Outcome Analysis in Elective Electrical Cardioversion of Atrial Fibrillation Patients: Development and Validation of a Machine Learning Prognostic Model

被引:8
|
作者
Nunez-Garcia, Jean C. [1 ]
Sanchez-Puente, Antonio [1 ,2 ]
Sampedro-Gomez, Jesus [1 ,2 ]
Vicente-Palacios, Victor [1 ,3 ]
Jimenez-Navarro, Manuel [4 ,5 ]
Oterino-Manzanas, Armando [1 ]
Jimenez-Candil, Javier [1 ,2 ,6 ]
Dorado-Diaz, P. Ignacio [1 ,2 ]
Sanchez, Pedro L. [1 ,2 ,6 ]
机构
[1] Hosp Univ Salamanca IBSAL, Dept Cardiol, Salamanca 37007, Spain
[2] Inst Salud Carlos III, CIBERCV, Ctr Invest Biomed Red Enfermedades Cardiovasc, Monforte Lemos 3-5,Pabellon 11,Planta 0, Madrid 28029, Spain
[3] Philips Healthcare, Madrid 28050, Spain
[4] Hosp Virgen Victoria IBIMA, Dept Cardiol, Malaga 29010, Spain
[5] Univ Malaga, Fac Med, Malaga 29071, Spain
[6] Univ Salamanca, Dept Med, Salamanca 37007, Spain
关键词
machine-learning; electrical cardioversion; atrial fibrillation; rhythm control; pharmacologic cardioversion; SINUS RHYTHM; SUCCESS RATE; PREDICTION; RECURRENCE; MAINTENANCE; RISK;
D O I
10.3390/jcm11092636
中图分类号
R5 [内科学];
学科分类号
1002 ; 100201 ;
摘要
Background: The integrated approach to electrical cardioversion (EC) in atrial fibrillation (AF) is complex; candidates can resolve spontaneously while waiting for EC, and post-cardioversion recurrence is high. Thus, it is especially interesting to avoid the programming of EC in patients who would restore sinus rhythm (SR) spontaneously or present early recurrence. We have analyzed the whole elective EC of the AF process using machine-learning (ML) in order to enable a more realistic and detailed simulation of the patient flow for decision making purposes. Methods: The dataset consisted of electronic health records (EHRs) from 429 consecutive AF patients referred for EC. For analysis of the patient outcome, we considered five pathways according to restoring and maintaining SR: (i) spontaneous SR restoration, (ii) pharmacologic-cardioversion, (iii) direct-current cardioversion, (iv) 6-month AF recurrence, and (v) 6-month rhythm control. We applied ML classifiers for predicting outcomes at each pathway and compared them with the CHA2DS2-VASc and HATCH scores. Results: With the exception of pathway (iii), all ML models achieved improvements in comparison with CHA2DS2-VASc or HATCH scores (p < 0.01). Compared to the most competitive score, the area under the ROC curve (AUC-ROC) was: 0.80 vs. 0.66 for predicting (i); 0.71 vs. 0.55 for (ii); 0.64 vs. 0.52 for (iv); and 0.66 vs. 0.51 for (v). For a threshold considered optimal, the empirical net reclassification index was: +7.8%, +47.2%, +28.2%, and +34.3% in favor of our ML models for predicting outcomes for pathways (i), (ii), (iv), and (v), respectively. As an example tool of generalizability of ML models, we deployed our algorithms in an open-source calculator, where the model would personalize predictions. Conclusions: An ML model improves the accuracy of restoring and maintaining SR predictions over current discriminators. The proposed approach enables a detailed simulation of the patient flow through personalized predictions.
引用
收藏
页数:19
相关论文
共 50 条
  • [21] Predicting Electrical Cardioversion Outcome in Persistent Atrial Fibrillation Through Multiscale Entropy Analysis
    Cirugeda, E.
    Plancha, E.
    Hidalgo, V. M.
    Calero, S.
    Rieta, J. J.
    Alcaraz, R.
    2019 E-HEALTH AND BIOENGINEERING CONFERENCE (EHB), 2019,
  • [22] Role for machine learning in sex-specific prediction of successful electrical cardioversion in atrial fibrillation?
    Vinter, Nicklas
    Frederiksen, Anne Sofie
    Albertsen, Andi Eie
    Lip, Gregory Y. H.
    Fenger-Gron, Morten
    Trinquart, Ludovic
    Frost, Lars
    Moller, Dorthe Svenstrup
    OPEN HEART, 2020, 7 (01):
  • [23] Efficacy and Safety of Outpatient Clinic-based Elective External Electrical Cardioversion in Patients with Atrial Fibrillation
    Nguyen Khac Le Son
    Park, Je-Wook
    Kim, Min
    Yang, Song Yi
    Yu, Hee Tae
    Kim, Tae-Hoon
    Uhm, Jae-Sun
    Joung, Boyoung
    Lee, Moon-Hyoung
    Pak, Hui-Nam
    KOREAN CIRCULATION JOURNAL, 2020, 50 (06) : 511 - 523
  • [24] Atrial fibrillation of unknown duration: characteristics and outcome after electrical cardioversion
    Madrid, A
    Cabeza, P
    Marin, I
    Rebollo, J
    Bernal, E
    Limon, L
    Escobar, C
    Moro, C
    EUROPEAN HEART JOURNAL, 2003, 24 : 281 - 281
  • [25] Development and external validation of a prognostic model for occult atrial fibrillation in patients with ischemic stroke
    Wang, Xuan
    Meng, Longyan
    Zhao, Yanxin
    Liu, Xueyuan
    FRONTIERS IN NEUROLOGY, 2023, 13
  • [26] Adjunctive Pharmacotherapy for Elective Direct Current Cardioversion in Patients With Atrial Fibrillation
    Hirt, Liam S.
    Gobin, Maya S.
    CARDIOLOGY RESEARCH, 2012, 3 (04) : 158 - 163
  • [27] Prognostic significance of P wave morphology in post-electrical cardioversion atrial fibrillation patients
    Gouveia Fiuza, J. Joao
    Almeida, M. Duarte
    Ferreira, G. Rm
    Neto, V. Devesa
    Kungel, O.
    Santos, F. Rodrigues
    Pires, I.
    Craveiro, N.
    Pereira, J. Gil
    Costa, A.
    EUROPEAN JOURNAL OF HEART FAILURE, 2024, 26 : 5 - 6
  • [28] Wavelet transform analysis predicts outcome of DC cardioversion for atrial fibrillation patients
    Watson, J. N.
    Addison, P. S.
    Uchaipichat, N.
    Shah, A. S.
    Grubb, N. R.
    COMPUTERS IN BIOLOGY AND MEDICINE, 2007, 37 (04) : 517 - 523
  • [29] Prediction of outcome of electrical cardioversion by left atrial appendage flow velocities in atrial fibrillation
    Tanabe, K
    Yoshitomi, H
    Asanuma, T
    Okada, S
    Shimada, T
    Morioka, S
    JAPANESE CIRCULATION JOURNAL-ENGLISH EDITION, 1997, 61 (01): : 19 - 24
  • [30] Multidimensional Characterization of the Atrial Activity to Predict Electrical Cardioversion Outcome of Persistent Atrial Fibrillation
    Cirugeda, Eva
    Calero, Sofia
    Plancha, Eva
    Enero, Jose
    Rieta, Jose J.
    Alcaraz, Raul
    2020 COMPUTING IN CARDIOLOGY, 2020,