arXiv cs.AI· Hakima Laribi, Olivier Lefebvre, Dan Poenaru, Martin Valli\`eres·· 12 小时前AI 评分27
DIGOM：面向多模态医疗结果预测的解耦交互图框架
DIGOM: Disentangled Interaction Graphs for Outcome prediction in Multimodal healthcare
AI 导读
DIGOM 是一个基于图的框架，同时建模患者内跨模态、跨患者同模态与跨患者跨模态三类交互，通过可微机制采样患者自适应稀疏邻接矩阵实现端到端学习。在 MIMIC-IV 和 NIH-TB 两个数据集、五项临床预测任务上，DIGOM 全部取得最高 AUROC，且所用连接数少于现有多交互方法。消融实验显示各交互类型贡献随任务变化，模型对模态缺失也表现出更强鲁棒性。
正文 · 原文
Abstract:Multimodal healthcare data contain relational information that extends beyond individual patient observations. Effective clinical outcome prediction therefore requires not only integrating information from multiple modalities, but also modeling the relationships between them. Standard fusion approaches do not explicitly capture these interactions, while existing graph-based approaches typically model only a subset of them. We propose DIGOM (Disentangled Interaction Graphs for Outcome prediction in Multimodal healthcare), a graph-based framework that jointly models three complementary interaction types: Intra-patient cross-modal, Cross-patient same-modal, and Cross-patient cross-modal interactions. DIGOM learns a sparse multiplex graph with disentangled views, each encoding interactions between pairs of modalities across patients. Discrete adjacency matrices with patient-adaptive connectivity are sampled via a differentiable mechanism, enabling end-to-end learning and allowing the model to select informative relationships without imposing a fixed number of neighbors. A regularization objective maintains overall graph sparsity, while message passing integrates this relational context into patient representations for outcome prediction. We evaluate DIGOM on two multimodal healthcare datasets, MIMIC-IV and NIH-TB, across five clinical prediction tasks. DIGOM achieves the highest AUROC on all five tasks while using fewer connections than existing multi-interaction approaches. Ablation studies reveal that each interaction type's contribution varies across tasks, highlighting the need to adapt relational structures per task. DIGOM also demonstrates greater robustness to missing modalities, suggesting learned relationships provide complementary information when modalities are unavailable. Post-hoc analyses further reveal task- and outcome-specific connectivity patterns in the learned graphs.
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.32451 [cs.LG] |
| (or arXiv:2610.32451v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.32451 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Hakima Laribi [view email]
[v1]
Fri, 23 Oct 2026 10:17:32 UTC (628 KB)
来源：arXiv cs.AI · arxiv.org