1
|
Liu CM, Chen WS, Chang SL, Hsieh YC, Hsu YH, Chang HX, Lin YJ, Lo LW, Hu YF, Chung FP, Chao TF, Tuan TC, Liao JN, Lin CY, Chang TY, Kuo L, Wu CI, Wu MH, Chen CK, Chang YY, Shiu YC, Lu HHS, Chen SA. Use of artificial intelligence and I-Score for prediction of recurrence before catheter ablation of atrial fibrillation. Int J Cardiol 2024; 402:131851. [PMID: 38360099 DOI: 10.1016/j.ijcard.2024.131851] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 11/13/2023] [Revised: 01/14/2024] [Accepted: 02/10/2024] [Indexed: 02/17/2024]
Abstract
BACKGROUND Based solely on pre-ablation characteristics, previous risk scores have demonstrated variable predictive performance. This study aimed to predict the recurrence of AF after catheter ablation by using artificial intelligence (AI)-enabled pre-ablation computed tomography (PVCT) images and pre-ablation clinical data. METHODS A total of 638 drug-refractory paroxysmal atrial fibrillation (AF) patients undergone ablation were recruited. For model training, we used left atria (LA) acquired from pre-ablation PVCT slices (126,288 images). A total of 29 clinical variables were collected before ablation, including baseline characteristics, medical histories, laboratory results, transthoracic echocardiographic parameters, and 3D reconstructed LA volumes. The I-Score was applied to select variables for model training. For the prediction of one-year AF recurrence, PVCT deep-learning and clinical variable machine-learning models were developed. We then applied machine learning to ensemble the PVCT and clinical variable models. RESULTS The PVCT model achieved an AUC of 0.63 in the test set. Various combinations of clinical variables selected by I-Score can yield an AUC of 0.72, which is significantly better than all variables or features selected by nonparametric statistics (AUCs of 0.66 to 0.69). The ensemble model (PVCT images and clinical variables) significantly improved predictive performance up to an AUC of 0.76 (sensitivity of 86.7% and specificity of 51.0%). CONCLUSIONS Before ablation, AI-enabled PVCT combined with I-Score features was applicable in predicting recurrence in paroxysmal AF patients. Based on all possible predictors, the I-Score is capable of identifying the most influential combination.
Collapse
Affiliation(s)
- Chih-Min Liu
- Heart Rhythm Center, Division of Cardiology, Department of Medicine, Taipei Veterans General Hospital, Taiwan; Cardiovascular Research Center, National Yang Ming Chiao Tung University, Taipei, Taiwan.
| | - Wei-Shiang Chen
- Institute of Statistics, National Yang Ming Chiao Tung University, Hsinchu, Taiwan
| | - Shih-Lin Chang
- Heart Rhythm Center, Division of Cardiology, Department of Medicine, Taipei Veterans General Hospital, Taiwan; Cardiovascular Research Center, National Yang Ming Chiao Tung University, Taipei, Taiwan
| | - Yu-Cheng Hsieh
- Cardiovascular Center, Taichung Veterans General Hospital, Taichung, Taiwan
| | - Yuan-Heng Hsu
- Institute of Statistics, National Yang Ming Chiao Tung University, Hsinchu, Taiwan
| | - Hao-Xiang Chang
- Institute of Statistics, National Yang Ming Chiao Tung University, Hsinchu, Taiwan
| | - Yenn-Jiang Lin
- Heart Rhythm Center, Division of Cardiology, Department of Medicine, Taipei Veterans General Hospital, Taiwan; Cardiovascular Research Center, National Yang Ming Chiao Tung University, Taipei, Taiwan
| | - Li-Wei Lo
- Heart Rhythm Center, Division of Cardiology, Department of Medicine, Taipei Veterans General Hospital, Taiwan; Cardiovascular Research Center, National Yang Ming Chiao Tung University, Taipei, Taiwan
| | - Yu-Feng Hu
- Heart Rhythm Center, Division of Cardiology, Department of Medicine, Taipei Veterans General Hospital, Taiwan; Cardiovascular Research Center, National Yang Ming Chiao Tung University, Taipei, Taiwan
| | - Fa-Po Chung
- Heart Rhythm Center, Division of Cardiology, Department of Medicine, Taipei Veterans General Hospital, Taiwan; Cardiovascular Research Center, National Yang Ming Chiao Tung University, Taipei, Taiwan
| | - Tze-Fan Chao
- Heart Rhythm Center, Division of Cardiology, Department of Medicine, Taipei Veterans General Hospital, Taiwan; Cardiovascular Research Center, National Yang Ming Chiao Tung University, Taipei, Taiwan
| | - Ta-Chuan Tuan
- Heart Rhythm Center, Division of Cardiology, Department of Medicine, Taipei Veterans General Hospital, Taiwan; Cardiovascular Research Center, National Yang Ming Chiao Tung University, Taipei, Taiwan
