Int J Arrhythm.  2020 Dec;21(4):19. 10.1186/s42444-020-00027-3.

A deep learning model to predict recurrence of atrial fibrillation after pulmonary vein isolation

Affiliations
  • 1Division of Cardiology, Department of Internal Medicine, Uijeongbu St. Mary’s Hospital, College of Medicine, The Catholic University of Korea, Uijeongbu, Republic of Korea
  • 2Department of Computer Science and Engi‑ neering, College of Computing, Sungkyunkwan University, Suwon, Republic of Korea
  • 3Technical Research, Geotwo Co., Ltd, Gyeonggi‑do, Republic of Korea
  • 4Division of Cardiology, Department of Internal Medicine, Incheon St. Mary’s Hospital, College of Medicine, The Catholic University of Korea, Incheon, Republic of Korea
  • 5Division of Cardiology, Department of Internal Medicine, Seoul St. Mary’s Hospital, College of Medicine, The Catholic Univer‑ sity of Korea, 222 Banpo‑daero, Seocho‑gu, Seoul 06591, Republic of Korea.
  • 6Division of Cardiology, Department of Internal Medicine, St. Vincent’s Hos‑ pital, College of Medicine, The Catholic University of Korea, Suwon, Republic of Korea.
  • 7Division of Cardiology, Department of Internal Medicine, Daejeon St. Mary’s Hospital, College of Medicine, The Catholic University of Korea, Daejeon, Republic of Korea
  • 8Division of Cardiology, Department of Internal Medicine, Eunpyeong St. Mary’s Hospital, College of Medicine, The Catholic University of Korea, Seoul, Republic of Korea
  • 9Division of Cardiology, Depart‑ ment of Internal Medicine, Yeouido St. Mary’s Hospital, College of Medicine, The Catholic University of Korea, Seoul, Republic of Korea.

Abstract

Background and Objectives
The efficacy of radiofrequency catheter ablation (RFCA) in atrial fibrillation (AF) is well established. The standard approach to RFCA in AF is pulmonary vein isolation (PVI). However, a large proportion of patients experiences recurrence of atrial tachyarrhythmia. The purpose of this study is to find out whether the AI model can assess AF recurrence in patients who underwent PVI.
Materials and methods
This study was a retrospective cohort study that enrolled consecutive patients who under‑ went catheter ablation for symptomatic, drug-refractory AF and PVI. We developed an AI algorithm to predict recur‑ rence of AF after PVI using patient demographics and three-dimensional (3D) reconstructed left atrium (LA) images.
Results
We included 527 consecutive patients in the study. The overall mean LA diameter was 42.0 ± 6.8 mm, and the mean LA volume calculated using 3D reconstructed images was 151.1 ± 46.7 ml. During the follow-up period, atrial tachyarrhythmia recurred in 158 patients. The area under the curve (AUC) of the AI model based on a convolu‑ tional neural network (including 3D reconstruction images) was 0.61 (95% confidence interval [CI] 0.53–0.74) using the test dataset. The total test accuracy was 66.3% (57.0–75.6), and the sensitivity was 53.3% (34.8–71.9). The specificity was 73.2% (51.8–75.0), and the F1 score was 52.5% 34.5–66.7).
Conclusion
In this study, we developed an AI algorithm to predict recurrence of AF after catheter ablation of PVI using individual reconstructed LA images. This AI model was unable to predict recurrence of AF overwhelmingly; therefore, further large-scale study is needed.

Keyword

Left atrium; Atrial fibrillation; Pulmonary vein isolation; Catheter ablation
Full Text Links
  • IJA
Actions
Cited
CITED
export Copy
Close
Share
  • Twitter
  • Facebook
Similar articles
    DB Error: unknown error