27 47

Cited 0 times in

Machine Learning-Predicted Progression to Permanent Atrial Fibrillation After Catheter Ablation

Authors
 Je-Wook Park  ;  Oh-Seok Kwon  ;  Jaemin Shim  ;  Inseok Hwang  ;  Yun Gi Kim  ;  Hee Tae Yu  ;  Tae-Hoon Kim  ;  Jae-Sun Uhm  ;  Jong-Youn Kim  ;  Jong Il Choi  ;  Boyoung Joung  ;  Moon-Hyoung Lee  ;  Young-Hoon Kim  ;  Hui-Nam Pak 
Citation
 FRONTIERS IN CARDIOVASCULAR MEDICINE, Vol.9 : 813914, 2022-02 
Journal Title
FRONTIERS IN CARDIOVASCULAR MEDICINE
Issue Date
2022-02
Keywords
atrial fibrillation ; catheter ablation ; machine learning ; progression ; risk score
Abstract
Introduction: We developed a prediction model for atrial fibrillation (AF) progression and tested whether machine learning (ML) could reproduce the prediction power in an independent cohort using pre-procedural non-invasive variables alone.

Methods: Cohort 1 included 1,214 patients and cohort 2, 658, and all underwent AF catheter ablation (AFCA). AF progression to permanent AF was defined as sustained AF despite repeat AFCA or cardioversion under antiarrhythmic drugs. We developed a risk stratification model for AF progression (STAAR score) and stratified cohort 1 into three groups. We also developed an ML-prediction model to classify three STAAR risk groups without invasive parameters and validated the risk score in cohort 2.

Results: The STAAR score consisted of a stroke (2 points, p = 0.003), persistent AF (1 point, p = 0.049), left atrial (LA) dimension ≥43 mm (1 point, p = 0.010), LA voltage <1.109 mV (2 points, p = 0.004), and PR interval ≥196 ms (1 point, p = 0.001), based on multivariate Cox analyses, and it had a good discriminative power for progression to permanent AF [area under curve (AUC) 0.796, 95% confidence interval (CI): 0.753-0.838]. The ML prediction model calculated the risk for AF progression without invasive variables and achieved excellent risk stratification: AUC 0.935 for low-risk groups (score = 0), AUC 0.855 for intermediate-risk groups (score 1-3), and AUC 0.965 for high-risk groups (score ≥ 4) in cohort 1. The ML model successfully predicted the high-risk group for AF progression in cohort 2 (log-rank p < 0.001).

Conclusions: The ML-prediction model successfully classified the high-risk patients who will progress to permanent AF after AFCA without invasive variables but has a limited discrimination power for the intermediate-risk group.
Files in This Item:
T202200835.pdf Download
DOI
10.3389/fcvm.2022.813914
Appears in Collections:
1. College of Medicine (의과대학) > Dept. of Internal Medicine (내과학교실) > 1. Journal Papers
Yonsei Authors
Kim, Jong Youn(김종윤) ORCID logo https://orcid.org/0000-0001-7040-8771
Kim, Tae-Hoon(김태훈) ORCID logo https://orcid.org/0000-0003-4200-3456
Park, Je Wook(박제욱)
Pak, Hui Nam(박희남) ORCID logo https://orcid.org/0000-0002-3256-3620
Uhm, Jae Sun(엄재선) ORCID logo https://orcid.org/0000-0002-1611-8172
Yu, Hee Tae(유희태) ORCID logo https://orcid.org/0000-0002-6835-4759
Lee, Moon-Hyoung(이문형) ORCID logo https://orcid.org/0000-0002-7268-0741
Joung, Bo Young(정보영) ORCID logo https://orcid.org/0000-0001-9036-7225
URI
https://ir.ymlib.yonsei.ac.kr/handle/22282913/188310
사서에게 알리기
  feedback

qrcode

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

Browse

Links