Artificial Intelligence to Predict Major Arrhythmic Events Based on Left Ventricular Electroanatomic Mapping Data

Background/Objectives: Electroanatomic mapping (EAM) provides high-resolution spatial and electrogram information, but the prognostic utility of quantitative EAM features has not been systematically evaluated with contemporary artificial intelligence (AI) methods. We investigated whether an AI analysis of quantitative EAM exports from the CARTO system enhances the prediction of major arrhythmic events (MAEs). Methods: In this retrospective, multicenter cohort study, 248 consecutive patients undergoing left ventricular EAM at four tertiary electrophysiology centers were analyzed. Numerical EAM descriptors (spatial coordinates, unipolar/bipolar voltages, local activation time, impedance) were transformed into derived metrics, including local activation heterogeneity (GR), late-potential extent (LAT), bipolar-unipolar discrepancy (VLT), and low-amplitude scar extent (Scar Areas), and were spatially normalized via spherical projection. Clinical, anamnestic, and imaging variables were integrated. Machine learning and deep learning models were trained with an 80:20 train/test split and evaluated using three-fold cross-validation. Performance metrics included area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, specificity, and precision. Results: Models incorporating both clinical and AI-processed EAM features achieved high discriminatory performance (test AUC up to 0.92; accuracy up to 0.896). Specificity was consistently high (≈0.97-0.998), whereas sensitivity remained modest (≈0.39-0.58). Among the EAM-derived features, GR was the most consistently informative predictor across algorithms and analyses; VLT, LAT, and Scar Areas also contributed substantially. Regionally, basal sub-mitral, subaortic, and posterolateral basal-to-mid zones exhibited the strongest associations with MAEs. Conclusions: AI-driven quantitative analysis of left ventricular EAM exports augments risk stratification for MAEs beyond conventional clinical and binary EAM descriptors. Reflecting local conduction heterogeneity, GR emerged as the dominant EAM predictor. Prospective validation in larger, disease-specific cohorts and real-time integration within EAM platforms are warranted.