Clinical Validation of the New 12-Lead ECG Noninvasive Panoramic Epi-endocardial Mapping Technology

Mikhail Chmelevsky1, Stepan Zubarev2, Svyatoslav Khamzin2, Arsenii Dokuchaev2, Anastasia Bazhutina2, Margarita Budanova2, Aleksandr Sinitca2, Angelo Auricchio1
1Division of Cardiology, Fondazione Cardiocentro Ticino, 2XSpline S.p.a.


Aim: Noninvasive electrocardiographic mapping systems require a high number of ECG body surface recordings (150-250 channels), which hinders their adoption into clinical practice. However, currently available noninvasive mapping systems provide accurate representation of epicardial activation only. In recent years, technical solutions such as machine learning algorithms have been implemented to improve the accuracy of ECG forward-inverse calculations. In this study, we developed a fully automated system for noninvasive panoramic epi-endocardial mapping based on 12-lead ECG to evaluate its accuracy in heart failure patients with typical LBBB. Methods: Eight heart failure patients (5 male, median age: 65) with typical LBBB (QRS duration 146–224 ms) underwent a cardiac CT scan and 12-lead ECG recording, followed by bi-ventricular endocardial electroanatomical contact mapping (EAM). A median of 258 (181-576) local electrograms in LV and 86 (70-139) in RV were collected during EAM. Noninvasive epi-endocardial activation maps were calculated using state-of-the-art mathematical models including machine learning methods. These data were compared with EAM from the invasive mapping system using Spearman correlation (r), mean absolute error (MAE) and relative distance metrics. Results: The study accurately identified all early and late activation patterns. The endocardial activation maps' average correlation was 0.92 for all cases, and the QRS complex was correctly reproduced by the new method in all cases (r = 0.96). The average distance error was 14 mm, and the mean absolute error was between 9-15 mm when the non-invasive late activation zone nearly matched the CARTO data. Conclusions: The study demonstrates that the new mapping technique accurately reconstructs endocardial electrical activation maps using a 12-lead ECG and cardiac CT scan. This approach may be helpful in pre-procedural planning of device implantation and catheter ablation. However, further studies are required to validate the method's accuracy at the epicardial site.