AI-enhanced synergistic chemo-immunotherapy: From mechanistic insights to clinical translation

The integration of chemotherapy with immune checkpoint inhibitors (ICIs) represents a transformative strategy in oncology, synergistically enhancing anti-tumor efficacy by combining cytotoxic effects with immune reactivation. However, the full potential of this combination is often limited by therapeutic resistance, immune-related adverse events, and a lack of predictive biomarkers. This review comprehensively examines the mechanistic basis, clinical applications, and current challenges of chemo-immunotherapy, with a particular emphasis on the emerging role of artificial intelligence (AI) in optimizing such combinations. We discuss how chemotherapy-induced immunogenic cell death (ICD), antigen release, and remodeling of the tumor microenvironment (TME) potentiate ICI efficacy. Furthermore, we explore how AI-driven approaches, including multi-omics integration, radiomics, and deep learning facilitate the identification of synergistic drug pairs, prediction of treatment responses, and stratification of patients. Despite promising clinical outcomes across various malignancies, key challenges such as chemotherapy-induced immunosuppression, tumor heterogeneity, and data interpretability remain. Ultimately, the convergence of AI with immuno-oncology holds great promise for advancing personalized cancer therapy through improved biomarker discovery, rational combination design, and dynamic treatment adaptation.