{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,9]],"date-time":"2026-03-09T16:51:55Z","timestamp":1773075115557,"version":"3.50.1"},"reference-count":50,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,5,17]],"date-time":"2025-05-17T00:00:00Z","timestamp":1747440000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,5,17]],"date-time":"2025-05-17T00:00:00Z","timestamp":1747440000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/100016036","name":"Health~Holland","doi-asserted-by":"publisher","award":["LSHM20103"],"award-info":[{"award-number":["LSHM20103"]}],"id":[{"id":"10.13039\/100016036","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100016036","name":"Health~Holland","doi-asserted-by":"publisher","award":["LSHM20103"],"award-info":[{"award-number":["LSHM20103"]}],"id":[{"id":"10.13039\/100016036","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100016036","name":"Health~Holland","doi-asserted-by":"publisher","award":["LSHM20103"],"award-info":[{"award-number":["LSHM20103"]}],"id":[{"id":"10.13039\/100016036","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100016036","name":"Health~Holland","doi-asserted-by":"publisher","award":["LSHM20103"],"award-info":[{"award-number":["LSHM20103"]}],"id":[{"id":"10.13039\/100016036","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100016036","name":"Health~Holland","doi-asserted-by":"publisher","award":["LSHM20103"],"award-info":[{"award-number":["LSHM20103"]}],"id":[{"id":"10.13039\/100016036","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003246","name":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek","doi-asserted-by":"publisher","award":["NWO-KIC-Siemens HealthyAI (KICH3.LTP.20.006)"],"award-info":[{"award-number":["NWO-KIC-Siemens HealthyAI (KICH3.LTP.20.006)"]}],"id":[{"id":"10.13039\/501100003246","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003246","name":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek","doi-asserted-by":"publisher","award":["VIDI grant (number 18388)"],"award-info":[{"award-number":["VIDI grant (number 18388)"]}],"id":[{"id":"10.13039\/501100003246","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003246","name":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek","doi-asserted-by":"publisher","award":["VIDI grant (number 18388)"],"award-info":[{"award-number":["VIDI grant (number 18388)"]}],"id":[{"id":"10.13039\/501100003246","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100007601","name":"Horizon 2020","doi-asserted-by":"publisher","award":["PANCAIM project (101016851)"],"award-info":[{"award-number":["PANCAIM project (101016851)"]}],"id":[{"id":"10.13039\/501100007601","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100007601","name":"Horizon 2020","doi-asserted-by":"publisher","award":["PANCAIM project (101016851)"],"award-info":[{"award-number":["PANCAIM project (101016851)"]}],"id":[{"id":"10.13039\/501100007601","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100007601","name":"Horizon 2020","doi-asserted-by":"publisher","award":["ProCAncer-I project (952159)"],"award-info":[{"award-number":["ProCAncer-I project (952159)"]}],"id":[{"id":"10.13039\/501100007601","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100007601","name":"Horizon 2020","doi-asserted-by":"publisher","award":["ProCAncer-I project (952159)"],"award-info":[{"award-number":["ProCAncer-I project (952159)"]}],"id":[{"id":"10.13039\/501100007601","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100007601","name":"Horizon 2020","doi-asserted-by":"publisher","award":["PANCAIM project (101016851)"],"award-info":[{"award-number":["PANCAIM project (101016851)"]}],"id":[{"id":"10.13039\/501100007601","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Junior Researcher Grant Radboud Institute for Health Sciences and Jeroen Bosch Ziekenhuis","award":["RIHS JO 18.51773"],"award-info":[{"award-number":["RIHS JO 18.51773"]}]},{"name":"European Union HORIZON-HLTH-2022: COMFORT","award":["101079894"],"award-info":[{"award-number":["101079894"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["npj Digit. Med."],"abstract":"<jats:title>Abstract<\/jats:title>\n          <jats:p>Artificial Intelligence can mitigate the global shortage of medical diagnostic personnel but requires large-scale annotated datasets to train clinical algorithms. Natural Language Processing (NLP), including Large Language Models (LLMs), shows great potential for annotating clinical data to facilitate algorithm development but remains underexplored due to a lack of public benchmarks. This study introduces the DRAGON challenge, a benchmark for clinical NLP with 28 tasks and 28,824 annotated medical reports from five Dutch care centers. It facilitates automated, large-scale, cost-effective data annotation. Foundational LLMs were pretrained using four million clinical reports from a sixth Dutch care center. Evaluations showed the superiority of domain-specific pretraining (DRAGON 2025 test score of 0.770) and mixed-domain pretraining (0.756), compared to general-domain pretraining (0.734, <jats:italic>p<\/jats:italic>\u2009&lt;\u20090.005). While strong performance was achieved on 18\/28 tasks, performance was subpar on 10\/28 tasks, uncovering where innovations are needed. Benchmark, code, and foundational LLMs are publicly available.<\/jats:p>","DOI":"10.1038\/s41746-025-01626-x","type":"journal-article","created":{"date-parts":[[2025,5,17]],"date-time":"2025-05-17T01:58:00Z","timestamp":1747447080000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["The DRAGON benchmark for clinical NLP"],"prefix":"10.1038","volume":"8","author":[{"given":"Joeran S.","family":"Bosma","sequence":"first","affiliation":[]},{"given":"Koen","family":"Dercksen","sequence":"additional","affiliation":[]},{"given":"Luc","family":"Builtjes","sequence":"additional","affiliation":[]},{"given":"Romain","family":"Andr\u00e9","sequence":"additional","affiliation":[]},{"given":"Christian","family":"Roest","sequence":"additional","affiliation":[]},{"given":"Stefan J.","family":"Fransen","sequence":"additional","affiliation":[]},{"given":"Constant R.","family":"Noordman","sequence":"additional","affiliation":[]},{"given":"Mar","family":"Navarro-Padilla","sequence":"additional","affiliation":[]},{"given":"Judith","family":"Lefkes","sequence":"additional","affiliation":[]},{"given":"Nat\u00e1lia","family":"Alves","sequence":"additional","affiliation":[]},{"given":"Max J. J.","family":"de Grauw","sequence":"additional","affiliation":[]},{"given":"Leander","family":"van Eekelen","sequence":"additional","affiliation":[]},{"given":"Joey M. A.","family":"Spronck","sequence":"additional","affiliation":[]},{"given":"Megan","family":"Schuurmans","sequence":"additional","affiliation":[]},{"given":"Bram","family":"de Wilde","sequence":"additional","affiliation":[]},{"given":"Ward","family":"Hendrix","sequence":"additional","affiliation":[]},{"given":"Witali","family":"Aswolinskiy","sequence":"additional","affiliation":[]},{"given":"Anindo","family":"Saha","sequence":"additional","affiliation":[]},{"given":"Jasper J.","family":"Twilt","sequence":"additional","affiliation":[]},{"given":"Daan","family":"Geijs","sequence":"additional","affiliation":[]},{"given":"Jeroen","family":"Veltman","sequence":"additional","affiliation":[]},{"given":"Derya","family":"Yakar","sequence":"additional","affiliation":[]},{"given":"Maarten","family":"de Rooij","sequence":"additional","affiliation":[]},{"given":"Francesco","family":"Ciompi","sequence":"additional","affiliation":[]},{"given":"Alessa","family":"Hering","sequence":"additional","affiliation":[]},{"given":"Jeroen","family":"Geerdink","sequence":"additional","affiliation":[]},{"given":"Henkjan","family":"Huisman","sequence":"additional","affiliation":[]},{"name":"On behalf of the DRAGON consortium","sequence":"additional","affiliation":[]},{"given":"Max J. J.","family":"de Grauw","sequence":"additional","affiliation":[]},{"given":"Leander","family":"van Eekelen","sequence":"additional","affiliation":[]},{"given":"Bram","family":"de Wilde","sequence":"additional","affiliation":[]},{"given":"Quintin","family":"van Lohuizen","sequence":"additional","affiliation":[]},{"given":"Michelle","family":"Stegeman","sequence":"additional","affiliation":[]},{"given":"Karlijn","family":"Rutten","sequence":"additional","affiliation":[]},{"given":"Inge M. E.","family":"Smit","sequence":"additional","affiliation":[]},{"given":"Gijs","family":"Stultiens","sequence":"additional","affiliation":[]},{"given":"Christiaan G.","family":"Overduin","sequence":"additional","affiliation":[]},{"given":"Matthieu J. C. M.","family":"Rutten","sequence":"additional","affiliation":[]},{"given":"Ernst Th.","family":"Scholten","sequence":"additional","affiliation":[]},{"given":"Rachel S.","family":"van der Post","sequence":"additional","affiliation":[]},{"given":"Katrien","family":"Gr\u00fcnberg","sequence":"additional","affiliation":[]},{"given":"Shoko","family":"Vos","sequence":"additional","affiliation":[]},{"given":"Elise M. G.","family":"Taken","sequence":"additional","affiliation":[]},{"given":"Iris D.","family":"Nagtegaal","sequence":"additional","affiliation":[]},{"given":"Anne","family":"Mickan","sequence":"additional","affiliation":[]},{"given":"Miriam","family":"Groeneveld","sequence":"additional","affiliation":[]},{"given":"Paul K.","family":"Gerke","sequence":"additional","affiliation":[]},{"given":"James A.","family":"Meakin","sequence":"additional","affiliation":[]},{"given":"M. G.","family":"Looijen-Salamon","sequence":"additional","affiliation":[]},{"given":"Tijmen L. M.","family":"de Haas","sequence":"additional","affiliation":[]},{"given":"Fabian","family":"Hoitsma","sequence":"additional","affiliation":[]},{"given":"Marina","family":"D\u2019Amato","sequence":"additional","affiliation":[]},{"given":"Maarten","family":"de Rooij","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,5,17]]},"reference":[{"key":"1626_CR1","doi-asserted-by":"publisher","first-page":"e136","DOI":"10.1016\/S1470-2045(20)30751-8","volume":"22","author":"H Hricak","year":"2021","unstructured":"Hricak, H. et al. Medical imaging and nuclear medicine: a Lancet Oncology Commission. Lancet Oncol. 22, e136\u2013e172 (2021).","journal-title":"Lancet Oncol."},{"key":"1626_CR2","doi-asserted-by":"publisher","first-page":"209","DOI":"10.3322\/caac.21660","volume":"71","author":"H Sung","year":"2021","unstructured":"Sung, H. et al. Global Cancer Statistics 2020: GLOBOCAN Estimates of Incidence and Mortality Worldwide for 36 Cancers in 185 Countries. CA A Cancer J. Clinicians 71, 209\u2013249 (2021).","journal-title":"CA A Cancer J. Clinicians"},{"key":"1626_CR3","doi-asserted-by":"publisher","first-page":"799","DOI":"10.1097\/RLI.0000000000000791","volume":"56","author":"N Netzer","year":"2021","unstructured":"Netzer, N. et al. Fully Automatic Deep Learning in Bi-institutional Prostate Magnetic Resonance Imaging: Effects of Cohort Size and Heterogeneity. Invest. Radio. 56, 799\u2013808 (2021).","journal-title":"Invest. Radio."},{"key":"1626_CR4","doi-asserted-by":"publisher","first-page":"936","DOI":"10.1016\/S1470-2045(23)00298-X","volume":"24","author":"K L\u00e5ng","year":"2023","unstructured":"L\u00e5ng, K. et al. Artificial intelligence-supported screen reading versus standard double reading in the Mammography Screening with Artificial Intelligence trial (MASAI): a clinical safety analysis of a randomised, controlled, non-inferiority, single-blinded, screening accuracy study. Lancet Oncol. 24, 936\u2013944 (2023).","journal-title":"Lancet Oncol."},{"key":"1626_CR5","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-022-10292-y","volume":"12","author":"DD Martin","year":"2022","unstructured":"Martin, D. D., Calder, A. D., Ranke, M. B., Binder, G. & Thodberg, H. H. Accuracy and self-validation of automated bone age determination. Sci. Rep. 12, 6388 (2022).","journal-title":"Sci. Rep."},{"key":"1626_CR6","doi-asserted-by":"publisher","first-page":"2402","DOI":"10.1001\/jama.2016.17216","volume":"316","author":"V Gulshan","year":"2016","unstructured":"Gulshan, V. et al. Development and Validation of a Deep Learning Algorithm for Detection of Diabetic Retinopathy in Retinal Fundus Photographs. JAMA 316, 2402\u20132410 (2016).","journal-title":"JAMA"},{"key":"1626_CR7","doi-asserted-by":"publisher","first-page":"2224","DOI":"10.1007\/s00330-021-08320-y","volume":"32","author":"M Hosseinzadeh","year":"2022","unstructured":"Hosseinzadeh, M. et al. Deep learning\u2013assisted prostate cancer detection on bi-parametric MRI: minimum training data size requirements and effect of prior knowledge. Eur. Radio. 32, 2224\u20132234 (2022).","journal-title":"Eur. Radio."},{"key":"1626_CR8","doi-asserted-by":"publisher","first-page":"e17984","DOI":"10.2196\/17984","volume":"8","author":"I Spasic","year":"2020","unstructured":"Spasic, I. & Nenadic, G. Clinical text data in machine learning: systematic review. JMIR Med. Inf. 8, e17984 (2020).","journal-title":"JMIR Med. Inf."},{"key":"1626_CR9","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-019-0322-0","volume":"6","author":"AEW Johnson","year":"2019","unstructured":"Johnson, A. E. W. et al. MIMIC-CXR, a de-identified publicly available database of chest radiographs with free-text reports. Sci. Data 6, 317 (2019).","journal-title":"Sci. Data"},{"key":"1626_CR10","doi-asserted-by":"publisher","first-page":"101797","DOI":"10.1016\/j.media.2020.101797","volume":"66","author":"A Bustos","year":"2020","unstructured":"Bustos, A., Pertusa, A., Salinas, J.-M. & De La Iglesia-Vay\u00e1, M. PadChest: a large chest x-ray image dataset with multi-label annotated reports. Med. Image Anal. 66, 101797 (2020).","journal-title":"Med. Image Anal."},{"key":"1626_CR11","doi-asserted-by":"publisher","first-page":"304","DOI":"10.1093\/jamia\/ocv080","volume":"23","author":"D Demner-Fushman","year":"2016","unstructured":"Demner-Fushman, D. et al. Preparing a collection of radiology examinations for distribution and retrieval. J. Am. Med. Inform. Assoc. 23, 304\u2013310 (2016).","journal-title":"J. Am. Med. Inform. Assoc."},{"key":"1626_CR12","doi-asserted-by":"publisher","unstructured":"Hamamci, I. E. et al. A foundation model utilizing chest CT volumes and radiology reports for supervised-level zero-shot detection of abnormalities. Preprint at https:\/\/doi.org\/10.48550\/arXiv.2403.17834, https:\/\/www.researchsquare.com\/article\/rs-5271327\/v1 (2024).","DOI":"10.48550\/arXiv.2403.17834"},{"key":"1626_CR13","doi-asserted-by":"publisher","unstructured":"Johnson, A., Pollard, T., Horng, S., Celi, L. A. & Mark, R. MIMIC-IV-Note: Deidentified free-text clinical notes (version 2.2). PhysioNet. https:\/\/doi.org\/10.13026\/1n74-ne17 (2023).","DOI":"10.13026\/1n74-ne17"},{"key":"1626_CR14","doi-asserted-by":"publisher","unstructured":"Kefeli, J. TCGA-reports: a machine-readable pathology report resource for benchmarking text-based AI models. Kefeli et al. Mendeley Data https:\/\/doi.org\/10.17632\/HYG5XKZNPX.1 (2024).","DOI":"10.17632\/HYG5XKZNPX.1"},{"key":"1626_CR15","doi-asserted-by":"publisher","unstructured":"Li, Y. et al. ChatDoctor: a medical chat model fine-tuned on a large language model meta-AI (LLaMA) using medical domain knowledge. Cureus https:\/\/doi.org\/10.7759\/cureus.40895 (2023).","DOI":"10.7759\/cureus.40895"},{"key":"1626_CR16","doi-asserted-by":"publisher","first-page":"2076","DOI":"10.1093\/jamia\/ocae133","volume":"31","author":"A Wang","year":"2024","unstructured":"Wang, A., Liu, C., Yang, J. & Weng, C. Fine-tuning large language models for rare disease concept normalization. J. Am. Med. Inform. Assoc. 31, 2076\u20132083 (2024).","journal-title":"J. Am. Med. Inform. Assoc."},{"key":"1626_CR17","doi-asserted-by":"publisher","first-page":"172","DOI":"10.1038\/s41586-023-06291-2","volume":"620","author":"K Singhal","year":"2023","unstructured":"Singhal, K. et al. Large language models encode clinical knowledge. Nature 620, 172\u2013180 (2023).","journal-title":"Nature"},{"key":"1626_CR18","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-024-53081-z","volume":"15","author":"Q Jin","year":"2024","unstructured":"Jin, Q. et al. Matching patients to clinical trials with large language models. Nat. Commun. 15, 9074 (2024).","journal-title":"Nat. Commun."},{"key":"1626_CR19","unstructured":"Lin, C.-Y. ROUGE: a package for automatic evaluation of summaries. Text summarization branches out, 74\u201381 (Association for Computational Linguistics, 2004)."},{"key":"1626_CR20","doi-asserted-by":"publisher","unstructured":"Lu, Q., Dou, D. & Nguyen, T. ClinicalT5: a generative language model for clinical text. In: Findings of the association for computational linguistics: EMNLP, 2022, 5436\u20135443 (Association for Computational Linguistics, 2022). https:\/\/doi.org\/10.18653\/v1\/2022.findings-emnlp.398.","DOI":"10.18653\/v1\/2022.findings-emnlp.398"},{"key":"1626_CR21","doi-asserted-by":"publisher","first-page":"e210258","DOI":"10.1148\/ryai.210258","volume":"4","author":"A Yan","year":"2022","unstructured":"Yan, A. et al. RadBERT: adapting transformer-based language models to radiology. Radiol. Artif. Intell. 4, e210258 (2022).","journal-title":"Radiol. Artif. Intell."},{"key":"1626_CR22","unstructured":"Verkijk, S. & Vossen, P. MedRoBERTa.nl: A Language Model for Dutch Electronic Health Records. Comput. Linguist. Neth. J. 11, 141\u2013159. Retrieved from https:\/\/clinjournal.org\/clinj\/article\/view\/132 (2021)."},{"key":"1626_CR23","doi-asserted-by":"publisher","unstructured":"Huang, K., Altosaar, J. & Ranganath, R. ClinicalBERT: modeling clinical notes and predicting hospital readmission. Preprint at https:\/\/doi.org\/10.48550\/ARXIV.1904.05342 (2019).","DOI":"10.48550\/ARXIV.1904.05342"},{"key":"1626_CR24","doi-asserted-by":"publisher","unstructured":"Busch, F. et al. Large language models for structured reporting in radiology: past, present, and future. Eur. Radiol. https:\/\/doi.org\/10.1007\/s00330-024-11107-6 (2024).","DOI":"10.1007\/s00330-024-11107-6"},{"key":"1626_CR25","doi-asserted-by":"publisher","unstructured":"Meakin, J. et al. Grand-Challenge.org. Zenodo https:\/\/doi.org\/10.5281\/ZENODO.3356819 (2023).","DOI":"10.5281\/ZENODO.3356819"},{"key":"1626_CR26","doi-asserted-by":"publisher","unstructured":"Deng, J. et al. ImageNet: A large-scale hierarchical image database. In 2009 IEEE Conference on Computer Vision and Pattern Recognition 248\u2013255 (IEEE, 2009). https:\/\/doi.org\/10.1109\/CVPR.2009.5206848.","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"1626_CR27","unstructured":"Wang, A. et al. GLUE: a multi-task benchmark and analysis platform for natural language understanding. International Conference on Learning Representations https:\/\/openreview.net\/forum?id=rJ4km2R5t7 (2019)."},{"key":"1626_CR28","unstructured":"Buckeye, A. J. et al. Data Science Bowl 2017. https:\/\/kaggle.com\/competitions\/data-science-bowl-2017 (2017)."},{"key":"1626_CR29","unstructured":"Devlin, J., Chang, M.-W., Lee, K. & Toutanova, K. BERT: pre-training of deep bidirectional transformers for language understanding. Preprint at http:\/\/arxiv.org\/abs\/1810.04805 (2019)."},{"key":"1626_CR30","unstructured":"Central Intelligence Agency. Field listing - languages (Central Intelligence Agency, 2007)."},{"key":"1626_CR31","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3458754","volume":"3","author":"Y Gu","year":"2022","unstructured":"Gu, Y. et al. Domain-specific language model pretraining for biomedical natural language processing. ACM Trans. Comput. Healthc. 3, 1\u201323 (2022).","journal-title":"ACM Trans. Comput. Healthc."},{"key":"1626_CR32","doi-asserted-by":"publisher","first-page":"1251","DOI":"10.3390\/diagnostics13071251","volume":"13","author":"MT Rietberg","year":"2023","unstructured":"Rietberg, M. T., Nguyen, V. B., Geerdink, J., Vijlbrief, O. & Seifert, C. Accurate and reliable classification of unstructured reports on their diagnostic goal using BERT models. Diagnostics 13, 1251 (2023).","journal-title":"Diagnostics"},{"key":"1626_CR33","unstructured":"Liu, Y. et al. RoBERTa: a robustly optimized BERT pretraining approach. Preprint at http:\/\/arxiv.org\/abs\/1907.11692 (2019)."},{"key":"1626_CR34","unstructured":"Beltagy, I., Peters, M. E. & Cohan, A. Longformer: the long-document transformer. Preprint at http:\/\/arxiv.org\/abs\/2004.05150 (2020)."},{"key":"1626_CR35","doi-asserted-by":"publisher","first-page":"1797","DOI":"10.1093\/jamia\/ocac127","volume":"29","author":"Y Gao","year":"2022","unstructured":"Gao, Y. et al. A scoping review of publicly available language tasks in clinical natural language processing. J. Am. Med. Inform. Assoc. 29, 1797\u20131806 (2022).","journal-title":"J. Am. Med. Inform. Assoc."},{"key":"1626_CR36","doi-asserted-by":"publisher","first-page":"104286","DOI":"10.1016\/j.jbi.2023.104286","volume":"138","author":"Y Gao","year":"2023","unstructured":"Gao, Y. et al. DR.BENCH: diagnostic reasoning benchmark for clinical natural language processing. J. Biomed. Inform. 138, 104286 (2023).","journal-title":"J. Biomed. Inform."},{"key":"1626_CR37","doi-asserted-by":"publisher","unstructured":"Hendrix, W. et al. Trends in the incidence of pulmonary nodules in chest computed tomography: 10-year results from two Dutch hospitals. Eur. Radiol. https:\/\/doi.org\/10.1007\/s00330-023-09826-3 (2023).","DOI":"10.1007\/s00330-023-09826-3"},{"key":"1626_CR38","doi-asserted-by":"publisher","first-page":"342","DOI":"10.1136\/amiajnl-2012-001034","volume":"20","author":"D Carrell","year":"2013","unstructured":"Carrell, D. et al. Hiding in plain sight: use of realistic surrogates to reduce exposure of protected health information in clinical text. J. Am. Med. Inf. Assoc. 20, 342\u2013348 (2013).","journal-title":"J. Am. Med. Inf. Assoc."