{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,28]],"date-time":"2026-10-28T17:36:05Z","timestamp":1793208965946,"version":"4.5.0"},"reference-count":64,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T00:00:00Z","timestamp":1792713600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Journal of Biomedical Informatics"],"published-print":{"date-parts":[[2026,12]]},"DOI":"10.1016\/j.jbi.2026.105106","type":"journal-article","created":{"date-parts":[[2026,10,22]],"date-time":"2026-10-22T15:27:20Z","timestamp":1792682840000},"page":"105106","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["MDeID: A dataset for multilingual medical de-identification"],"prefix":"10.1016","volume":"184","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-5550-7992","authenticated-orcid":false,"given":"Risha","family":"Surana","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1661-3720","authenticated-orcid":false,"given":"Rodolfo","family":"Quispe","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alistair","family":"Johnson","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Thomas","family":"Lin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.jbi.2026.105106_b1","doi-asserted-by":"crossref","first-page":"1144","DOI":"10.1186\/1471-2458-14-1144","article-title":"A systematic review of barriers to data sharing in public health","volume":"14","author":"van Panhuis","year":"2014","journal-title":"BMC Public Health"},{"key":"10.1016\/j.jbi.2026.105106_b2","series-title":"Health insurance portability and accountability act of 1996","author":"U.S. Department of Health and Human Services","year":"1996"},{"key":"10.1016\/j.jbi.2026.105106_b3","series-title":"Health information technology for economic and clinical health act","author":"Congress","year":"2009"},{"issue":"Suppl","key":"10.1016\/j.jbi.2026.105106_b4","doi-asserted-by":"crossref","first-page":"S20","DOI":"10.1016\/j.jbi.2015.07.020","article-title":"Annotating longitudinal clinical narratives for de-identification: The 2014 i2b2\/UTHealth corpus","volume":"58","author":"Stubbs","year":"2015","journal-title":"J. Biomed. Inform."},{"issue":"4","key":"10.1016\/j.jbi.2026.105106_b5","doi-asserted-by":"crossref","first-page":"1053","DOI":"10.1162\/coli_a_00458","article-title":"The text anonymization benchmark (TAB): A dedicated corpus and evaluation framework for text anonymization","volume":"48","author":"Pil\u00e1n","year":"2022","journal-title":"Comput. Linguist."},{"key":"10.1016\/j.jbi.2026.105106_b6","series-title":"Proceedings of the Workshop on Ethical and Legal Issues in Human Language Technologies and Multilingual de-Identification of Sensitive Data in Language Resources Within the 13th Language Resources and Evaluation Conference","first-page":"64","article-title":"MAPA project: Ready-to-go open-source datasets and deep learning technology to remove identifying information from text documents","author":"Arranz","year":"2022"},{"key":"10.1016\/j.jbi.2026.105106_b7","series-title":"TIPSTER Text Program Phase II: Proceedings of a Workshop","first-page":"445","article-title":"The multilingual entity task (MET) overview","author":"Merchant","year":"1996"},{"issue":"5","key":"10.1016\/j.jbi.2026.105106_b8","doi-asserted-by":"crossref","first-page":"550","DOI":"10.1197\/jamia.M2444","article-title":"Evaluating the state-of-the-art in automatic de-identification","volume":"14","author":"Uzuner","year":"2007","journal-title":"J. Am. Med. Inform. Assoc."},{"key":"10.1016\/j.jbi.2026.105106_b9","series-title":"Proceedings of the Iberian Languages Evaluation Forum Co-Located with the 35th Conference of the Spanish Society for Natural Language Processing (IberLEF@SEPLN 2019), Bilbao, Spain, September 24th, 2019","first-page":"618","article-title":"Automatic de-identification of medical texts in Spanish: the MEDDOCAN track, corpus, guidelines, methods and evaluation of results","volume":"vol. 2421","author":"Marimon","year":"2019"},{"key":"10.1016\/j.jbi.2026.105106_b10","series-title":"NLNDE: The neither-language-nor-domain-experts\u2019 way of Spanish medical document de-identification","author":"Lange","year":"2020"},{"issue":"2","key":"10.1016\/j.jbi.2026.105106_b11","doi-asserted-by":"crossref","first-page":"ooab025","DOI":"10.1093\/jamiaopen\/ooab025","article-title":"Annotation and initial evaluation of a large annotated German oncological corpus","volume":"4","author":"Kittner","year":"2021","journal-title":"JAMIA Open"},{"key":"10.1016\/j.jbi.2026.105106_b12","unstructured":"D. Benikova, C. Biemann, M. Kisselew, S. Pad\u00f3, GermEval 2014 Named Entity Recognition Shared Task: Companion Paper, in: Proceedings of the KONVENS GermEval Workshop, 2014, pp. 104\u2013112."},{"key":"10.1016\/j.jbi.2026.105106_b13","doi-asserted-by":"crossref","first-page":"317","DOI":"10.1038\/s41597-019-0322-0","article-title":"MIMIC-CXR, a de-identified publicly available database of chest radiographs with free-text reports","volume":"6","author":"Johnson","year":"2019","journal-title":"Sci. Data"},{"key":"10.1016\/j.jbi.2026.105106_b14","series-title":"Proceedings of the Fifth International Conference on Language Resources and Evaluation (LREC 2006)","doi-asserted-by":"crossref","first-page":"1051","DOI":"10.63317\/2t7a4mqb9ktq","article-title":"An introduction to NLP-based textual anonymisation","author":"Medlock","year":"2006"},{"key":"10.1016\/j.jbi.2026.105106_b15","series-title":"Shaip de-identified medical text dataset","author":"Inc.","year":"2022"},{"key":"10.1016\/j.jbi.2026.105106_b16","series-title":"Proceedings of the Annual Conference of the Spanish Association for Natural Language Processing: Projects and Demonstrations (SEPLN-PD 2021)","first-page":"17","article-title":"The E3C project: European clinical case corpus","volume":"vol. 2968","author":"Magnini","year":"2021"},{"key":"10.1016\/j.jbi.2026.105106_b17","first-page":"241","article-title":"Mention detection, normalization and classification of species, pathogens, humans and food in clinical documents: Overview of the LivingNER shared task and resources","volume":"69","author":"Miranda-Escalada","year":"2022","journal-title":"Proces. Del Leng. Nat."},{"key":"10.1016\/j.jbi.2026.105106_b18","first-page":"243","article-title":"NLP applied to occupational health: MEDDOPROF shared task at IberLEF 2021 on automatic recognition, classification and normalization of professions and occupations from medical texts","volume":"67","author":"Lima-L\u00f3pez","year":"2021","journal-title":"Proces. Del Leng. Nat."},{"key":"10.1016\/j.jbi.2026.105106_b19","series-title":"PubMed","author":"National Library of Medicine","year":"2026"},{"key":"10.1016\/j.jbi.2026.105106_b20","series-title":"GPT-4o","author":"OpenAI","year":"2024"},{"key":"10.1016\/j.jbi.2026.105106_b21","series-title":"DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter","author":"Sanh","year":"2019"},{"key":"10.1016\/j.jbi.2026.105106_b22","series-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2019"},{"key":"10.1016\/j.jbi.2026.105106_b23","series-title":"DeepSeek-R1: Incentivizing reasoning capability in LLMs via reinforcement learning","author":"DeepSeek-AI","year":"2025"},{"key":"10.1016\/j.jbi.2026.105106_b24","series-title":"o4-mini","author":"OpenAI","year":"2025"},{"key":"10.1016\/j.jbi.2026.105106_b25","series-title":"German Medical Data Sciences 2022 \u2013 Future Medicine: More Precise, more Integrative, more Sustainable!","first-page":"66","article-title":"GraSCCo \u2013 the first publicly shareable, multiply-alienated German clinical text corpus","volume":"vol. 296","author":"Modersohn","year":"2022"},{"issue":"1","key":"10.1016\/j.jbi.2026.105106_b26","doi-asserted-by":"crossref","first-page":"1088","DOI":"10.1038\/s41597-025-05320-1","article-title":"A textual dataset of de-identified health records in Spanish and Catalan for medical entity recognition and anonymization","volume":"12","author":"Lima-L\u00f3pez","year":"2025","journal-title":"Sci. Data"},{"key":"10.1016\/j.jbi.2026.105106_b27","series-title":"Studies in Health Technology and Informatics. Vol. 317","first-page":"171","article-title":"De-identifying GraSCCo \u2013 a pilot study for the de-identification of the German medical text project (GeMTeX) corpus","author":"Lohr","year":"2024"},{"key":"10.1016\/j.jbi.2026.105106_b28","doi-asserted-by":"crossref","first-page":"586","DOI":"10.1038\/s41597-023-02487-3","article-title":"ACI-Bench: a novel ambient clinical intelligence dataset for benchmarking automatic visit note generation","volume":"10","author":"Yim","year":"2023","journal-title":"Sci. Data"},{"key":"10.1016\/j.jbi.2026.105106_b29","series-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)","first-page":"528","article-title":"Asking the right question: Inferring advice-seeking intentions from personal narratives","author":"Fu","year":"2019"},{"key":"10.1016\/j.jbi.2026.105106_b30","doi-asserted-by":"crossref","DOI":"10.1016\/j.jbi.2023.104293","article-title":"Detecting evidence of invasive fungal infections in cytology and histopathology reports enriched with concept-level annotations","volume":"139","author":"Rozova","year":"2023","journal-title":"J. Biomed. Inform."},{"key":"10.1016\/j.jbi.2026.105106_b31","series-title":"CORAL: Expert-curated medical oncology reports to advance language model inference","author":"Sushil","year":"2024"},{"key":"10.1016\/j.jbi.2026.105106_b32","series-title":"Proceedings of the 17th International Conference on Educational Data Mining","first-page":"790","article-title":"The cleaned repository of annotated personally identifiable information (CRAPII)","author":"Holmes","year":"2024"},{"key":"10.1016\/j.jbi.2026.105106_b33","series-title":"CheXpert Plus: Augmenting a large chest X-ray dataset with text radiology reports, patient demographics and additional image formats","author":"Chambon","year":"2024"},{"issue":"2","key":"10.1016\/j.jbi.2026.105106_b34","doi-asserted-by":"crossref","first-page":"304","DOI":"10.1093\/jamia\/ocv080","article-title":"Preparing a collection of radiology examinations for distribution and retrieval","volume":"23","author":"Demner-Fushman","year":"2016","journal-title":"J. Am. Med. Inform. Assoc."},{"key":"10.1016\/j.jbi.2026.105106_b35","doi-asserted-by":"crossref","DOI":"10.1038\/sdata.2016.35","article-title":"MIMIC-III, a freely accessible critical care database","volume":"3","author":"Johnson","year":"2016","journal-title":"Sci. Data"},{"key":"10.1016\/j.jbi.2026.105106_b36","series-title":"Proceedings of the 2023 ACM Conference on Fairness, Accountability, and Transparency (FAccT \u201923)","first-page":"123","article-title":"In the name of fairness: Assessing the bias in clinical record de-identification","author":"Xiao","year":"2023"},{"key":"10.1016\/j.jbi.2026.105106_b37","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/s41597-022-01899-x","article-title":"MIMIC-IV, a freely accessible electronic health record dataset","volume":"10","author":"Johnson","year":"2023","journal-title":"Sci. Data"},{"key":"10.1016\/j.jbi.2026.105106_b38","series-title":"CC-MAIN-2023-06: January\/February 2023 General Web Crawl","author":"Crawl","year":"2023"},{"issue":"1","key":"10.1016\/j.jbi.2026.105106_b39","doi-asserted-by":"crossref","first-page":"19973","DOI":"10.1038\/s41598-021-99554-9","article-title":"The OpenDeID corpus for patient de-identification","volume":"11","author":"Jonnagaddala","year":"2021","journal-title":"Sci. Rep."},{"key":"10.1016\/j.jbi.2026.105106_b40","doi-asserted-by":"crossref","first-page":"909","DOI":"10.1038\/s41597-023-02814-8","article-title":"A large-scale dataset of patient summaries for retrieval-based clinical decision support systems","volume":"10","author":"Zhao","year":"2023","journal-title":"Sci. Data"},{"key":"10.1016\/j.jbi.2026.105106_b41","doi-asserted-by":"crossref","first-page":"32","DOI":"10.1186\/1472-6947-8-32","article-title":"Automated de-identification of free-text medical records","volume":"8","author":"Neamatullah","year":"2008","journal-title":"BMC Med. Inform. Decis. Mak."},{"key":"10.1016\/j.jbi.2026.105106_b42","series-title":"De-identification annotations: Labeling of PhysioNet gold corpus by i2b2-2014","author":"Google Health","year":"2017"},{"key":"10.1016\/j.jbi.2026.105106_b43","series-title":"Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)","first-page":"588","article-title":"PriMock57: A dataset of primary care mock consultations","author":"Papadopoulos Korfiatis","year":"2022"},{"key":"10.1016\/j.jbi.2026.105106_b44","doi-asserted-by":"crossref","first-page":"18","DOI":"10.12688\/gatesopenres.12812.1","article-title":"A de-identified database of 11,979 verbal autopsy open-ended responses","volume":"2","author":"Flaxman","year":"2018","journal-title":"Gates Open Res."},{"key":"10.1016\/j.jbi.2026.105106_b45","series-title":"wikipiifed: Automated dataset creation from Wikipedia biographies for federated named-entity recognition","author":"wikipiifed contributors","year":"2026"},{"issue":"1","key":"10.1016\/j.jbi.2026.105106_b46","doi-asserted-by":"crossref","first-page":"7","DOI":"10.1186\/s13326-020-00225-x","article-title":"CAS: Corpus of clinical cases in French","volume":"11","author":"Grabar","year":"2020","journal-title":"J. Biomed. Semant."},{"key":"10.1016\/j.jbi.2026.105106_b47","series-title":"Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)","first-page":"7450","article-title":"FRASIMED: A clinical French annotated resource produced through crosslingual BERT-based annotation projection","author":"Zaghir","year":"2024"},{"key":"10.1016\/j.jbi.2026.105106_b48","series-title":"Proceedings of the Thirteenth Language Resources and Evaluation Conference","doi-asserted-by":"crossref","first-page":"3650","DOI":"10.63317\/45xa5amgy44x","article-title":"GGPONC 2.0 \u2013 the German clinical guideline corpus for oncology: Curation workflow, annotation policy, baseline NER taggers","author":"Borchert","year":"2022"},{"key":"10.1016\/j.jbi.2026.105106_b49","series-title":"GPTNERMED: Synthetic medical NER dataset","author":"Frank Kramer Lab","year":"2023"},{"key":"10.1016\/j.jbi.2026.105106_b50","series-title":"Proceedings of the Thirteenth Language Resources and Evaluation Conference","doi-asserted-by":"crossref","first-page":"5609","DOI":"10.63317\/42k6q2qtymf5","article-title":"BRATECA (Brazilian tertiary care dataset): a clinical information dataset for the Portuguese language","author":"Consoli","year":"2022"},{"issue":"1","key":"10.1016\/j.jbi.2026.105106_b51","doi-asserted-by":"crossref","first-page":"13","DOI":"10.1186\/s13326-022-00269-1","article-title":"SemClinBr \u2013 a multi-institutional and multi-specialty semantically annotated corpus for Portuguese clinical NLP tasks","volume":"13","author":"e Oliveira","year":"2022","journal-title":"J. Biomed. Semant."},{"key":"10.1016\/j.jbi.2026.105106_b52","unstructured":"A. Intxaurrondo, et al., The Biomedical Abbreviation Recognition and Resolution (BARR) Track: Benchmarking, Evaluation and Importance of Abbreviation Recognition Systems Applied to Spanish Biomedical Abstracts, in: Proceedings of the Iberian Language Evaluation Forum (IberEval 2017), 2017, pp. 230\u2013246."},{"key":"10.1016\/j.jbi.2026.105106_b53","unstructured":"A. Intxaurrondo, et al., Finding Mentions of Abbreviations and Their Definitions in Spanish Clinical Cases: The BARR2 Shared Task Evaluation Results, in: Proceedings of the Iberian Language Evaluation Forum (IberEval 2018), 2018, pp. 280\u2013289."},{"key":"10.1016\/j.jbi.2026.105106_b54","series-title":"Proceedings of the Iberian Languages Evaluation Forum (IberLEF 2020)","first-page":"303","article-title":"Named entity recognition, concept normalization and clinical coding: Overview of the CANTEMIST track for cancer text mining in Spanish, corpus, guidelines, methods and results","volume":"vol. 2664","author":"Miranda-Escalada","year":"2020"},{"key":"10.1016\/j.jbi.2026.105106_b55","series-title":"Overview of automatic clinical coding: Annotations, guidelines, and solutions for non-English clinical cases at CodiEsp track of CLEF eHealth 2020","author":"Miranda-Escalada","year":"2020"},{"issue":"1","key":"10.1016\/j.jbi.2026.105106_b56","doi-asserted-by":"crossref","first-page":"69","DOI":"10.1186\/s12911-021-01395-z","article-title":"A clinical trials corpus annotated with UMLS entities to enhance the access to evidence-based medicine","volume":"21","author":"Campillos-Llanos","year":"2021","journal-title":"BMC Med. Inform. Decis. Mak."