ABSTRACT
Longitudinal cancer monitoring has become an essential component of precision oncology because cancer is a dynamic disease characterized by continuous molecular evolution, treatment adaptation, immune modulation, and changing clinical trajectories. Conventional oncology frequently relies on intermittent assessments that provide isolated snapshots of disease status, limiting the ability to detect early progression, therapeutic resistance, recurrence, and treatment-related toxicity. Recent advances in artificial intelligence (AI), particularly foundation models, multimodal transformers, graph neural networks, self-supervised learning, and generative AI, have enabled the development of intelligent longitudinal monitoring systems capable of integrating radiological imaging, digital pathology, genomics, transcriptomics, proteomics, metabolomics, epigenomics, spatial biology, liquid biopsy, laboratory biomarkers, wearable physiological monitoring, electronic health records, patient-reported outcomes, and real-world clinical data into continuously evolving computational frameworks. These intelligent ecosystems support early detection of disease progression, predictive therapeutic optimization, digital twin simulation, biomarker discovery, survivorship management, and adaptive clinical decision support. Emerging technologies including multimodal large language models, federated learning, reinforcement learning, retrieval-augmented generation, explainable artificial intelligence, and agentic AI further strengthen longitudinal cancer monitoring by enabling collaborative, privacy-preserving, and continuously adaptive precision oncology. Despite remarkable technological progress, important scientific, technical, ethical, and regulatory challenges remain regarding multimodal data harmonization, computational scalability, interpretability, interoperability, cybersecurity, clinical validation, and equitable implementation. This review provides a comprehensive overview of artificial intelligence for longitudinal cancer monitoring, emphasizing multimodal learning across the entire patient journey as a cornerstone of future precision oncology.[1]
Keywords: Longitudinal monitoring, Artificial intelligence, Precision oncology, Foundation models, Multimodal learning, Digital twins, Clinical decision support, Liquid biopsy, Personalized medicine, Computational oncology.
