MADE: leveraging informative missingness and temporal evaluation for electronic health record-based deterioration prediction in general wards

Yechan Mun, Jee Hwan Ahn, Chang Youl Lee, Byungeun Ahn, Jin Won Huh, Kyung Soo Chung 

Electronic health record (EHR) time series are irregularly sampled and frequently incomplete, with missingness potentially carrying clinically informative signals. We developed Masked-Attention-based timestamp-wise Data Embedding (MADE), a missingness-aware model for continuous prediction of deterioration in general wards, and evaluated it across heterogeneous hospitals.