CAGCL: Predicting Short- and Long-Term Breast Cancer Survival with Cross-Modal Attention and Graph Contrastive Learning

In breast cancer treatment, accurately predicting how long a patient will survive is crucial for decision-making. This information guides treatment choices and supports patients' psychological recovery. To address this challenge, we introduce a novel predictive model to forecast breast cancer prognosis by leveraging diverse data sources, including clinical records, copy number variation, gene expressions, DNA methylation, microRNA sequencing, and whole slide image data from the TCGA Database. The methodology incorporates graph contrastive learning with cross-modality attention (CAGCL), considering all possible combinations of the six distinct data modalities. Feature embeddings are enhanced through graph contrastive learning, which identifies subtle differences and similarities among samples. Further, to learn the complementary nature of information across multiple data modalities, a cross-attention framework is proposed and applied to the graph contrastive learning-based extracted features from various data sources for breast cancer survival prediction. It performs a binary classification to anticipate the likelihood of short- and long-term breast cancer survivors, delineated by a five-year threshold. The proposed model (CAGCL) showcases superior performance compared to baseline models and other state-of-the-art models. The model attains an accuracy of 0.932, a sensitivity of 0.954, a precision of 0.958, an F1 score of 0.956, and an AUC of 0.948, underscoring its effectiveness in predicting breast cancer survival.