Robust Multimodal Representation Learning in Healthcare
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866910224220160000 |
|---|---|
| author | Zhu, Xiaoguang Gong, Linxiao Sun, Lianlong Liu, Yang Wang, Haoyu Liu, Jing |
| author_facet | Zhu, Xiaoguang Gong, Linxiao Sun, Lianlong Liu, Yang Wang, Haoyu Liu, Jing |
| contents | Medical multimodal representation learning aims to integrate heterogeneous data into unified patient representations to support clinical outcome prediction. However, real-world medical datasets commonly contain systematic biases from multiple sources, which poses significant challenges for medical multimodal representation learning. Existing approaches typically focus on effective multimodal fusion, neglecting inherent biased features that affect the generalization ability. To address these challenges, we propose a Dual-Stream Feature Decorrelation Framework that identifies and handles the biases through structural causal analysis introduced by latent confounders. Our method employs a causal-biased decorrelation framework with dual-stream neural networks to disentangle causal features from spurious correlations, utilizing generalized cross-entropy loss and mutual information minimization for effective decorrelation. The framework is model-agnostic and can be integrated into existing medical multimodal learning methods. Comprehensive experiments on MIMIC-IV, eICU, and ADNI datasets demonstrate consistent performance improvements. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_21941 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Robust Multimodal Representation Learning in Healthcare Zhu, Xiaoguang Gong, Linxiao Sun, Lianlong Liu, Yang Wang, Haoyu Liu, Jing Machine Learning Artificial Intelligence Medical multimodal representation learning aims to integrate heterogeneous data into unified patient representations to support clinical outcome prediction. However, real-world medical datasets commonly contain systematic biases from multiple sources, which poses significant challenges for medical multimodal representation learning. Existing approaches typically focus on effective multimodal fusion, neglecting inherent biased features that affect the generalization ability. To address these challenges, we propose a Dual-Stream Feature Decorrelation Framework that identifies and handles the biases through structural causal analysis introduced by latent confounders. Our method employs a causal-biased decorrelation framework with dual-stream neural networks to disentangle causal features from spurious correlations, utilizing generalized cross-entropy loss and mutual information minimization for effective decorrelation. The framework is model-agnostic and can be integrated into existing medical multimodal learning methods. Comprehensive experiments on MIMIC-IV, eICU, and ADNI datasets demonstrate consistent performance improvements. |
| title | Robust Multimodal Representation Learning in Healthcare |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2601.21941 |