MedFuse: Multiplicative Embedding Fusion For Irregular Clinical Time Series
This addresses the challenge of handling irregular, asynchronous, and heterogeneous clinical data for healthcare prediction tasks, though it appears incremental as it builds on existing embedding strategies with a novel fusion method.
The authors tackled the problem of modeling irregular clinical time series from EHRs by proposing MedFuse, a framework that uses multiplicative embedding fusion to capture value-dependent feature interactions, and it consistently outperformed state-of-the-art baselines on predictive tasks across three real-world datasets.
Clinical time series derived from electronic health records (EHRs) are inherently irregular, with asynchronous sampling, missing values, and heterogeneous feature dynamics. While numerical laboratory measurements are highly informative, existing embedding strategies usually combine feature identity and value embeddings through additive operations, which constrains their ability to capture value-dependent feature interactions. We propose MedFuse, a framework for irregular clinical time series centered on the MuFuse (Multiplicative Embedding Fusion) module. MuFuse fuses value and feature embeddings through multiplicative modulation, preserving feature-specific information while modeling higher-order dependencies across features. Experiments on three real-world datasets covering both intensive and chronic care show that MedFuse consistently outperforms state-of-the-art baselines on key predictive tasks. Analysis of the learned representations further demonstrates that multiplicative fusion enhances expressiveness and supports cross-dataset pretraining. These results establish MedFuse as a generalizable approach for modeling irregular clinical time series.