EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Modality-Specific Sparse Autoencoders for Efficient Multimodal ICU Alignment: A Symmetry–Asymmetry Learning Framework

Hashim Ali, Muhammad Tahir Akhtar

Symmetry · 18.04.2026 · 18 (4) · 677

DOI: 10.3390/sym18040677 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Symmetry, online erschienen am 18.04.2026. Verfasst von Hashim Ali und 1 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 47 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Intensive care units (ICUs) generate heterogeneous data streams, including structured electronic health records, physiological time series, and medical imaging, that describe the same patient state through different observational forms. Effective multimodal learning in this setting requires a principled balance between representation-level symmetry and architectural asymmetry. Clinically corresponding patient states should exhibit cross-modal representational symmetry, whereas each modality retains intrinsic asymmetry in dimensionality, temporal resolution, noise characteristics, and missingness. This study proposes a modality-specific sparse autoencoder framework for efficient multimodal ICU representation learning under this symmetry–asymmetry principle. Separate sparse encoders are assigned to each modality to preserve the modality-dependent structure while suppressing redundant latent activity through adaptive gating. Representation-level symmetry is encouraged through a sparsity-aware contrastive objective that aligns paired latent embeddings across modalities only on active informative dimensions. To further model inter-patient dependencies, the framework incorporates a graph neural network (GNN) whose message-passing operations respect modality-specific sparsity patterns. Experimental results indicate that the proposed framework improves predictive performance and computational efficiency relative to conventional multimodal baselines, while also exhibiting stronger robustness under missing-modality conditions and more selective latent representations. Overall, the method provides an effective and clinically relevant multimodal learning strategy for ICU decision support while offering a measurable symmetry-aware and asymmetry-preserving formulation for heterogeneous medical data.

Zitieren

APA

Ali, H., & Akhtar, M. T. (2026). Modality-Specific Sparse Autoencoders for Efficient Multimodal ICU Alignment: A Symmetry–Asymmetry Learning Framework. Symmetry, 18(4), 677. https://doi.org/10.3390/sym18040677

Vancouver

Ali H, Akhtar MT. Modality-Specific Sparse Autoencoders for Efficient Multimodal ICU Alignment: A Symmetry–Asymmetry Learning Framework. Symmetry. 2026;18(4):677. doi:10.3390/sym18040677

BibTeX
@article{Ali2026,
  author = {Ali, Hashim and Akhtar, Muhammad Tahir},
  title = {Modality-Specific Sparse Autoencoders for Efficient Multimodal ICU Alignment: A Symmetry–Asymmetry Learning Framework},
  journal = {Symmetry},
  year = {2026},
  volume = {18},
  number = {4},
  pages = {677},
  doi = {10.3390/sym18040677}
}
Kostenlos starten →