1

On the Importance of Step-wise Embeddings for Heterogeneous Clinical Time-Series

Recent advances in deep learning architectures for sequence modeling have not fully transferred to tasks handling time-series from electronic health records. In particular, in problems related to the Intensive Care Unit (ICU), the state-of-the-art …

Temporal Label Smoothing for Early Event Prediction

Models that can predict the occurrence of events ahead of time with low false-alarm rates are critical to the acceptance of decision support systems in the medical community. This challenging task is typically treated as a simple binary …

Clinical Trajectory Representations for Clustering

Analyzing and grouping typical patient trajectories is crucial to understanding their health state, estimating prognosis, and determining optimal treatment. The increasing availability of electronic health records (EHRs) opens the opportunity to …

POETREE: Interpretable Policy Learning with Adaptive Decision Trees

Building models of human decision-making from observed behaviour is critical to better understand, diagnose and support real-world policies such as clinical care. As established policy learning approaches remain focused on imitation performance, they …