Robust Multimodal Representation Learning in Healthcare

TL;DR

This paper introduces a causal-aware dual-stream neural network framework for medical multimodal representation learning that effectively disentangles causal features from biases, improving clinical outcome predictions across multiple datasets.

Contribution

It proposes a novel dual-stream decorrelation method based on structural causal analysis to handle biases in multimodal medical data, enhancing generalization.

Findings

Consistent performance improvements on MIMIC-IV, eICU, and ADNI datasets.

Effective disentanglement of causal features from spurious correlations.

Model-agnostic framework adaptable to existing methods.

Abstract

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.