The convergence of artificial intelligence (AI) and big data is reshaping contemporary oncology by enabling the integration of multimodal information across imaging, pathology, genomics, and clinical records. From a physician-centered perspective, these technologies can potentially be used to improve diagnostic precision, support individualized treatment planning, enhance longitudinal patient management, and accelerate both clinical and translational research. In this review, we synthesize the core AI methodologies most relevant to oncology-machine learning, deep learning, and large language models-and examine how they interact with established and emerging oncology data platforms. We further highlight practical use cases in clinical workflows and research pipelines, emphasizing opportunities for advancing precision cancer care while also addressing challenges associated with data heterogeneity, model generalizability, privacy protection, and real-world implementation. By underscoring the synergistic value of AI and big data, this review aims to inform the development of clinically meaningful, context-adapted strategies that promote translational innovation in both global and locally resourced healthcare environments.
{"title":"AI and Big Data in Oncology: A Physician-Centered Perspective on Emerging Clinical and Research Applications.","authors":"Binliang Liu, Qingyao Shang, Jun Li, Shuna Yao, Meishuo Ouyang, Yu Wang, Sheng Luo, Quchang Ouyang","doi":"10.1002/cai2.70047","DOIUrl":"10.1002/cai2.70047","url":null,"abstract":"<p><p>The convergence of artificial intelligence (AI) and big data is reshaping contemporary oncology by enabling the integration of multimodal information across imaging, pathology, genomics, and clinical records. From a physician-centered perspective, these technologies can potentially be used to improve diagnostic precision, support individualized treatment planning, enhance longitudinal patient management, and accelerate both clinical and translational research. In this review, we synthesize the core AI methodologies most relevant to oncology-machine learning, deep learning, and large language models-and examine how they interact with established and emerging oncology data platforms. We further highlight practical use cases in clinical workflows and research pipelines, emphasizing opportunities for advancing precision cancer care while also addressing challenges associated with data heterogeneity, model generalizability, privacy protection, and real-world implementation. By underscoring the synergistic value of AI and big data, this review aims to inform the development of clinically meaningful, context-adapted strategies that promote translational innovation in both global and locally resourced healthcare environments.</p>","PeriodicalId":100212,"journal":{"name":"Cancer Innovation","volume":"5 1","pages":"e70047"},"PeriodicalIF":2.0,"publicationDate":"2026-01-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12855167/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146109491","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}