A Representation Fusion Framework for Decoupling Diagnostic Information in Multimodal Learning.

ABSTRACT: Modern medicine increasingly relies on multimodal data, ranging from clinical notes to imaging and genomics, to guide diagnosis and treatment. However, integrating these heterogeneous data sources in a principled and interpretable manner remains a major challenge. We present MODES (Multi-mOdal Disentangled Embedding Space), a representation fusion framework that explicitly separates shared and modality-specific factors of variation, offering a structured latent space for multimodal information that improves both prediction and interpretability. By leveraging pre-trained unimodal foundation models, MODES mitigates the dependency on extensive paired datasets, crucial in data-scarce clinical settings. We introduce a masking strategy that optimizes representation dimensionality by eliminating

SUBMITTER: Tonekaboni S 

PROVIDER: S-EPMC12712021 | biostudies-literature | 2025 Dec

REPOSITORIES: biostudies-literature