Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2509.21600 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909806868037632 |
|---|---|
| author | Malafaia, Mafalda Bosman, Peter A. N. Rasch, Coen Alderliesten, Tanja |
| author_facet | Malafaia, Mafalda Bosman, Peter A. N. Rasch, Coen Alderliesten, Tanja |
| contents | Accurate and interpretable survival analysis remains a core challenge in oncology. With growing multimodal data and the clinical need for transparent models to support validation and trust, this challenge increases in complexity. We propose an interpretable multimodal AI framework to automate survival analysis by integrating clinical variables and computed tomography imaging. Our MultiFIX-based framework uses deep learning to infer survival-relevant features that are further explained: imaging features are interpreted via Grad-CAM, while clinical variables are modeled as symbolic expressions through genetic programming. Risk estimation employs a transparent Cox regression, enabling stratification into groups with distinct survival outcomes. Using the open-source RADCURE dataset for head and neck cancer, MultiFIX achieves a C-index of 0.838 (prediction) and 0.826 (stratification), outperforming the clinical and academic baseline approaches and aligning with known prognostic markers. These results highlight the promise of interpretable multimodal AI for precision oncology with MultiFIX. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_21600 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Automated and Interpretable Survival Analysis from Multimodal Data Malafaia, Mafalda Bosman, Peter A. N. Rasch, Coen Alderliesten, Tanja Artificial Intelligence Machine Learning Accurate and interpretable survival analysis remains a core challenge in oncology. With growing multimodal data and the clinical need for transparent models to support validation and trust, this challenge increases in complexity. We propose an interpretable multimodal AI framework to automate survival analysis by integrating clinical variables and computed tomography imaging. Our MultiFIX-based framework uses deep learning to infer survival-relevant features that are further explained: imaging features are interpreted via Grad-CAM, while clinical variables are modeled as symbolic expressions through genetic programming. Risk estimation employs a transparent Cox regression, enabling stratification into groups with distinct survival outcomes. Using the open-source RADCURE dataset for head and neck cancer, MultiFIX achieves a C-index of 0.838 (prediction) and 0.826 (stratification), outperforming the clinical and academic baseline approaches and aligning with known prognostic markers. These results highlight the promise of interpretable multimodal AI for precision oncology with MultiFIX. |
| title | Automated and Interpretable Survival Analysis from Multimodal Data |
| topic | Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2509.21600 |