Artificial intelligence in radiobiology: Bridging mechanisms and data analysis

This is the authors' abstract. We don't add key points for this paper.

The rapid development of artificial intelligence (AI) technology is profoundly transforming research paradigms in radiobiology. By integrating multimodal data, AI models have significantly enhanced both the efficiency and accuracy of elucidating complex radiobiological mechanisms and biomarker discovery. This review provides an in-depth examination of the critical roles of artificial intelligence in mechanism-based radiosensitivity prediction, biomarker discovery, and multi-dimensional data integration. It emphasizes the importance of interdisciplinary collaboration in bridging fundamental research and clinical practice, thereby broadening the scope of discussion. Advances in ethical regulatory frameworks and the accumulation of clinical validation evidence are jointly driving AI to become a key driver in radiobiology research. The review highlights how AI, by establishing a dynamic closed-loop connecting data, models, and mechanisms, enhances the precision, efficiency, and personalization of radiobiology research.