| | - Jo-Nan Liao
- Heart Rhythm Center, Division of Cardiology, Department of Medicine, Taipei Veterans General Hospital, Taiwan; Cardiovascular Research Center, National Yang Ming Chiao Tung University, Taipei, Taiwan
| | - Chin-Yu Lin
- Heart Rhythm Center, Division of Cardiology, Department of Medicine, Taipei Veterans General Hospital, Taiwan; Cardiovascular Research Center, National Yang Ming Chiao Tung University, Taipei, Taiwan
| | - Ting-Yung Chang
- Heart Rhythm Center, Division of Cardiology, Department of Medicine, Taipei Veterans General Hospital, Taiwan; Cardiovascular Research Center, National Yang Ming Chiao Tung University, Taipei, Taiwan
| | - Ling Kuo
- Heart Rhythm Center, Division of Cardiology, Department of Medicine, Taipei Veterans General Hospital, Taiwan; Cardiovascular Research Center, National Yang Ming Chiao Tung University, Taipei, Taiwan
| | - Cheng-I Wu
- Heart Rhythm Center, Division of Cardiology, Department of Medicine, Taipei Veterans General Hospital, Taiwan; Cardiovascular Research Center, National Yang Ming Chiao Tung University, Taipei, Taiwan
| | - Mei-Han Wu
- Department of Medical Imaging, Diagnostic Radiology, Cheng Hsin General Hospital, Taipei, Taiwan
| | - Chun-Ku Chen
- Department of Radiology, Taipei Veterans General Hospital, Taipei, Taiwan
| | - Ying-Yueh Chang
- Department of Radiology, Taipei Veterans General Hospital, Taipei, Taiwan
| | - Yang-Che Shiu
- Heart Rhythm Center, Division of Cardiology, Department of Medicine, Taipei Veterans General Hospital, Taiwan
| | - Henry Horng-Shing Lu
- Institute of Statistics, National Yang Ming Chiao Tung University, Hsinchu, Taiwan; Department of Statistics and Data Science, Cornell University, Ithaca, New York, USA.
| | - Shih-Ann Chen
- Heart Rhythm Center, Division of Cardiology, Department of Medicine, Taipei Veterans General Hospital, Taiwan; Cardiovascular Research Center, National Yang Ming Chiao Tung University, Taipei, Taiwan; Cardiovascular Center, Taichung Veterans General Hospital, Taichung, Taiwan; National Chung Hsing University, Taichung, Taiwan
| |
Collapse
|
2
|
Dong Y, Zhai Z, Zhu B, Xiao S, Chen Y, Hou A, Zou P, Xia Z, Yu J, Li J. Development and Validation of a Novel Prognostic Model Predicting the Atrial Fibrillation Recurrence Risk for Persistent Atrial Fibrillation Patients Treated with Nifekalant During the First Radiofrequency Catheter Ablation. Cardiovasc Drugs Ther 2023; 37:1117-1129. [PMID: 35731452 PMCID: PMC10721663 DOI: 10.1007/s10557-022-07353-9] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Accepted: 06/06/2022] [Indexed: 11/03/2022]
Abstract
BACKGROUND This study aimed to establish and assess a prediction model for patients with persistent atrial fibrillation (AF) treated with nifekalant during the first radiofrequency catheter ablation (RFCA). METHODS In this study, 244 patients with persistent AF from January 17, 2017 to December 14, 2017, formed the derivation cohort, and 205 patients with persistent AF from December 15, 2017 to October 28, 2018, constituted the validation cohort. The least absolute shrinkage and selection operator regression was used for variable screening and the multivariable Cox survival model for nomogram development. The accuracy and discriminative capability of this predictive model were assessed according to discrimination (area under the curve [AUC]) and calibration. Clinical practical value was evaluated using decision curve analysis. RESULTS Body mass index, AF duration, sex, left atrial diameter, and the different responses after nifekalant administration were identified as AF recurrence-associated factors, all of which were selected for the nomogram. In the development and validation cohorts, the AUC for predicting 1-year AF-free survival was 0.863 (95% confidence interval (CI) 0.801-0.926) and 0.855 (95% CI 0.782-0.929), respectively. The calibration curves showed satisfactory agreement between the actual AF-free survival and the nomogram prediction in the derivation and validation cohorts. In both groups, the prognostic score enabled stratifying the patients into different AF recurrence risk groups. CONCLUSIONS This predictive nomogram can serve as a quantitative tool for estimating the 1-year AF recurrence risk for patients with persistent AF treated with nifekalant during the first RFCA.
