aiqbench analysis
This research introduces the EMMS model, which enhances multimodal survival prediction by robustly handling missing data modalities common in clinical environments. By leveraging Dempster-Shafer theory and treating absent inputs as vacuous evidence, the approach effectively manages uncertainty without requiring computationally expensive generative imputation phases. The method achieves state-of-the-art performance on cancer datasets while providing calibrated predictions that reflect increased uncertainty under incomplete observations.
Evidential Fusion Network for Multimodal Survival Prediction under Missing Modalities
arXiv:2606.20757v2 Announce Type: replace Abstract: Recent multimodal survival prediction models have demonstrated strong predictive performance by leveraging complementary information across modalities. However, such models generally assume data completeness and exhibit limited robustness toward missing modalities, which are frequently encountered in real-world clinical settings. We propose the Evidential Missing Modality Survival Fusion (EMMS) model for multimodal survival prediction under missing modalities. EMMS offers a straightforward, computationally effective approach to survival analysis without requiring a generative phase for missing data. By employing Dempster-Shafer theory and Gaussian Random Fuzzy Numbers for multimodal decision fusion, it considers both aleatoric and epistemic uncertainty alongside modality reliability for fusion. Moreover, the model treats missing modalities as vacuous evidence, preventing interference with available inputs and naturally reflecting increased uncertainty and calibrated predictions. Extensive experiments on four cancer datasets demonstrate state-of-the-art performance while providing calibrated and interpretable uncertainty estimates under incomplete multimodal observations, without introducing additional computational overhead.
Abstract:Recent multimodal survival prediction models have demonstrated strong predictive performance by leveraging complementary information across modalities. However, such models generally assume data completeness and exhibit limited robustness toward missing modalities, which are frequently encountered in real-world clinical settings. We propose the Evidential Missing Modality Survival Fusion (EMMS) model for multimodal survival prediction under missing modalities. EMMS offers a straightforward, computationally effective approach to survival analysis without requiring a generative phase for missing data. By employing Dempster-Shafer theory and Gaussian Random Fuzzy Numbers for multimodal decision fusion, it considers both aleatoric and epistemic uncertainty alongside modality reliability for fusion. Moreover, the model treats missing modalities as vacuous evidence, preventing interference with available inputs and naturally reflecting increased uncertainty and calibrated predictions. Extensive experiments on four cancer datasets demonstrate state-of-the-art performance while providing calibrated and interpretable uncertainty estimates under incomplete multimodal observations, without introducing additional computational overhead.
Machine Learning (cs.LG)
arXiv:2606.20757 [cs.LG]
(or arXiv:2606.20757v2 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2606.20757 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 237 words
Related coverage
Multimodality Stacking with Blockwise missing values and application to the PIONeeR biomarkers study for prediction of resistance to immunotherapy
arXiv · Jul 24, 2026
Design Choices for Multimodal Transformer Learning with Missing and Longitudinal Healthcare Data
arXiv · Oct 14, 2026
Latent World Recovery for Multimodal Learning with Missing Modalities
arXiv · Jun 12, 2026
An Attention-based Model for Robust Forecasting with Missing Modality
arXiv · Jun 16, 2026