<ul><li>DynaGraph is an interpretable contrastive graph model that learns the dynamics of multivariate time-series electronic health records (EHRs) as part of optimization.</li><li>DynaGraph captures the hidden dependencies of the multivariate time-series using dynamic graph construction.</li><li>Compared to state-of-the-art models, DynaGraph achieves significant improvements in accuracy and sensitivity in various clinical datasets.</li><li>DynaGraph provides clinical validation by indicating the importance of clinical covariates over time.</li></ul>

DynaGraph: Interpretable Multi-Label Prediction from EHRs via Dynamic Graph Learning and Contrastive Augmentation

Discover more