Artificial intelligence in multidisciplinary tumor boards enhancing decision making and clinical outcomes in oncology
Xiaodong Wang, Qianqian Wang, Gouping Ding, Junjie Wang, Yixuan Tang, Yeqian Feng
Abstract
Multidisciplinary tumor boards (MDTs) coordinate complex oncology decisions across imaging, pathology, genomics, and patient factors. Here we synthesize how artificial intelligence (AI)-including machine learning, natural language processing, deep learning, and large language models-supports MDT preparation and deliberation. Across cancers, reported agreement between AI recommendations and MDT decisions commonly ranges from 70% to 90%, and task-focused tools achieve high diagnostic performance in screening and staging. Benefits include faster information synthesis, more consistent guideline alignment, and clearer documentation of options, while human review remains central. Key limitations-data bias, uneven generalizability, privacy and governance concerns, and limited prospective validation-temper adoption. We outline implementation priorities: prospective multicenter evaluation, integration with electronic records, clinician training, and transparent oversight. Overall, AI can augment MDT decision-making and help personalize care and workflow efficiency when deployed with rigorous evaluation and safeguards.