Continually Evolved Multimodal Foundation Models for Cancer Prognosis
This work addresses cancer prognosis for patients by enabling robust and adaptive multimodal integration, though it appears incremental in method.
The paper tackled the problem of improving cancer prognosis by integrating diverse data modalities, addressing limitations in handling new data and capturing complex interdependencies, and demonstrated effectiveness on the TCGA dataset.
Cancer prognosis is a critical task that involves predicting patient outcomes and survival rates. To enhance prediction accuracy, previous studies have integrated diverse data modalities, such as clinical notes, medical images, and genomic data, leveraging their complementary information. However, existing approaches face two major limitations. First, they struggle to incorporate newly arrived data with varying distributions into training, such as patient records from different hospitals, thus rendering sub-optimal generalizability and limited utility in real-world applications. Second, most multimodal integration methods rely on simplistic concatenation or task-specific pipelines, which fail to capture the complex interdependencies across modalities. To address these, we propose a continually evolving multi-modal foundation model. Extensive experiments on the TCGA dataset demonstrate the effectiveness of our approach, highlighting its potential to advance cancer prognosis by enabling robust and adaptive multimodal integration.