Collapse
Affiliation(s)
- Youzheng Dong
- Department of Cardiovascular Medicine, The Second Affiliated Hospital of Nanchang University, Nanchang, 330006, People's Republic of China
| | - Zhenyu Zhai
- Department of Cardiovascular Medicine, The Second Affiliated Hospital of Nanchang University, Nanchang, 330006, People's Republic of China
| | - Bo Zhu
- Department of Cardiovascular Medicine, The Second Affiliated Hospital of Nanchang University, Nanchang, 330006, People's Republic of China
| | - Shucai Xiao
- Department of Cardiovascular Medicine, The Second Affiliated Hospital of Nanchang University, Nanchang, 330006, People's Republic of China
| | - Yang Chen
- Department of Cardiovascular Medicine, The Second Affiliated Hospital of Nanchang University, Nanchang, 330006, People's Republic of China
| | - Anxue Hou
- Department of Cardiovascular Medicine, The Second Affiliated Hospital of Nanchang University, Nanchang, 330006, People's Republic of China
| | - Pengtao Zou
- Department of Cardiovascular Medicine, The Second Affiliated Hospital of Nanchang University, Nanchang, 330006, People's Republic of China
| | - Zirong Xia
- Department of Cardiovascular Medicine, The Second Affiliated Hospital of Nanchang University, Nanchang, 330006, People's Republic of China.
| | - Jianhua Yu
- Department of Cardiovascular Medicine, The Second Affiliated Hospital of Nanchang University, Nanchang, 330006, People's Republic of China.
| | - Juxiang Li
- Department of Cardiovascular Medicine, The Second Affiliated Hospital of Nanchang University, Nanchang, 330006, People's Republic of China.
| |
Collapse
|
3
|
Liu X, He Y, Gui C, Wen W, Jiang Z, Zhong G, Wu M. Comparison of clinical outcomes of Ibutilide-guided cardioversion and direct current synchronized cardioversion after radiofrequency ablation of persistent atrial fibrillation. Front Cardiovasc Med 2023; 10:1141698. [PMID: 38028483 PMCID: PMC10658000 DOI: 10.3389/fcvm.2023.1141698] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/10/2023] [Accepted: 10/25/2023] [Indexed: 12/01/2023] Open
Abstract
Backgroup Ibutilide has already been used for cardioversion of persistent atrial fibrillation (PsAF) after radiofrequency catheter ablation (RFCA). The purpose of this study was to determine the effect of Ibutilide-guided cardioversion on clinical outcomes after individualized ablation of PsAF. Methods From October 2020 to September 2021, consecutive patients with PsAF accepted for RFCA were prospectively enrolled. After individualized ablation including pulmonary vein isolation plus left atrial roof line ablation and personalized linear ablation based on left atrial low-voltage zones, patients were divided into the spontaneous conversion (SCV) group, direct current synchronized cardioversion (DCC) group and Ibutilide group according to different cardioversion types during ablation. The rates of freedom from atrial tachyarrhythmia (ATT) among the three groups were evaluated after follow-up. Results In this study, 110 patients were enrolled, including 12 patients with SCV, 50 patients receiving DCC and 48 patients receiving Ibutilide cardioversion after individualized ablation. Among the three groups, the SCV group had shorter AF duration {12 months [interquartile range (IQR) 12-16], P = 0.042} and smaller left atrial diameter (LAD) [35 mm (IQR: 33-42), P = 0.023]. A 12-month freedom from ATT rate was 83.3% in SCV group, 69.4% in DCC group, and 79.2% in Ibutilide group, respectively (Log-rank, P = 0.745). During the follow-up [17 months (IQR: 15-19)], the rate of freedom from ATT of SCV group (83.3%), and Ibutilide group (72.9%) were both higher than that of DCC group (53.1%, P = 0.042). Moreover, Kaplan-Meier analysis showed a significantly higher sinus rhythm (SR) maintenance in Ibutilide group than in DCC group (Log-rank, P = 0.041). After adjusting for risk factors of AF recurrence, the hazard ratio for AF recurrence of the DCC group with reference to the Ibutilide group was 4.10 [95% confidence interval (CI) (1.87-8.98), P < 0.001]. Furthermore, subgroup analysis showed that freedom from ATT rate in effective Ibutilide subgroup was significantly higher than noneffective Ibutilide subgroup (Log-rank, P < 0.001). Conclusion For the treatment of the patients with PsAF, Ibutilide-guided cardioversion after individualized RFCA may be benefit for maintenance of SR compared to conventional DCC, especially for the patients who are effective for administration of Ibutilide.
Collapse
Affiliation(s)
- Xing Liu
- Department of Cardiology, Xiangtan Central Hospital, Xiangtan, China
- Department of Cardiology, The First Affiliated Hospital of Guangxi Medical University, Nanning, China
| | - Yan He
- Department of Cardiology, The First Affiliated Hospital of Guangxi Medical University, Nanning, China
| | - Chun Gui
- Department of Cardiology, The First Affiliated Hospital of Guangxi Medical University, Nanning, China
| | - Weiming Wen
- Department of Cardiology, The First Affiliated Hospital of Guangxi Medical University, Nanning, China
| | - Zhiyuan Jiang
- Department of Cardiology, The First Affiliated Hospital of Guangxi Medical University, Nanning, China
| | - Guoqiang Zhong
- Department of Cardiology, The First Affiliated Hospital of Guangxi Medical University, Nanning, China
| | - Mingxing Wu
- Department of Cardiology, Xiangtan Central Hospital, Xiangtan, China
| |
Collapse
|
4
|
Guichard JB, Guasch E, Roche F, Da Costa A, Mont L. Premature atrial contractions: A predictor of atrial fibrillation and a relevant marker of atrial cardiomyopathy. Front Physiol 2022; 13:971691. [PMID: 36353376 PMCID: PMC9638131 DOI: 10.3389/fphys.2022.971691] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/17/2022] [Accepted: 10/14/2022] [Indexed: 09/08/2023] Open
Abstract
An increased burden of premature atrial contractions (PACs) has long been considered a benign phenomenon. However, strong evidence of their involvement in the occurrence of atrial fibrillation (AF), ischemic stroke, and excess mortality suggests the need for management. The central question to be resolved is whether increased ectopic atrial rhythm is only a predictor of AF or whether it is a marker of atrial cardiomyopathy and therefore of ischemic stroke. After reviewing the pathophysiology of PACs and its impact on patient prognosis, this mini-review proposes to 1) detail the physiological and clinical elements linking PACs and AF, 2) present the evidence in favor of supraventricular ectopic activity as a marker of cardiomyopathy, and 3) outline the current limitations of this concept and the potential future clinical implications.
Collapse
Affiliation(s)
- Jean-Baptiste Guichard
- Arrhythmia Unit, Hospital Clínic de Barcelona, Institut d’Investigacions Biomèdiques August Pi iSunyer (IDIBAPS), Universitat de Barcelona, Barcelona, Spain
- Centro de Investigación Biomédica en Red Enfermedades Cardiovasculares (CIBERCV), Madrid, Spain
- Department of Cardiology, University Hospital of Saint-Étienne, Saint-Étienne, France
- Sainbiose, DVH, Inserm U1059, University Hospital of Saint-Étienne, Saint-Étienne, France
| | - Eduard Guasch
- Arrhythmia Unit, Hospital Clínic de Barcelona, Institut d’Investigacions Biomèdiques August Pi iSunyer (IDIBAPS), Universitat de Barcelona, Barcelona, Spain
- Centro de Investigación Biomédica en Red Enfermedades Cardiovasculares (CIBERCV), Madrid, Spain
| | - Frederic Roche
- Sainbiose, DVH, Inserm U1059, University Hospital of Saint-Étienne, Saint-Étienne, France
| | - Antoine Da Costa
- Department of Cardiology, University Hospital of Saint-Étienne, Saint-Étienne, France
- Sainbiose, DVH, Inserm U1059, University Hospital of Saint-Étienne, Saint-Étienne, France
| | - Lluís Mont
- Arrhythmia Unit, Hospital Clínic de Barcelona, Institut d’Investigacions Biomèdiques August Pi iSunyer (IDIBAPS), Universitat de Barcelona, Barcelona, Spain
- Centro de Investigación Biomédica en Red Enfermedades Cardiovasculares (CIBERCV), Madrid, Spain
| |
Collapse
|