TOWARDS AN INTELLIGENT CANCER LEARNING HEALTH SYSTEM: FOUNDATION AI MODELS FOR ADAPTIVE AND PERSONALIZED ONCOLOGY

Abstract

The emergence of intelligent cancer learning health systems represents a transformative paradigm in precision oncology, where artificial intelligence (AI), foundation models, multimodal learning, and continuously evolving clinical knowledge converge to create adaptive healthcare ecosystems capable of improving diagnosis, treatment, and survivorship through iterative learning. Conventional oncology frequently relies on fragmented clinical workflows, episodic data collection, and static predictive models that inadequately reflect the dynamic biological evolution of cancer or the continuous accumulation of real-world clinical evidence. Recent advances in foundation AI models, multimodal transformer architectures, graph neural networks, self-supervised learning, reinforcement learning, and generative artificial intelligence have enabled seamless integration of radiological imaging, digital pathology, genomics, transcriptomics, proteomics, metabolomics, epigenomics, spatial biology, laboratory biomarkers, circulating tumor DNA, wearable physiological monitoring, electronic health records, patient-reported outcomes, biomedical literature, and longitudinal clinical outcomes into unified computational ecosystems. These intelligent systems support early cancer detection, molecular characterization, biomarker discovery, prognostic prediction, therapeutic optimization, immunotherapy selection, digital twin simulation, adaptive disease monitoring, and evidence-based clinical decision support. Emerging technologies including multimodal large language models, federated learning, retrieval-augmented generation, explainable artificial intelligence, agentic AI, cloud-native healthcare platforms, and Internet of Medical Things (IoMT) technologies further strengthen learning health systems by enabling collaborative, privacy-preserving, transparent, and continuously adaptive biomedical intelligence. Despite substantial technological advances, important scientific, technical, ethical, and regulatory challenges remain regarding multimodal data harmonization, computational scalability, interoperability, explainability, cybersecurity, clinical validation, and equitable implementation. This review provides a comprehensive overview of intelligent cancer learning health systems, emphasizing foundation AI models as transformative technologies for adaptive and personalized oncology.