NOAH: Learning the Full Patient Journey. A Longitudinal Multimodal Time-Aware Model for Representation and Forecasting

Researchers introduced NOAH, a longitudinal multimodal time-aware model designed to learn the full patient journey by representing and forecasting patient state trajectories from digitized healthcare records. The model addresses the challenge of capturing complex, irregular temporal patterns in lifelong patient data.

The digitization of healthcare has generated vast, longitudinal, and multimodal patient records over a lifetime, yet fully exploiting these data to represent and predict patient state trajectories remains a critical challenge. Current AI models often struggle to capture the complex, irregular tempor