cAPM: Continual AI-assisted pace-mapping with active learning

Ventricular tachycardia (VT) is a life-threatening rhythm disorder and a major cause of sudden cardiac death. Pace-mapping is a standard clinical procedure for identifying the intervention target during catheter ablation of VT. It requires the clinicians to pace different sites in ventricles and rapidly interpret the resulting electrocardiograms (ECGs) to determine where to pace next or whether a target site has been identified. Active learning-based AI models have been proposed to guide clinicians to the next pacing site, showing promise in reducing the number of pacing sites and improving the efficiency of pace-mapping. Existing methods, however, require retraining from scratch for each target localization without the ability to transfer knowledge across multiple VTs within the same patient or across patients. We introduce cAPM for continuous AI-assisted pace-mapping to continually capture and transfer knowledge accumulated from past pace-mapping data to reduce the number of pace-mapping data needed for future target VTs. This is made possible by a task-agnostic surrogate neural network that learns the mapping from pacing sites to 12-lead ECG morphology, an active-learning strategy that refines this surrogate model by progressively selecting the most informative pacing site for each target, and a continual learning strategy to do so sequentially while retaining knowledge from prior targets. Evaluated on an in-silico testbed consisting of sequentially-presented localization tasks across different physiological conditions and ventricular geometries, averaging both proposed cAPM with and without replay of past data samples across all settings on average achieved an approximate 82% probability of localizing within clinical tolerance (5 mm accuracy) using just 4.5 pace-mapping sites, compared to the state-of-the-art active-learning method achieving an approximate 45% probability using 12.6 pacing sites. These results provide support for additional studies preparing cAPM towards prospective in-vivo preclinical and clinical studies where it can be used to guide pace-mapping on the fly.