Key result
Physiology-aware graph attention classifier predicts sustained ventricular reentry with ~95% accuracy.
Why the study?
Post-infarct ventricular tachycardia risk is difficult to predict from infarct imaging alone, and exploring multiple substrates and pacing locations via in silico induction studies is computationally expensive.
Does a physiology-aware graph attention classifier accurately predict sustained ventricular reentry from early paced activations in simulated post-infarct cardiac electrophysiology substrates compared to full electrophysiology simulations and baseline models?
Does a physiology-aware graph attention classifier accurately predict sustained ventricular reentry from early paced activations in simulated post-infarct cardiac electrophysiology substrates compared to full electrophysiology simulations and baseline models?
A physiology-aware graph attention network can predict sustained ventricular reentry from the first two paced activations in silico with 94.6% accuracy while running nearly five orders of magnitude faster than full electrophysiology simulations.
Answers are grounded in this paper and cite their sources.
May aid in silico reentry screening; hypothesis-generating and should not yet change post-MI risk stratification.
Sudden cardiac death mostly originates from post-infarct ventricular tachycardia. This reentry is sustained by propagation around scar tissue, but its risk remains difficult to predict from infarct imaging alone. While in silico induction studies can reveal these mechanisms, exploring many substrates and pacing locations remains computationally expensive. We propose a graph attention classifier for early prediction of sustained ventricular reentry from simulated cardiac electrophysiology. Each simulation is represented as a graph with early nodal voltage samples and edge attributes encoding geometry, stimulation frequency, tissue labels, amplitude, and diastolic interval. These descriptors are computed only from the first two paced activations, before sustained reentry is observed. On a balanced independent test set of 1000 simulations, the classifier achieves 94.6% accuracy, 95.4% sensitivity, 93.8% specificity, 94.6% F1-score, 0.987 ROC-AUC, and 0.985 PR-AUC. Ablation experiments show that diastolic interval is the most critical descriptor. Qualitative attention inspection suggests that different heads focus on border-zone, stimulation location, and early propagation path. These results support graph attention as a fast early-prediction approach for large-scale in silico ventricular reentry studies.
No takes yet. Share an insight, caveat, or question.
Morier et al. (2026) studied Post-infarct ventricular tachycardia (sustained ventricular reentry) (n=8,004). Physiology-aware residual Graph Attention Network (GATv2) classifier vs. Full Mitchell-Schaeffer electrophysiology simulation and baseline machine learning models (Sequential GAT, GCN, SVM-RBF, NodeMLP) was evaluated on Early prediction of sustained ventricular reentry on a balanced independent test set (n=1,000 simulations) (Accuracy 94.6%, Sensitivity 95.4%, Specificity 93.8%, F1-score 94.6%, ROC-AUC 0.987, PR-AUC 0.985). The physiology-aware graph attention classifier predicted sustained ventricular reentry with 94.6% accuracy, 95.4% sensitivity, 93.8% specificity, and 0.987 ROC-AUC on an independent test set.
Synapse has enriched 10 related papers. Consider them for comparative context: