Quantifying Cross-Modal Interactions in Multimodal Glioma Survival Prediction via InterSHAP: Evidence for Additive Signal Integration
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911591033733120 |
|---|---|
| author | Swift, Iain Ye, JingHua O'Reilly, Ruairi |
| author_facet | Swift, Iain Ye, JingHua O'Reilly, Ruairi |
| contents | Multimodal deep learning for cancer prognosis is commonly assumed to benefit from synergistic cross-modal interactions, yet this assumption has not been directly tested in survival prediction settings. This work adapts InterSHAP, a Shapley interaction index-based metric, from classification to Cox proportional hazards models and applies it to quantify cross-modal interactions in glioma survival prediction. Using TCGA-GBM and TCGA-LGG data (n=575), we evaluate four fusion architectures combining whole-slide image (WSI) and RNA-seq features. Our central finding is an inverse relationship between predictive performance and measured interaction: architectures achieving superior discrimination (C-index 0.64$\to$0.82) exhibit equivalent or lower cross-modal interaction (4.8\%$\to$3.0\%). Variance decomposition reveals stable additive contributions across all architectures (WSI${\approx}$40\%, RNA${\approx}$55\%, Interaction${\approx}$4\%), indicating that performance gains arise from complementary signal aggregation rather than learned synergy. These findings provide a practical model auditing tool for comparing fusion strategies, reframe the role of architectural complexity in multimodal fusion, and have implications for privacy-preserving federated deployment. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_29977 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Quantifying Cross-Modal Interactions in Multimodal Glioma Survival Prediction via InterSHAP: Evidence for Additive Signal Integration Swift, Iain Ye, JingHua O'Reilly, Ruairi Machine Learning Artificial Intelligence Quantitative Methods Multimodal deep learning for cancer prognosis is commonly assumed to benefit from synergistic cross-modal interactions, yet this assumption has not been directly tested in survival prediction settings. This work adapts InterSHAP, a Shapley interaction index-based metric, from classification to Cox proportional hazards models and applies it to quantify cross-modal interactions in glioma survival prediction. Using TCGA-GBM and TCGA-LGG data (n=575), we evaluate four fusion architectures combining whole-slide image (WSI) and RNA-seq features. Our central finding is an inverse relationship between predictive performance and measured interaction: architectures achieving superior discrimination (C-index 0.64$\to$0.82) exhibit equivalent or lower cross-modal interaction (4.8\%$\to$3.0\%). Variance decomposition reveals stable additive contributions across all architectures (WSI${\approx}$40\%, RNA${\approx}$55\%, Interaction${\approx}$4\%), indicating that performance gains arise from complementary signal aggregation rather than learned synergy. These findings provide a practical model auditing tool for comparing fusion strategies, reframe the role of architectural complexity in multimodal fusion, and have implications for privacy-preserving federated deployment. |
| title | Quantifying Cross-Modal Interactions in Multimodal Glioma Survival Prediction via InterSHAP: Evidence for Additive Signal Integration |
| topic | Machine Learning Artificial Intelligence Quantitative Methods |
| url | https://arxiv.org/abs/2603.29977 |