},{"key":"1626_CR39","doi-asserted-by":"publisher","unstructured":"Natural Language Processing and Computational Linguistics group at the University of Groningen. bert-base-dutch-cased. Hugging Face https:\/\/doi.org\/10.57967\/HF\/0149 (2022).","DOI":"10.57967\/HF\/0149"},{"key":"1626_CR40","doi-asserted-by":"publisher","unstructured":"Joeran Bosma. dragon-bert-base-mixed-domain. Hugging Face https:\/\/doi.org\/10.57967\/HF\/2166 (2024).","DOI":"10.57967\/HF\/2166"},{"key":"1626_CR41","doi-asserted-by":"publisher","unstructured":"Joeran Bosma. dragon-bert-base-domain-specific. Hugging Face https:\/\/doi.org\/10.57967\/HF\/2167 (2024).","DOI":"10.57967\/HF\/2167"},{"key":"1626_CR42","doi-asserted-by":"publisher","unstructured":"Joeran Bosma. dragon-roberta-base-mixed-domain. Hugging Face https:\/\/doi.org\/10.57967\/HF\/2168 (2024).","DOI":"10.57967\/HF\/2168"},{"key":"1626_CR43","doi-asserted-by":"publisher","unstructured":"Joeran Bosma. dragon-roberta-base-domain-specific. Hugging Face https:\/\/doi.org\/10.57967\/HF\/2169 (2024).","DOI":"10.57967\/HF\/2169"},{"key":"1626_CR44","doi-asserted-by":"publisher","unstructured":"Joeran Bosma. dragon-roberta-large-mixed-domain. Hugging Face https:\/\/doi.org\/10.57967\/HF\/2170 (2024).","DOI":"10.57967\/HF\/2170"},{"key":"1626_CR45","doi-asserted-by":"publisher","unstructured":"Joeran Bosma. dragon-roberta-large-domain-specific. Hugging Face https:\/\/doi.org\/10.57967\/HF\/2171 (2024).","DOI":"10.57967\/HF\/2171"},{"key":"1626_CR46","doi-asserted-by":"publisher","unstructured":"Joeran Bosma. dragon-longformer-base-mixed-domain. Hugging Face https:\/\/doi.org\/10.57967\/HF\/2172 (2024).","DOI":"10.57967\/HF\/2172"},{"key":"1626_CR47","doi-asserted-by":"publisher","unstructured":"Joeran Bosma. dragon-longformer-base-domain-specific. Hugging Face https:\/\/doi.org\/10.57967\/HF\/2173 (2024).","DOI":"10.57967\/HF\/2173"},{"key":"1626_CR48","doi-asserted-by":"publisher","unstructured":"Joeran Bosma. dragon-longformer-large-mixed-domain. Hugging Face https:\/\/doi.org\/10.57967\/HF\/2174 (2024).","DOI":"10.57967\/HF\/2174"},{"key":"1626_CR49","doi-asserted-by":"publisher","unstructured":"Joeran Bosma. dragon-longformer-large-domain-specific. Hugging Face https:\/\/doi.org\/10.57967\/HF\/2175 (2024).","DOI":"10.57967\/HF\/2175"},{"key":"1626_CR50","doi-asserted-by":"publisher","unstructured":"Bosma, J. S. et al. DRAGON statistical analysis plan. https:\/\/doi.org\/10.5281\/ZENODO.10374512 (2024).","DOI":"10.5281\/ZENODO.10374512"}],"container-title":["npj Digital Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41746-025-01626-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-025-01626-x","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-025-01626-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,17]],"date-time":"2025-05-17T14:03:54Z","timestamp":1747490634000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41746-025-01626-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,17]]},"references-count":50,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["1626"],"URL":"https:\/\/doi.org\/10.1038\/s41746-025-01626-x","relation":{},"ISSN":["2398-6352"],"issn-type":[{"value":"2398-6352","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,5,17]]},"assertion":[{"value":"4 November 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 April 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 May 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"A.S. has received lecture honorarium from Guerbet. F.C. has been Chair of the Scientific and Medical Advisory Board of TRIBVN Healthcare, received advisory board fees from TRIBVN Healthcare, and is shareholder in Aiosyn BV.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"289"}}