Graph attention predicts early heart arrhythmias after heart attack
Physiology-Aware Graph Attention for Early Ventricular Reentry Prediction
Artificial Intelligence
Summary
Sudden heart problems after a heart attack can be hard to predict from images alone. The authors used computer simulations of heart activity and represented them as graphs with details about the heart tissue and electrical signals. Their system looks at early signals to predict if a dangerous heart rhythm will happen later. It was very accurate at predicting this early on, which could save time in larger studies. They found some specific heart features were most important for the prediction.
What this means in practice
- •For cardiac simulation teams: Predict the risk of sustained ventricular arrhythmia early in simulations without running lengthy electrophysiology models to completion.
- •For machine learning engineers: Design graph attention models combining physiological and geometric heart data for early prediction of disease states in biomedical simulations.
Authors
Ma{ë}lis Morier, Jairo Rodr{í}guez Padilla, Patrick Gallinari, Maxime Sermesant
Abstract
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.