Key result
Machine learning decision tree distinguishes non-fibrotic from fibrotic atrial tissue with ~98% accuracy.
Why the study?
In patients with atrial fibrillation, finding fibrotic areas and differentiating their density and transmurality to guide catheter ablation remains an open challenge.
Does a machine learning algorithm trained on hybrid in silico and in vivo datasets characterize atrial fibrotic substrate in patients with atrial fibrillation?
Does a machine learning algorithm trained on hybrid in silico and in vivo datasets characterize atrial fibrotic substrate in patients with atrial fibrillation?
A machine learning approach using hybrid in silico and in vivo electrogram data can characterize atrial fibrosis density and transmurality, potentially overcoming the limitations of single voltage cut-offs to guide ablation.
May aid fibrosis mapping for AF ablation; leaves open prospective validation in clinical trials.
In patients with atrial fibrillation, intracardiac electrogram signal amplitude is known to decrease with increased structural tissue remodeling, referred to as fibrosis. In addition to the isolation of the pulmonary veins, fibrotic sites are considered a suitable target for catheter ablation. However, it remains an open challenge to find fibrotic areas and to differentiate their density and transmurality. This study aims to identify the volume fraction and transmurality of fibrosis in the atrial substrate. Simulated cardiac electrograms, combined with a generalized model of clinical noise, reproduce clinically measured signals. Our hybrid dataset approach combines in silico and clinical electrograms to train a decision tree classifier to characterize the fibrotic atrial substrate. This approach captures different in vivo dynamics of the electrical propagation reflected on healthy electrogram morphology and synergistically combines it with synthetic fibrotic electrograms from in silico experiments. The machine learning algorithm was tested on five patients and compared against clinical voltage maps as a proof of concept, distinguishing non-fibrotic from fibrotic tissue and characterizing the patient’s fibrotic tissue in terms of density and transmurality. The proposed approach can be used to overcome a single voltage cut-off value to identify fibrotic tissue and guide ablation targeting fibrotic areas.
No takes yet. Share an insight, caveat, or question.
Sánchez et al. (2021) studied Persistent atrial fibrillation (n=9). Machine learning decision tree classifier vs. Clinical voltage maps (<0.5 mV cut-off) was evaluated on Accuracy for distinguishing non-fibrotic vs. fibrotic tissue. A machine learning decision tree classifier trained on a hybrid in silico and in vivo dataset distinguished non-fibrotic from fibrotic atrial tissue with a mean accuracy of 97.95%.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: