Leave No Data Behind: Exploring a new paradigm in oncology with foundation models and large language models

作者：Federica Corso, A. Zec, Margherita Favali, Marta Ligero, Lars Hilgers, Luca Mauro Invernizzi, Laura Mazzeo, Adrià Marcos Morales, Gustav Müller‐Franzes, Inês Machado, Felix Busch, V. Miskovic, Francesco Trovò, Claudia Proto, Giuseppe Lo Russo, Mario Occhipinti, Marta Brambilla, Teresa Beninato, Susan Halabi, Marina Chiara Garassino, Alessandra Pedrocchi, Anna Pellat, Lisa Adams, Julien Caldéraro, Daniel Truhn, Suzette Delaloge, Julien Vibert, Jana Lipková, Miriam Koopman, Raquel Pérez-López, Mireia Crispin-Ortuzar, Jakob Nikolas Kather, Arsela Prelaj · 发表于：Cell Reports Medicine · 年份：2026 · DOI：10.1016/j.xcrm.2026.102966 · 研究领域：Cancer Genomics and Diagnostics、Machine Learning in Healthcare、Topic Modeling

Foundation models (FMs) and large language models (LLMs) are transforming cancer AI by integrating heterogeneous data sources, including medical imaging, electronic health records, and molecular profiles. By learning from large-scale, unstructured, and label-free inputs, these models may support diagnosis, biomarker discovery, prognostic assessment, treatment personalization, and workflow automation. In this narrative review, we propose the paradigm of "Leave No Data Behind" to describe the promise that broad oncology data integration may generate clinically meaningful outputs. We critically assess whether this paradigm is supported by current evidence and identify the key challenges that must be addressed to harness the full potential of FMs and LLMs for clinical implementation in oncology.