Accurate and efficient cardiac digital twin from surface ECGs: Insights into identifiability of ventricular conduction system

Digital twins for cardiac electrophysiology are an enabling technology for precision cardiology. Current forward models are advanced enough to simulate the cardiac electric activity under different pathophysiological conditions and accurately replicate clinical signals like torso electrocardiograms (ECGs). In this work, we address the challenge of matching subject-specific QRS complexes using anatomically accurate, physiologically grounded cardiac digital twins. By fitting the initial conditions of a cardiac propagation model, our non-invasive method predicts activation patterns during sinus rhythm. For the first time, we demonstrate that distinct activation maps can generate identical surface ECGs. To address this non-uniqueness, we introduce a physiological prior based on the distribution of Purkinje-muscle junctions. Additionally, we develop a digital twin ensemble for probabilistic inference of cardiac activation. Our approach marks a significant advancement in the calibration of cardiac digital twins and enhances their credibility for clinical application. • We address the challenge of constructing cardiac digital twins (CDTs) for ventricular electrophysiology using purely non-invasive widely available clinical data, such as cardiac imaging and the 12-lead surface ECG. • Our CDTs are anatomically accurate and can reproduce the observed QRS complexes of the surface ECG with unprecedented fidelity. • We identify the ventricular conduction system, thereby endowing CDTs with verifiable predictive capabilities. • The construction of the CDT is orders of magnitude faster than existing methods, taking less than 20 min on a single workstation, scales excellently with the number of parameters, and can incorporate prior physiological knowledge as regularization. • We demonstrate that in the absence of prior physiological information, distinct activation patterns can yield identical surface ECGs. • We quantify the uncertainty in the reconstruction with an ensemble method, showing the robustness of our method.