Intelligent Cancer Decision Support Systems: The Convergence of Foundation Models and Precision Medicine

Abstract

Cancer remains one of the leading causes of morbidity and mortality worldwide despite remarkable advances in molecular diagnostics, targeted therapeutics, immunotherapy, and precision medicine. The growing complexity of oncology, driven by rapidly expanding volumes of radiological imaging, digital pathology, genomic sequencing, transcriptomics, proteomics, metabolomics, laboratory investigations, electronic health records, wearable technologies, and longitudinal clinical information, has created increasing demand for intelligent clinical decisionsupport systems capable of synthesizing heterogeneous biomedical data into actionable knowledge. Foundation artificial intelligence (AI) models have emerged as a transformative computational paradigm by learning generalized biomedical representations from large-scale multimodal datasets through self-supervised learning. Unlike conventional task-specific AI systems, foundation models integrate imaging, pathology, multi-omics, clinical documentation, laboratory medicine, and real-world healthcare data into unified patient-centered computational frameworks capable of supporting diagnosis, prognostic prediction, molecular characterization, therapeutic optimization, toxicity assessment, digital twins, clinical trial matching, and personalized medicine. Advances in transformer architectures, multimodal learning, graph neural networks, retrieval-augmented generation, large language models, agentic AI, and generative artificial intelligence have significantly accelerated development of intelligent cancer decision-support systems. Despite remarkable technological progress, important challenges remain regarding explainability, interoperability, computational scalability, cybersecurity, regulatory validation, ethical governance, and equitable implementation. This review provides a comprehensive overview of intelligent cancer decision-support systems, highlighting the convergence of foundation AI models and precision medicine while discussing current clinical applications, implementation challenges, and future directions for computational oncology.[1]