{"id":"https://openalex.org/W4410641494","doi":"https://doi.org/10.1016/j.artmed.2025.103148","title":"Creating, anonymizing and evaluating the first medical language model pre-trained on Dutch Electronic Health Records: MedRoBERTa.nl","display_name":"Creating, anonymizing and evaluating the first medical language model pre-trained on Dutch Electronic Health Records: MedRoBERTa.nl","publication_year":2025,"publication_date":"2025-05-23","ids":{"openalex":"https://openalex.org/W4410641494","doi":"https://doi.org/10.1016/j.artmed.2025.103148","pmid":"https://pubmed.ncbi.nlm.nih.gov/40472749"},"language":"en","primary_location":{"id":"doi:10.1016/j.artmed.2025.103148","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.artmed.2025.103148","pdf_url":null,"source":{"id":"https://openalex.org/S42468263","display_name":"Artificial Intelligence in Medicine","issn_l":"0933-3657","issn":["0933-3657","1873-2860"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Artificial Intelligence in Medicine","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1016/j.artmed.2025.103148","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5025435123","display_name":"Stella Verkijk","orcid":"https://orcid.org/0009-0000-9263-2272"},"institutions":[{"id":"https://openalex.org/I865915315","display_name":"Vrije Universiteit Amsterdam","ror":"https://ror.org/008xxew50","country_code":"NL","type":"education","lineage":["https://openalex.org/I865915315"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Stella Verkijk","raw_affiliation_strings":["Vrije Universiteit Amsterdam, The Netherlands. Electronic address: s.verkijk@vu.nl"],"raw_orcid":"https://orcid.org/0009-0000-9263-2272","affiliations":[{"raw_affiliation_string":"Vrije Universiteit Amsterdam, The Netherlands. Electronic address: s.verkijk@vu.nl","institution_ids":["https://openalex.org/I865915315"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003791447","display_name":"Piek Vossen","orcid":"https://orcid.org/0000-0002-6238-5941"},"institutions":[{"id":"https://openalex.org/I865915315","display_name":"Vrije Universiteit Amsterdam","ror":"https://ror.org/008xxew50","country_code":"NL","type":"education","lineage":["https://openalex.org/I865915315"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Piek Vossen","raw_affiliation_strings":["Vrije Universiteit Amsterdam, The Netherlands"],"raw_orcid":"https://orcid.org/0000-0002-6238-5941","affiliations":[{"raw_affiliation_string":"Vrije Universiteit Amsterdam, The Netherlands","institution_ids":["https://openalex.org/I865915315"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5003791447"],"corresponding_institution_ids":["https://openalex.org/I865915315"],"apc_list":{"value":3230,"currency":"USD","value_usd":3230},"apc_paid":{"value":3230,"currency":"USD","value_usd":3230},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.05052469,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"167","issue":null,"first_page":"103148","last_page":"103148"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9983999729156494,"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/T10028","display_name":"Topic Modeling","score":0.9983999729156494,"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":0.9976000189781189,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T13702","display_name":"Machine Learning in Healthcare","score":0.9957000017166138,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7292485237121582},{"id":"https://openalex.org/keywords/health-records","display_name":"Health records","score":0.7092074155807495},{"id":"https://openalex.org/keywords/medical-record","display_name":"Medical record","score":0.5519777536392212},{"id":"https://openalex.org/keywords/electronic-health-record","display_name":"Electronic health record","score":0.5516586303710938},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.42027032375335693},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3932371139526367},{"id":"https://openalex.org/keywords/health-care","display_name":"Health care","score":0.15135982632637024},{"id":"https://openalex.org/keywords/medicine","display_name":"Medicine","score":0.13717305660247803}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7292485237121582},{"id":"https://openalex.org/C3019952477","wikidata":"https://www.wikidata.org/wiki/Q1324077","display_name":"Health records","level":3,"score":0.7092074155807495},{"id":"https://openalex.org/C195910791","wikidata":"https://www.wikidata.org/wiki/Q1324077","display_name":"Medical record","level":2,"score":0.5519777536392212},{"id":"https://openalex.org/C3020144179","wikidata":"https://www.wikidata.org/wiki/Q10871684","display_name":"Electronic health record","level":3,"score":0.5516586303710938},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.42027032375335693},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3932371139526367},{"id":"https://openalex.org/C160735492","wikidata":"https://www.wikidata.org/wiki/Q31207","display_name":"Health care","level":2,"score":0.15135982632637024},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.13717305660247803},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C126838900","wikidata":"https://www.wikidata.org/wiki/Q77604","display_name":"Radiology","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009426","descriptor_name":"Netherlands","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009426","descriptor_name":"Netherlands","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009426","descriptor_name":"Netherlands","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012660","descriptor_name":"Semantics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012660","descriptor_name":"Semantics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012660","descriptor_name":"Semantics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D057286","descriptor_name":"Electronic Health Records","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D057286","descriptor_name":"Electronic Health Records","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D057286","descriptor_name":"Electronic Health Records","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":4,"locations":[{"id":"doi:10.1016/j.artmed.2025.103148","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.artmed.2025.103148","pdf_url":null,"source":{"id":"https://openalex.org/S42468263","display_name":"Artificial Intelligence in Medicine","issn_l":"0933-3657","issn":["0933-3657","1873-2860"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Artificial Intelligence in Medicine","raw_type":"journal-article"},{"id":"pmid:40472749","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40472749","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Artificial intelligence in medicine","raw_type":null},{"id":"pmh:oai:research.vu.nl:openaire/ba25c21d-10c1-4902-bc18-d74e0e7090f2","is_oa":true,"landing_page_url":"https://research.vu.nl/en/publications/ba25c21d-10c1-4902-bc18-d74e0e7090f2","pdf_url":null,"source":{"id":"https://openalex.org/S4306401107","display_name":"VU Research Portal","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I865915315","host_organization_name":"Vrije Universiteit Amsterdam","host_organization_lineage":["https://openalex.org/I865915315"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Verkijk, S & Vossen, P 2025, 'Creating, anonymizing and evaluating the first medical language model pre-trained on Dutch Electronic Health Records : MedRoBERTa.nl', Artificial Intelligence in Medicine, vol. 167, 103148, pp. 1-13. https://doi.org/10.1016/j.artmed.2025.103148","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:research.vu.nl:openaire_cris_publications/ba25c21d-10c1-4902-bc18-d74e0e7090f2","is_oa":true,"landing_page_url":"https://hdl.handle.net/1871.1/ba25c21d-10c1-4902-bc18-d74e0e7090f2","pdf_url":null,"source":{"id":"https://openalex.org/S4306401107","display_name":"VU Research Portal","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I865915315","host_organization_name":"Vrije Universiteit Amsterdam","host_organization_lineage":["https://openalex.org/I865915315"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Verkijk, S & Vossen, P 2025, 'Creating, anonymizing and evaluating the first medical language model pre-trained on Dutch Electronic Health Records : MedRoBERTa.nl', Artificial Intelligence in Medicine, vol. 167, 103148, pp. 1-13. https://doi.org/10.1016/j.artmed.2025.103148","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"doi:10.1016/j.artmed.2025.103148","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.artmed.2025.103148","pdf_url":null,"source":{"id":"https://openalex.org/S42468263","display_name":"Artificial Intelligence in Medicine","issn_l":"0933-3657","issn":["0933-3657","1873-2860"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Artificial Intelligence in Medicine","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6200000047683716}],"awards":[],"funders":[{"id":"https://openalex.org/F4320335454","display_name":"Nationaal Regieorgaan Onderwijsonderzoek","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":51,"referenced_works":["https://openalex.org/W1034374084","https://openalex.org/W1522301498","https://openalex.org/W1566289585","https://openalex.org/W1854884267","https://openalex.org/W2156061936","https://openalex.org/W2396881363","https://openalex.org/W2911489562","https://openalex.org/W2915429162","https://openalex.org/W2937845937","https://openalex.org/W2965373594","https://openalex.org/W2970511757","https://openalex.org/W2970771982","https://openalex.org/W2983004086","https://openalex.org/W2996428491","https://openalex.org/W2996580882","https://openalex.org/W2998353611","https://openalex.org/W3011411500","https://openalex.org/W3018763859","https://openalex.org/W3046375318","https://openalex.org/W3099950029","https://openalex.org/W3104033643","https://openalex.org/W3104578551","https://openalex.org/W3105220303","https://openalex.org/W3117432124","https://openalex.org/W3118485687","https://openalex.org/W3135542296","https://openalex.org/W3173215866","https://openalex.org/W3173954987","https://openalex.org/W3211022409","https://openalex.org/W4200628968","https://openalex.org/W4206105765","https://openalex.org/W4252122345","https://openalex.org/W4301329292","https://openalex.org/W4312220150","https://openalex.org/W4324392584","https://openalex.org/W4360951492","https://openalex.org/W4361008252","https://openalex.org/W4378498597","https://openalex.org/W4385381606","https://openalex.org/W4385572420","https://openalex.org/W4391109462","https://openalex.org/W4391888998","https://openalex.org/W6728484576","https://openalex.org/W6766869486","https://openalex.org/W6781031682","https://openalex.org/W6791635792","https://openalex.org/W6840931820","https://openalex.org/W6842827737","https://openalex.org/W6851013271","https://openalex.org/W7030197835","https://openalex.org/W7030437387"],"related_works":["https://openalex.org/W187932805","https://openalex.org/W2554558516","https://openalex.org/W2909369938","https://openalex.org/W4392490004","https://openalex.org/W1641026212","https://openalex.org/W4402738807","https://openalex.org/W4410420109","https://openalex.org/W2911982698","https://openalex.org/W2355354922","https://openalex.org/W2527724968"],"abstract_inverted_index":{"Electronic":[0],"Health":[1],"Records":[2],"(EHRs)":[3],"contain":[4],"written":[5],"notes":[6,62,130],"by":[7,145],"all":[8,14],"kinds":[9],"of":[10,16,18,33,53,84,87,106,180],"medical":[11,174],"professionals":[12],"about":[13],"aspects":[15],"well-being":[17],"a":[19,25],"patient.":[20],"When":[21],"adequately":[22],"processed":[23],"with":[24],"Large":[26],"Language":[27,97],"Model":[28],"(LLM),":[29],"this":[30,88],"enormous":[31],"source":[32],"information":[34],"can":[35,40,166],"be":[36,167],"analyzed":[37],"quantitatively,":[38],"which":[39,66,90],"lead":[41],"to":[42,141,156],"new":[43],"insights,":[44],"for":[45,93,111],"example":[46],"in":[47,51,60,73,117,131],"treatment":[48],"development":[49,105],"or":[50],"patterns":[52],"patient":[54],"recovery.":[55],"However,":[56],"the":[57,85,104,107,129],"language":[58],"used":[59],"clinical":[61],"is":[63,91],"very":[64],"idiosyncratic,":[65],"available":[67],"generic":[68],"LLMs":[69],"have":[70,78],"not":[71,79],"encountered":[72],"their":[74],"pre-training.":[75],"They":[76],"therefore":[77],"internalized":[80],"an":[81],"adequate":[82],"representation":[83],"semantics":[86],"data,":[89],"essential":[92],"building":[94],"reliable":[95],"Natural":[96],"Processing":[98],"(NLP)":[99],"software.":[100],"This":[101],"article":[102],"describes":[103],"first":[108],"domain-specific":[109],"LLM":[110],"Dutch":[112],"EHRs:":[113],"MedRoBERTa.nl.":[114],"We":[115,149,160],"discuss":[116],"detail":[118],"why":[119],"and":[120,136],"how":[121,137,163],"we":[122,138],"built":[123,173],"our":[124,151,164,181],"model,":[125],"pre-training":[126],"it":[127,143,155],"on":[128,178],"EHRs":[132],"using":[133],"different":[134],"strategies,":[135],"were":[139],"able":[140],"publish":[142],"publicly":[144],"thoroughly":[146],"anonymizing":[147],"it.":[148],"evaluate":[150],"model":[152,165],"extensively,":[153],"comparing":[154],"various":[157,170],"other":[158],"LLMs.":[159],"also":[161],"illustrate":[162],"used,":[168],"discussing":[169],"studies":[171],"that":[172],"text":[175],"mining":[176],"technology":[177],"top":[179],"model.":[182]},"counts_by_year":[],"updated_date":"2026-01-20T17:24:06.736184","created_date":"2025-10-10T00:00:00"}