{"id":"https://openalex.org/W7204493575","doi":"https://doi.org/10.5281/zenodo.22127863","title":"MedDeID English synthetic clinical corpus, benchmark and annotation guideline","display_name":"MedDeID English synthetic clinical corpus, benchmark and annotation guideline","publication_year":2026,"publication_date":"2026-08-27","ids":{"openalex":"https://openalex.org/W7204493575","doi":"https://doi.org/10.5281/zenodo.22127863"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.22127863","doi":"https://doi.org/10.5281/zenodo.22127863","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.22127863","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dataset"},"volume":null,"type":"dataset","is_traditional":false,"indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.22127863","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5026467114","display_name":"Stig Hellemans","orcid":"https://orcid.org/0000-0001-9441-3882","observed_orcids":["https://orcid.org/0000-0001-9441-3882"]},"institutions":[{"id":"https://openalex.org/I149213910","display_name":"University of Antwerp","ror":"https://ror.org/008x57b05","country_code":"BE","type":"education","lineage":["https://openalex.org/I149213910"]},{"id":"https://openalex.org/I4210102047","display_name":"Antwerp University Hospital","ror":"https://ror.org/01hwamj44","country_code":"BE","type":"funder","lineage":["https://openalex.org/I4210102047"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Hellemans, Stig","raw_affiliation_strings":["Adrem Data Lab, Department of Computer Science, University of Antwerp; Antwerp University Hospital"],"raw_orcid":"https://orcid.org/0000-0001-9441-3882","affiliations":[{"raw_affiliation_string":"Adrem Data Lab, Department of Computer Science, University of Antwerp; Antwerp University Hospital","institution_ids":["https://openalex.org/I149213910","https://openalex.org/I4210102047"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5146456860","display_name":"Tom Stroobants","orcid":"https://orcid.org/0009-0009-6983-5405","observed_orcids":["https://orcid.org/0009-0009-6983-5405"]},"institutions":[{"id":"https://openalex.org/I149213910","display_name":"University of Antwerp","ror":"https://ror.org/008x57b05","country_code":"BE","type":"education","lineage":["https://openalex.org/I149213910"]},{"id":"https://openalex.org/I4210102047","display_name":"Antwerp University Hospital","ror":"https://ror.org/01hwamj44","country_code":"BE","type":"funder","lineage":["https://openalex.org/I4210102047"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Stroobants, Tom","raw_affiliation_strings":["Laboratory of Experimental Medicine and Pediatrics (LEMP), University of Antwerp; Antwerp University Hospital (UZA)"],"raw_orcid":"https://orcid.org/0009-0009-6983-5405","affiliations":[{"raw_affiliation_string":"Laboratory of Experimental Medicine and Pediatrics (LEMP), University of Antwerp; Antwerp University Hospital (UZA)","institution_ids":["https://openalex.org/I149213910","https://openalex.org/I4210102047"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087186341","display_name":"Elyne Scheurwegs","orcid":"https://orcid.org/0000-0003-1560-7617","observed_orcids":["https://orcid.org/0000-0003-1560-7617"]},"institutions":[{"id":"https://openalex.org/I4210102047","display_name":"Antwerp University Hospital","ror":"https://ror.org/01hwamj44","country_code":"BE","type":"funder","lineage":["https://openalex.org/I4210102047"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Scheurwegs, Elyne","raw_affiliation_strings":["Antwerp University Hospital (UZA)"],"raw_orcid":"https://orcid.org/0000-0003-1560-7617","affiliations":[{"raw_affiliation_string":"Antwerp University Hospital (UZA)","institution_ids":["https://openalex.org/I4210102047"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024401144","display_name":"Pieter Meysman","orcid":"https://orcid.org/0000-0001-5903-633X","observed_orcids":["https://orcid.org/0000-0001-5903-633X"]},"institutions":[{"id":"https://openalex.org/I149213910","display_name":"University of Antwerp","ror":"https://ror.org/008x57b05","country_code":"BE","type":"education","lineage":["https://openalex.org/I149213910"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Meysman, Pieter","raw_affiliation_strings":["Adrem Data Lab, Department of Computer Science, University of Antwerp"],"raw_orcid":"https://orcid.org/0000-0001-5903-633X","affiliations":[{"raw_affiliation_string":"Adrem Data Lab, Department of Computer Science, University of Antwerp","institution_ids":["https://openalex.org/I149213910"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067177892","display_name":"Philippe G. Jorens","orcid":"https://orcid.org/0000-0002-5434-957X","observed_orcids":["https://orcid.org/0000-0002-5434-957X"]},"institutions":[{"id":"https://openalex.org/I149213910","display_name":"University of Antwerp","ror":"https://ror.org/008x57b05","country_code":"BE","type":"education","lineage":["https://openalex.org/I149213910"]},{"id":"https://openalex.org/I4210102047","display_name":"Antwerp University Hospital","ror":"https://ror.org/01hwamj44","country_code":"BE","type":"funder","lineage":["https://openalex.org/I4210102047"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Jorens, Philippe","raw_affiliation_strings":["Laboratory of Experimental Medicine and Pediatrics (LEMP), University of Antwerp; Antwerp University Hospital (UZA)"],"raw_orcid":"https://orcid.org/0000-0002-5434-957X","affiliations":[{"raw_affiliation_string":"Laboratory of Experimental Medicine and Pediatrics (LEMP), University of Antwerp; Antwerp University Hospital (UZA)","institution_ids":["https://openalex.org/I149213910","https://openalex.org/I4210102047"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024445778","display_name":"Kris Laukens","orcid":"https://orcid.org/0000-0002-8217-2564","observed_orcids":["https://orcid.org/0000-0002-8217-2564"]},"institutions":[{"id":"https://openalex.org/I149213910","display_name":"University of Antwerp","ror":"https://ror.org/008x57b05","country_code":"BE","type":"education","lineage":["https://openalex.org/I149213910"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Laukens, Kris","raw_affiliation_strings":["Adrem Data Lab, Department of Computer Science, University of Antwerp"],"raw_orcid":"https://orcid.org/0000-0002-8217-2564","affiliations":[{"raw_affiliation_string":"Adrem Data Lab, Department of Computer Science, University of Antwerp","institution_ids":["https://openalex.org/I149213910"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.8237000107765198,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.8237000107765198,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.04190000146627426,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T14029","display_name":"Thoreau and American Literature","score":0.010599999688565731,"subfield":{"id":"https://openalex.org/subfields/3605","display_name":"Health Information Management"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/english-language","display_name":"English language","score":0.4309999942779541},{"id":"https://openalex.org/keywords/benchmark-dataset","display_name":"benchmark dataset","score":0.5180000066757202},{"id":"https://openalex.org/keywords/data-anonymization","display_name":"data anonymization","score":0.421999990940094}],"concepts":[{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.8427000045776367},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7508000135421753},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6690999865531921},{"id":"https://openalex.org/C2780182762","wikidata":"https://www.wikidata.org/wiki/Q1630279","display_name":"Guideline","level":2,"score":0.616599977016449},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5591999888420105},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.45910000801086426},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40610000491142273},{"id":"https://openalex.org/C45340560","wikidata":"https://www.wikidata.org/wiki/Q215382","display_name":"Disjoint sets","level":2,"score":0.40220001339912415},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3443000018596649},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.3174000084400177},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.30239999294281006},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.29899999499320984},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.2556000053882599}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.5281/zenodo.22127863","doi":"https://doi.org/10.5281/zenodo.22127863","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.22127863","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dataset"},{"id":"doi:10.5281/zenodo.22127864","doi":"https://doi.org/10.5281/zenodo.22127864","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.22127864","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dataset"},{"id":"doi:10.5281/zenodo.22129255","doi":"https://doi.org/10.5281/zenodo.22129255","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.22129255","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dataset"},{"id":"doi:10.5281/zenodo.22689857","doi":"https://doi.org/10.5281/zenodo.22689857","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.22689857","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dataset"}],"best_oa_location":{"id":"doi:10.5281/zenodo.22127863","doi":"https://doi.org/10.5281/zenodo.22127863","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.22127863","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dataset"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G3748284682","display_name":"QUEHR.AI: Towards a Question-Answering System for Electronic Health Records: Bridging Clinicians and Data","funder_award_id":"1SA3226N","funder_id":"https://openalex.org/F4320321730","funder_display_name":"Fonds Wetenschappelijk Onderzoek"}],"funders":[{"id":"https://openalex.org/F4320321730","display_name":"Fonds Wetenschappelijk Onderzoek","ror":"https://ror.org/03qtxy027"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7215090134","https://openalex.org/W7202187010","https://openalex.org/W3175122546","https://openalex.org/W7212727604","https://openalex.org/W6940950575","https://openalex.org/W7212145642","https://openalex.org/W7160388826","https://openalex.org/W2574739597","https://openalex.org/W7100013398","https://openalex.org/W7163353615"],"abstract_inverted_index":{"A":[0],"synthetic":[1],"English":[2,40],"clinical-text":[3],"de-identification":[4],"release":[5],"containing":[6],"6,700":[7],"model-development":[8],"documents":[9],"and":[10,19,28,43],"a":[11],"disjoint":[12],"300-document":[13],"human-validated":[14],"benchmark,":[15],"balanced":[16],"between":[17],"en-GB":[18],"en-US.":[20],"The":[21,35],"benchmark":[22],"contains":[23,38,47],"1,717":[24],"primary":[25],"PII":[26],"spans":[27],"7,358":[29],"confirmed":[30],"nested":[31],"core-PII":[32],"subannotation":[33],"segments.":[34],"archive":[36],"also":[37],"the":[39],"annotation":[41],"guideline":[42],"provenance":[44],"manifests.":[45],"It":[46],"no":[48],"real":[49],"patient":[50],"notes":[51],"or":[52],"personal":[53],"information.":[54]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-08-28T00:00:00"}