Spatiotemporal

Learning to Map Global Atrial Fibrillation Dynamics from Sparse Measurements

FibMap reconstructs global atrial fibrillation dynamics from sparse clinical measurements using a spatiotemporal graph neural network, enabling personalised cardiac mapping for catheter ablation guidance.

Relational Conformal Prediction for Correlated Time Series

We introduce CoRel, a novel distribution-free conformal prediction method that leverages graph neural networks to quantify uncertainty in correlated time series forecasting by exploiting relational dependencies across sequences.