Cancer immunotherapy, which leverages the immune system to combat tumor cells, has made significant advancements in oncology treatment in recent years. Yet significant challenges remain in predicting treatment responses and understanding mechanisms of resistance. Artificial intelligence (AI) and machine learning (ML) provide powerful tools to address these challenges, enabling breakthroughs in patient stratification, biomarker discovery, and treatment strategy optimization. While remarkable progress has been made in developing deep learning frameworks, including large language models (LLMs) to integrate the exponentially growing multi-omics biomedical data for cancer immunotherapy, little effort has been made to systematically and comprehensively summarize these developments or critically evaluate their translational potential. To fill these gaps, this review comprehensively examines the current landscape and future directions of AI/ML applications in cancer immunotherapy. Specifically, we discuss four key areas in AI for cancer immunotherapy: (1) patient stratification, (2) biomarker discovery, (3) treatment strategy optimization, and (4) foundation models and LLMs for cancer immunotherapy. In addition, we also critically discuss current limitations and future directions for existing AI approaches for cancer immunotherapy, highlighting the actionable insights and roadmaps to accelerate the integration of AI/ML into precision cancer immunotherapy.
Wu et al. (Wed,) studied this question.