'Città della Salute e della Scienza di Torino' Hospital, University of Turin, Turin, Italy $1 https://orcid.org/0000000194751507
245    10
$a AFA-Recur: an ESC EORP AFA-LT registry machine-learning web calculator predicting atrial fibrillation recurrence after ablation / $c A. Saglietto, F. Gaita, C. Blomstrom-Lundqvist, E. Arbelo, N. Dagres, J. Brugada, AP. Maggioni, L. Tavazzi, J. Kautzner, GM. De Ferrari, M. Anselmino
520    9_
$a 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.
650    _2
$a lidé $7 D006801
650    12
$a fibrilace síní $x diagnóza $x chirurgie $7 D001281
650    _2
$a registrace $7 D012042
650    _2
$a strojové učení $7 D000069550
650    12
$a katetrizační ablace $x škodlivé účinky $x metody $7 D017115
650    _2
$a recidiva $7 D012008
650    _2
$a rizikové faktory $7 D012307
650    _2
$a výsledek terapie $7 D016896
655    _2
$a časopisecké články $7 D016428
700    1_
$a Gaita, Fiorenzo $u Cardiology Unit, J Medical, Turin, Italy $1 https://orcid.org/0000000331786205
700    1_
$a Blomstrom-Lundqvist, Carina $u Department of Medical Science and Cardiology, Uppsala University, Uppsala, Sweden $1 https://orcid.org/0000000328063903
700    1_
$a Arbelo, Elena $u Department of Cardiology, Cardiovascular Institut, Hospital Clinic de Barcelona, Universitat de Barcelona, Barcelona, Spain $u Institut d'Investigació August Pi iSunyer (IDIBAPS), Barcelona, Spain $u Centro de Investigación Biomédica en Red de Enfermedades Cardiovasculares (CIBERCV), Madrid, Spain $1 https://orcid.org/0000000304246393
700    1_
$a Dagres, Nikolaos $u Department of Electrophysiology, Heart Center Leipzig at University of Leipzig, Leipzig, Germany $1 https://orcid.org/0000000303234956
700    1_
$a Brugada, Josep $u Hospital Clínic Pediatric Arrhythmia Unit, Cardiovascular Institute, Hospital Sant Joan de Déu University of Barcelona, Barcelona, Spain $1 https://orcid.org/0000000256628302 $7 xx0272940
700    1_
$a Maggioni, Aldo Pietro $u EURObservational Research Programme (EORP), European Society of Cardiology, Sophia-Antipolis, France $u ANMCO Research Centre, Florence, Italy $1 https://orcid.org/0000000327646779
700    1_
$a Tavazzi, Luigi $u Cardiovascular Department, Maria Cecilia Hospital, GVM Care & Research, Cotignola, Italy $1 https://orcid.org/0000000344485209
700    1_
$a Kautzner, Josef $u Department of Cardiology, Institute for Clinical and Experimental Medicine (ΙΚΕΜ), Prague, Czech Republic $1 https://orcid.org/0000000216326182 $7 xx0037112
700    1_
$a De Ferrari, Gaetano Maria $u Division of Cardiology, Department of Medical Sciences, 'Città della Salute e della Scienza di Torino' Hospital, University of Turin, Turin, Italy $1 https://orcid.org/0000000349400876
700    1_
$a Anselmino, Matteo $u Division of Cardiology, Department of Medical Sciences, 'Città della Salute e della Scienza di Torino' Hospital, University of Turin, Turin, Italy $1 https://orcid.org/0000000263114270
773    0_
$w MED00149837 $t 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 $x 1532-2092 $g Roč. 25, č. 1 (2023), s. 92-100
856    41
$u https://pubmed.ncbi.nlm.nih.gov/36006664 $y Pubmed
910    __
$a ABA008 $b sig $c sign $y p $z 0
990    __
$a 20230418 $b ABA008
991    __
$a 20230425141219 $b ABA008
999    __
$a ok $b bmc $g 1924724 $s 1190435
BAS    __
$a 3
BAS    __
$a PreBMC-MEDLINE
BMC    __
$a 2023 $b 25 $c 1 $d 92-100 $e 2023Feb08 $i 1532-2092 $m Europace $n Europace $x MED00149837
LZP    __
$a Pubmed-20230418

Find record

Citation metrics

Archiving options