CoC: Chain-of-Cancer based on Cross-Modal Autoregressive Traction for Survival Prediction

TL;DR

This paper introduces the Chain-of-Cancer framework, integrating four modalities including clinical data and language, to improve survival prediction in cancer patients through a novel cross-modal autoregressive approach.

Contribution

It is the first to utilize textual descriptions alongside multiple clinical modalities for cancer survival prediction, employing a Chain-of-Thought inspired framework with an autoregressive mutual traction module.

Findings

Achieved state-of-the-art results on five public cancer datasets.

Validated the effectiveness of the proposed cross-modal and autoregressive methods.

Demonstrated improved joint learning among multiple modalities.

Abstract

Survival prediction aims to evaluate the risk level of cancer patients. Existing methods primarily rely on pathology and genomics data, either individually or in combination. From the perspective of cancer pathogenesis, epigenetic changes, such as methylation data, could also be crucial for this task. Furthermore, no previous endeavors have utilized textual descriptions to guide the prediction. To this end, we are the first to explore the use of four modalities, including three clinical modalities and language, for conducting survival prediction. In detail, we are motivated by the Chain-of-Thought (CoT) to propose the Chain-of-Cancer (CoC) framework, focusing on intra-learning and inter-learning. We encode the clinical data as the raw features, which remain domain-specific knowledge for intra-learning. In terms of inter-learning, we use language to prompt the raw features and introduce an Autoregressive Mutual Traction module for synergistic representation. This tailored framework facilitates joint learning among multiple modalities. Our approach is evaluated across five public cancer datasets, and extensive experiments validate the effectiveness of our methods and proposed designs, leading to producing \sota results. Codes will be released.