Search

Introduction: Training in clinical cardiac electrophysiology (CCEP) involves the development of catheter handling skills to safely deliver effective treatment. Objective data from analysis of ablation data for evaluating trainee of CCEP procedures has not previously been possible. Using the artificial intelligence cloud‐based system (CARTONET), we assessed the impact of trainee progress through ablation procedural quality. Methods: Lesion‐ and procedure‐level data from all de novo atrial fibrillation (AF) and cavotricuspid isthmus (CTI) ablations involving first‐year (Y1) or second‐year (Y2) fellows across a full year of fellowship was curated within Cartonet. Lesions were automatically assigned to anatomic locations. Results: Lesion characteristics, including contact force, catheter stability, impedance drop, ablation index value, and interlesion time/distance were similar over each training year. Anatomic location and supervising operator significantly affected catheter stability. The proportion of lesion sets delivered independently and of lesions delivered by the trainee increased steadily from the first quartile of Y1 to the last quartile of Y2. Trainee perception of difficult regions did not correspond to objective measures. Conclusion: Objective ablation data from Cartonet showed that the progression of trainees through CCEP training does not impact lesion‐level measures of treatment efficacy (i.e., catheter stability, impedance drop). Data demonstrates increasing independence over a training fellowship. Analyses like these could be useful to inform individualized training programs and to track trainee's progress. It may also be a useful quality assurance tool for ensuring ongoing consistency of treatment delivered within training institutions. [ABSTRACT FROM AUTHOR]

Radiofrequency ablation (RFA) using the CARTO 3D mapping system is a common approach for pulmonary vein isolation to treat atrial fibrillation (AF). Linkage between CARTO procedural data and patients' electronical health records (EHR) provides an opportunity to identify the ablation-related parameters that would predict AF recurrence. The objective of this study is to assess the incremental accuracy of RFA procedural data to predict post-ablation AF recurrence using machine learning model. Procedural data generated during RFA procedure were downloaded from CARTONET and linked to deidentified Mercy Health EHR data. Data were divided into train (70%) and test (30%) data for model development and validation. Automate machine learning (AutoML) was used to predict 1 year AF recurrence, defined as a composite of repeat ablation, electrical cardioversion, and AF hospitalization. At first, AutoML model only included Patients' demographic and clinical characteristics. Second, an AutoML model with procedural variables and demographical/clinical variables was developed. Area under receiver operating characteristic curve (AUROC) and net reclassification improvement (NRI) were used to compare model performances using test data. Among 306 patients, 67 (21.9%) patients experienced 1-year AF recurrence. AUROC increased from 0.66 to 0.78 after adding procedural data in the AutoML model based on test data. For patients with AF recurrence, NRI was 32% for model with procedural data. Nine of 10 important predictive features were CARTO procedural data. From CARTO procedural data, patients with lower contact force in right inferior site, long ablation duration, and low number of left inferior and right roof lesions had a higher risk of AF recurrence. Patients with persistent AF were more likely to have AF recurrence. The machine learning model with procedural data better predicted 1-year AF recurrence than the model without procedural data. The model could be used for identification of patients with high risk of AF recurrence post ablation. [ABSTRACT FROM AUTHOR]