Redefining the future of cancer care: Intelligent Oncology unveiled

Despite significant advances in oncology over the past few decades, the global burden of cancer continues to escalate 1 . The need for breakthroughs in the early diagnosis and precise treatment of this devastating disease is becoming increasingly urgent. Over the past decade, artificial intelligence (AI) has made strides in its applications to almost all fronts of the fight against cancer, including prevention, screening, diagnosis, treatment, and rehabilitation. The oncology–AI connection, driven by the vast amounts of data generated in clinical practice, requires the integration of advanced AI technologies to unlock its full potential. Meanwhile, the performance and explainability of algorithms have also been improved by learning from the multimodal data generated in the practice. This symbiotic relationship has given rise to a new discipline called intelligent oncology, a burgeoning field within the latest wave of AI advances 2 . We are launching this new journal, Intelligent Oncology , to provide a scholarly platform for showcasing the ongoing evolution of intelligent oncology, examining the current state of global research trends in the field, and exploring future directions for its continued advancement. The wealth of scenarios and data generated from clinical practice makes oncology an ideal field for the application of AI 3 . Oncology contains various medical scenarios. These scenarios are related to rich types of data which correlate with each other. AI plays a pivotal role by weaving these data together. This process allows the initially independent data and scenarios to become interconnected by AI, thereby moving toward the creation of a comprehensive, intelligent oncology diagnostic and treatment system. In essence, intelligent oncology is an interdisciplinary science that connects and integrates the fragmented scenes of AI applications to support the holistic diagnosis and treatment of tumors. AI can process large amounts of medical image data and extract key information from it by building deep learning models 4 , reducing the time required for doctors to analyze and diagnose. A new generation of digital pathology diagnostics, combined with AI, can significantly improve diagnostic accuracy by analyzing the microscopic information from pathological sections 5 . Generative AI can provide predictive algorithms that enhance the performance of clinical decision-support tools 6 . Large language models (LLMs) in clinical documentation can reduce the burden on physicians and allied health professionals by streamlining daily hospital workflows and introducing a paradigm for improved communication that benefits patients and healthcare providers 7 . On the drug discovery front, generative AIs can also explore extensive chemical spaces to help discover potential lead compounds, as well as complete preclinical testing and drug optimization more efficiently, thereby accelerating the drug development process 8 . Furthermore, AI can assist doctors in selecting the most appropriate therapeutic schedule to improve patient outcomes through the analysis of large amounts of genomic data 9 . Remarkably, through multi-modal data parsing, dynamic task learning, and medical knowledge application, generalist medical AI (GMAI) is able to flexibly handle a wide range of medical tasks such as what was mentioned above 10 .