Artificial Intelligence-Driven Biomarkers Development and Precision Strategies in Cancer Immunotherapy

Cancer immunotherapy has significantly changed the clinical management of multiple malignancies, yet substantial challenges remain in identifying which patients will benefit most, predicting treatment response, monitoring toxicity, and optimizing individualized therapeutic strategies. In clinical oncology, there is an urgent need for robust and interpretable artificial intelligence models that can integrate routinely available data, including clinical characteristics, imaging, pathology, blood-based biomarkers, and treatment outcomes. Such approaches may improve patient stratification, prognosis assessment, response prediction, and real-world decision-making in cancer immunotherapy. This Research Topic aims to highlight clinically relevant studies on artificial intelligence-driven biomarkers and precision strategies in cancer immunotherapy, with a particular focus on retrospective and prospective clinical cohorts, real-world data, model development and validation, and translational studies with direct clinical applicability. By emphasizing clinically oriented research, this collection seeks to promote the integration of AI tools into precision immuno-oncology and improve patient care. We try to provide a focused platform for clinically relevant research on artificial intelligence-driven precision strategies in cancer immunotherapy. It seeks to highlight how AI-based methods can improve patient stratification, treatment selection, response prediction, prognosis assessment, and toxicity monitoring across different cancer types. Particular emphasis will be placed on studies with direct clinical applicability, including retrospective and prospective clinical cohorts, real-world data analyses, biomarker-based prediction models, radiomics, digital pathology, and multi-modal data integration. The topic also welcomes translational studies that bridge computational innovation and oncology practice. By bringing together high-quality clinical and clinically oriented research, this topic aims to advance the development of robust, interpretable, and practical AI tools that support precision immunotherapy and improve outcomes for patients with cancer.This research Topic welcomes original research articles, reviews, and short communications addressing artificial intelligence-driven precision strategies in cancer immunotherapy, with a particular focus on clinically relevant studies. Topics of interest include, but are not limited to, AI-based prediction of immunotherapy response, prognosis assessment, patient stratification, toxicity evaluation, biomarker discovery, radiomics, digital pathology, and multi-modal data integration. Studies involving retrospective or prospective clinical cohorts, real-world data, and translational research with clear clinical implications are especially encouraged. Manuscripts should demonstrate methodological rigor, clinical relevance, and clear translational value. Purely technical studies without adequate oncological or clinical context may be considered less suitable. Authors are encouraged to submit work that advances interpretable, robust, and practical AI applications capable of supporting precision decision-making in cancer immunotherapy.Please note: Manuscripts consisting solely of bioinformatics, computational analysis, or predictions of public databases which are not accompanied by validation (independent clinical or patient cohort, or biological validation in vitro or in vivo, which are not based on public databases) are not suitable for publication in this journal. Topic editors: Han Yunwei, Ke Su, Xueting Li, Zhenfang Du Source: https://www.frontiersin.org/research-topics/79975/artificial-intelligence-driven-biomarkers-development-and-precision-strategies-in-cancer-immunotherapy