{"id":"doi:10.1038/s41591-025-03780-x","kind":"article","title":"Real-world deployment of a fine-tuned pathology foundation model for lung cancer biomarker detection","authors":["Campanella G","Kumar N","Nanda S","Singi S","Fluder E","Kwan R","Muehlstedt S","Pfarr N","Schüffler PJ","Häggström I","Neittaanmäki N","Akyürek LM","Basnet A","Jamaspishvili T","Nasr MR","Croken MM","Hirsch FR","Elkrief A","Yu H","Ardon O","Goldgof GM","Hameed M","Houldsworth J","Arcila M","Fuchs TJ"],"author_count":26,"year":2025,"published":"2025-07-09","venue":"Nature medicine","cited_by":66,"doi":"10.1038/s41591-025-03780-x","arxiv_id":null,"nct_id":null,"source_url":"https://doi.org/10.1038/s41591-025-03780-x","archive_url":"https://space-kitty.com/papers/doi:10.1038/s41591-025-03780-x","updated":null,"pmid":"40634781","pmcid":"PMC12443599","openalex_id":null,"pdf_url":"https://europepmc.org/articles/PMC12443599/pdf","abstract":"Artificial intelligence models using digital histopathology slides stained with hematoxylin and eosin offer promising, tissue-preserving diagnostic tools for patients with cancer. Despite their advantages, their clinical utility in real-world settings remains unproven. Assessing EGFR mutations in lung adenocarcinoma demands rapid, accurate and cost-effective tests that preserve tissue for genomic sequencing. PCR-based assays provide rapid results but with reduced accuracy compared with next-generation sequencing and require additional tissue. Computational biomarkers leveraging modern foundation models can address these limitations. Here we assembled a large international clinical dataset of digital lung adenocarcinoma slides (N = 8,461) to develop a computational EGFR biomarker. Our model fine-tunes an open-source foundation model, improving task-specific performance with out-of-center generalization and clinical-grade accuracy on primary and metastatic specimens (mean area under the curve: internal 0.847, external 0.870). To evaluate real-world clinical translation, we conducted a prospective silent trial of the biomarker on primary samples, achieving an area under the curve of 0.890. The artificial-intelligence-assisted workflow reduced the number of rapid molecular tests needed by up to 43% while maintaining the current clinical standard performance. Our retrospective and prospective analyses demonstrate the real-world clinical utility of a computational pathology biomarker.","abstract_license":"CC-BY (article license as recorded by Europe PMC; abstract reproduced unmodified apart from markup removal)","license":"CC-BY","is_open_access":true,"peer_reviewed":null,"categories":[],"details":null,"provenance":"europepmc","attribution":"Abstract of \"Real-world deployment of a fine-tuned pathology foundation model for lung cancer biomarker detection\" by Campanella G, Kumar N, Nanda S et al., https://doi.org/10.1038/s41591-025-03780-x, used under its Creative Commons Attribution license (CC-BY); markup removed, otherwise unmodified.","topics":[{"slug":"ai-medicine","name":"AI in Clinical Medicine","domain_slug":"medicine"}],"cited_in_dossiers":[]}