},{"key":"10.1016\/j.jbi.2026.105106_b57","series-title":"Proceedings of the 3rd Clinical Natural Language Processing Workshop","first-page":"291","article-title":"The Chilean Waiting List Corpus: A new resource for clinical Named Entity Recognition in Spanish","author":"B\u00e1ez","year":"2020"},{"key":"10.1016\/j.jbi.2026.105106_b58","series-title":"Working Notes of the Conference and Labs of the Evaluation Forum (CLEF 2022)","first-page":"179","article-title":"Overview of DisTEMIST at BioASQ: Automatic detection and normalization of diseases from clinical texts: Results, methods, evaluation and multilingual resources","volume":"vol. 3180","author":"Miranda-Escalada","year":"2022"},{"key":"10.1016\/j.jbi.2026.105106_b59","doi-asserted-by":"crossref","DOI":"10.1016\/j.jbi.2019.103172","article-title":"A corpus to support eHealth knowledge discovery technologies","volume":"94","author":"Piad-Morffis","year":"2019","journal-title":"J. Biomed. Inform."},{"key":"10.1016\/j.jbi.2026.105106_b60","series-title":"Proceedings of the Iberian Languages Evaluation Forum Co-Located with the 35th Conference of the Spanish Society for Natural Language Processing (IberLEF@SEPLN 2019), Bilbao, Spain, September 24th, 2019","first-page":"1","article-title":"Overview of the eHealth knowledge discovery challenge at IberLEF 2019","volume":"vol. 2421","author":"Piad-Morffis","year":"2019"},{"key":"10.1016\/j.jbi.2026.105106_b61","series-title":"Proceedings of the Iberian Languages Evaluation Forum (IberLEF 2020) Co-Located with the 36th Conference of the Spanish Society for Natural Language Processing (SEPLN 2020), M\u00c1laga, Spain, September 23rd, 2020","first-page":"71","article-title":"Overview of the eHealth knowledge discovery challenge at IberLEF 2020","volume":"vol. 2664","author":"Piad-Morffis","year":"2020"},{"key":"10.1016\/j.jbi.2026.105106_b62","series-title":"Proceedings of the Twelfth Language Resources and Evaluation Conference","first-page":"5772","article-title":"NUBes: A corpus of negation and uncertainty in Spanish clinical texts","author":"Lima-L\u00f3pez","year":"2020"},{"key":"10.1016\/j.jbi.2026.105106_b63","doi-asserted-by":"crossref","DOI":"10.1016\/j.media.2020.101797","article-title":"PadChest: A large chest X-ray image dataset with multi-label annotated reports","volume":"66","author":"Bustos","year":"2020","journal-title":"Med. Image Anal."},{"key":"10.1016\/j.jbi.2026.105106_b64","series-title":"Working Notes of CLEF 2021\u2014Conference and Labs of the Evaluation Forum","first-page":"732","article-title":"Overview of CLEF eHealth Task 1\u2014SpRadIE: A challenge on information extraction from Spanish radiology reports","volume":"vol. 2936","author":"Cotik","year":"2021"}],"container-title":["Journal of Biomedical Informatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1532046426001309?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1532046426001309?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,10,28]],"date-time":"2026-10-28T17:21:48Z","timestamp":1793208108000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1532046426001309"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,12]]},"references-count":64,"alternative-id":["S1532046426001309"],"URL":"https:\/\/doi.org\/10.1016\/j.jbi.2026.105106","relation":{},"ISSN":["1532-0464"],"issn-type":[{"value":"1532-0464","type":"print"}],"subject":[],"published":{"date-parts":[[2026,12]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"MDeID: A dataset for multilingual medical de-identification","name":"articletitle","label":"Article Title"},{"value":"Journal of Biomedical Informatics","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.jbi.2026.105106","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 The Authors. Published by Elsevier Inc.","name":"copyright","label":"Copyright"}],"article-number":"105106"}}