Scholarlink

Background <p>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.</p> Main body <p>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.</p> Conclusions <p>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.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Artificial intelligence integrated multi-omics and multimodal studies promote the efficacy of neoadjuvant chemotherapy in breast cancer: opportunities, challenges, and future perspectives

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年5月18日

查看全文
  • Sijing Ye,
  • Zimeng Jin,
  • Wenjing Li,
  • Guikang Wei,
  • Shiying Jiang,
  • Qinchuan Wang

摘要

Background

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.

Main body

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.

Conclusions

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.