Neoadjuvant chemotherapy (NAC) is a critical therapeutic strategy for locally advanced breast cancer; however, its clinical utility is constrained by tumor heterogeneity and a lack of reliable predictive biomarkers. Integrating single-omics, multimodal, and multi-omics technologies provides comprehensive insights into the tumor biology, while artificial intelligence (AI) facilitates the efficient integration and interpretation of these high-dimensional data. Based on a comprehensive literature search, we review and synthesize existing literature on the progress of AI-driven data integration in the NAC of breast cancer. We highlight the significant role of AI in predicting treatment response, discovering biomarkers, and profiling tumor heterogeneity and immune microenvironment. We also discussed the major challenges, including data quality, model interpretability, ethical concerns, and clinical translation in AI-empowered multi-omics studies. Moreover, recent advances in spatial multi-omics and large language models to decode intratumoral heterogeneity and to support clinical decision were also discussed. However, despite these significant progressions, translation of these innovations into practice still requires data-sharing architectures and interdisciplinary collaboration. AI empowered data integration holds profound potential to decode the complex molecular landscape of breast cancer, which will ultimately promote precise personalized NAC strategies and prognosis of patients.
Ye et al. (Mon,) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: