Korean Circulation Journal

  • 제53권10호
  • /
  • Pages.677-689
  • /
  • 2023
  • /
  • 1738-5520(pISSN)
  • /
  • 1738-5555(eISSN)
대한심장학회 (The Korean Society of Cardiology)
권호 표지
DOI QR코드

DOI QR Code

Machine Learning Prediction for the Recurrence After Electrical Cardioversion of Patients With Persistent Atrial Fibrillation

  • Soonil Kwon (Department of Internal Medicine, Seoul National University Hospital) ;
  • Eunjung Lee (Department of Cardiovascular Medicine, Mayo Clinic) ;
  • Hojin Ju (Department of Internal Medicine, Seoul National University Hospital) ;
  • Hyo-Jeong Ahn (Department of Internal Medicine, Seoul National University Hospital) ;
  • So-Ryoung Lee (Department of Internal Medicine, Seoul National University Hospital) ;
  • Eue-Keun Choi (Department of Internal Medicine, Seoul National University Hospital) ;
  • Jangwon Suh (Department of Intelligence and Information, Seoul National University) ;
  • Seil Oh (Department of Internal Medicine, Seoul National University Hospital) ;
  • Wonjong Rhee (Department of Intelligence and Information, Seoul National University)
  • 투고 : 2023.01.09
  • 심사 : 2023.06.13
  • 발행 : 2023.10.01
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

Background and Objectives: There is limited evidence regarding machine-learning prediction for the recurrence of atrial fibrillation (AF) after electrical cardioversion (ECV). This study aimed to predict the recurrence of AF after ECV using machine learning of clinical features and electrocardiograms (ECGs) in persistent AF patients. Methods: We analyzed patients who underwent successful ECV for persistent AF. Machine learning was designed to predict patients with 1-month recurrence. Individual 12-lead ECGs were collected before and after ECV. Various clinical features were collected and trained the extreme gradient boost (XGBoost)-based model. Ten-fold cross-validation was used to evaluate the performance of the model. The performance was compared to the C-statistics of the selected clinical features. Results: Among 718 patients (mean age 63.5±9.3 years, men 78.8%), AF recurred in 435 (60.6%) patients after 1 month. With the XGBoost-based model, the areas under the receiver operating characteristic curves (AUROCs) were 0.57, 0.60, and 0.63 if the model was trained by clinical features, ECGs, and both (the final model), respectively. For the final model, the sensitivity, specificity, and F1-score were 84.7%, 28.2%, and 0.73, respectively. Although the AF duration showed the best predictive performance (AUROC, 0.58) among the clinical features, it was significantly lower than that of the final machine-learning model (p<0.001). Additional training of extended monitoring data of 15-minute single-lead ECG and photoplethysmography in available patients (n=261) did not significantly improve the model's performance. Conclusions: Machine learning showed modest performance in predicting AF recurrence after ECV in persistent AF patients, warranting further validation studies.

키워드

과제정보

This research was supported by the Korean Cardiac Research Foundation (No. 201901-01), the SNUH Research Fund (No. 0320202040), and the Korea Medical Device Development Fund by the Korean government (Ministry of Science and Information and Communications Technology, Ministry of Trade, Industry and Energy, Ministry of Health and Welfare, Republic of Korea, Ministry of Food and Drug Safety; project number 202013B14).

참고문헌

  1. Kirchhof P, Benussi S, Kotecha D, et al. 2016 ESC Guidelines for the management of atrial fibrillation developed in collaboration with EACTS. Europace 2016;18:1609-78. https://doi.org/10.1093/europace/euw295
  2. Juul-Moller S, Edvardsson N, Rehnqvist-Ahlberg N. Sotalol versus quinidine for the maintenance of sinus rhythm after direct current conversion of atrial fibrillation. Circulation 1990;82:1932-9. https://doi.org/10.1161/01.CIR.82.6.1932
  3. Van Gelder IC, Crijns HJ, Van Gilst WH, Van Wijk LM, Hamer HP, Lie KI. Efficacy and safety of flecainide acetate in the maintenance of sinus rhythm after electrical cardioversion of chronic atrial fibrillation or atrial flutter. Am J Cardiol 1989;64:1317-21. https://doi.org/10.1016/0002-9149(89)90574-2
  4. Van Gelder IC, Crijns HJ. Cardioversion of atrial fibrillation and subsequent maintenance of sinus rhythm. Pacing Clin Electrophysiol 1997;20:2675-83. https://doi.org/10.1111/j.1540-8159.1997.tb06116.x
  5. Inoue K, Kurotobi T, Kimura R, et al. Trigger-based mechanism of the persistence of atrial fibrillation and its impact on the efficacy of catheter ablation. Circ Arrhythm Electrophysiol 2012;5:295-301. https://doi.org/10.1161/CIRCEP.111.964080
  6. Brandes A, Crijns HJ, Rienstra M, et al. Cardioversion of atrial fibrillation and atrial flutter revisited: current evidence and practical guidance for a common procedure. Europace 2020;22:1149-61. https://doi.org/10.1093/europace/euaa057
  7. Ehrlich JR, Schadow K, Steul K, Zhang GQ, Israel CW, Hohnloser SH. Prediction of early recurrence of atrial fibrillation after external cardioversion by means of P wave signal-averaged electrocardiogram. Z Kardiol 2003;92:540-6. https://doi.org/10.1007/s00392-003-0940-5
  8. Walek P, Sielski J, Starzyk K, Gorczyca I, Roskal-Walek J, Wozakowska-Kaplon B. Echocardiographic assessment of left atrial morphology and function to predict maintenance of sinus rhythm after electrical cardioversion in patients with non-valvular persistent atrial fibrillation and normal function or mild dysfunction of left ventricle. Cardiol J 2020;27:246-53. https://doi.org/10.5603/CJ.a2019.0068
  9. Andersson J, Rosenqvist M, Tornvall P, Boman K. NT-proBNP predicts maintenance of sinus rhythm after electrical cardioversion. Thromb Res 2015;135:289-91. https://doi.org/10.1016/j.thromres.2014.11.014
  10. Liu T, Li G, Li L, Korantzopoulos P. Association between C-reactive protein and recurrence of atrial fibrillation after successful electrical cardioversion: a meta-analysis. J Am Coll Cardiol 2007;49:1642-8. https://doi.org/10.1016/j.jacc.2006.12.042
  11. Vizzardi E, Curnis A, Latini MG, et al. Risk factors for atrial fibrillation recurrence: a literature review. J Cardiovasc Med (Hagerstown) 2014;15:235-53. https://doi.org/10.2459/JCM.0b013e328358554b
  12. Al'Aref SJ, Anchouche K, Singh G, et al. Clinical applications of machine learning in cardiovascular disease and its relevance to cardiac imaging. Eur Heart J 2019;40:1975-86. https://doi.org/10.1093/eurheartj/ehy404
  13. Feeny AK, Chung MK, Madabhushi A, et al. Artificial intelligence and machine learning in arrhythmias and cardiac electrophysiology. Circ Arrhythm Electrophysiol 2020;13:e007952.
  14. Breiman L. Random forests. Mach Learn 2001;45:5-32. https://doi.org/10.1023/A:1010933404324
  15. Kwon S, Hong J, Choi EK, et al. Detection of atrial fibrillation using a ring-type wearable device (CardioTracker) and deep learning analysis of photoplethysmography signals: prospective observational proof-of-concept study. J Med Internet Res 2020;22:e16443.
  16. Hansen ML, Jepsen RM, Olesen JB, et al. Thromboembolic risk in 16 274 atrial fibrillation patients undergoing direct current cardioversion with and without oral anticoagulant therapy. Europace 2015;17:18-23. https://doi.org/10.1093/europace/euu189
  17. Apostolakis S, Haeusler KG, Oeff M, et al. Low stroke risk after elective cardioversion of atrial fibrillation: an analysis of the Flec-SL trial. Int J Cardiol 2013;168:3977-81. https://doi.org/10.1016/j.ijcard.2013.06.090
  18. Hindricks G, Potpara T, Dagres N, et al. 2020 ESC Guidelines for the diagnosis and management of atrial fibrillation developed in collaboration with the European Association for Cardio-Thoracic Surgery (EACTS): The Task Force for the diagnosis and management of atrial fibrillation of the European Society of Cardiology (ESC) Developed with the special contribution of the European Heart Rhythm Association (EHRA) of the ESC. Eur Heart J 2021;42:373-498. https://doi.org/10.1093/eurheartj/ehaa612
  19. Vinter N, Frederiksen AS, Albertsen AE, et al. Role for machine learning in sex-specific prediction of successful electrical cardioversion in atrial fibrillation? Open Heart 2020;7:e001297.
  20. Nunez-Garcia JC, Sanchez-Puente A, Sampedro-Gomez J, et al. Outcome analysis in elective electrical cardioversion of atrial fibrillation patients: development and validation of a machine learning prognostic model. J Clin Med 2022;11:2636.
  21. Weimann K, Conrad TOF. Transfer learning for ECG classification. Sci Rep 2021;11:5251.
  22. Weijs B, Limantoro I, Delhaas T, et al. Cardioversion of persistent atrial fibrillation is associated with a 24-hour relapse gap: observations from prolonged postcardioversion rhythm monitoring. Clin Cardiol 2018;41:366-71. https://doi.org/10.1002/clc.22877