ABSTRACT
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.
