{"id":"https://openalex.org/W4402279737","doi":"https://doi.org/10.3233/shti240853","title":"De-Identifying GRASCCO \u2013 A Pilot Study for the De-Identification of the German Medical Text Project (GeMTeX) Corpus","display_name":"De-Identifying GRASCCO \u2013 A Pilot Study for the De-Identification of the German Medical Text Project (GeMTeX) Corpus","publication_year":2024,"publication_date":"2024-08-30","ids":{"openalex":"https://openalex.org/W4402279737","doi":"https://doi.org/10.3233/shti240853","pmid":"https://pubmed.ncbi.nlm.nih.gov/39234720"},"language":"en","primary_location":{"id":"doi:10.3233/shti240853","is_oa":true,"landing_page_url":"http://dx.doi.org/10.3233/shti240853","pdf_url":null,"source":{"id":"https://openalex.org/S4210179765","display_name":"Studies in health technology and informatics","issn_l":"0926-9630","issn":["0926-9630","1879-8365"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"book series"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Studies in Health Technology and Informatics","raw_type":"book-chapter"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"http://dx.doi.org/10.3233/shti240853","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5042587817","display_name":"Christina Lohr","orcid":"https://orcid.org/0000-0001-9889-162X"},"institutions":[{"id":"https://openalex.org/I926574661","display_name":"Leipzig University","ror":"https://ror.org/03s7gtk40","country_code":"DE","type":"education","lineage":["https://openalex.org/I926574661"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Christina Lohr","raw_affiliation_strings":["GeMTeX Consortium of the German Medical Informatics Initiative","Institute for Medical Informatics, Statistics, and Epidemiology, Leipzig University, Germany"],"raw_orcid":"https://orcid.org/0000-0001-9889-162X","affiliations":[{"raw_affiliation_string":"GeMTeX Consortium of the German Medical Informatics Initiative","institution_ids":[]},{"raw_affiliation_string":"Institute for Medical Informatics, Statistics, and Epidemiology, Leipzig University, Germany","institution_ids":["https://openalex.org/I926574661"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084042518","display_name":"Franz Matthies","orcid":"https://orcid.org/0000-0001-7196-506X"},"institutions":[{"id":"https://openalex.org/I926574661","display_name":"Leipzig University","ror":"https://ror.org/03s7gtk40","country_code":"DE","type":"education","lineage":["https://openalex.org/I926574661"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Franz Matthies","raw_affiliation_strings":["GeMTeX Consortium of the German Medical Informatics Initiative","Institute for Medical Informatics, Statistics, and Epidemiology, Leipzig University, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"GeMTeX Consortium of the German Medical Informatics Initiative","institution_ids":[]},{"raw_affiliation_string":"Institute for Medical Informatics, Statistics, and Epidemiology, Leipzig University, Germany","institution_ids":["https://openalex.org/I926574661"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103019022","display_name":"Jakob Faller","orcid":"https://orcid.org/0009-0002-8875-5426"},"institutions":[{"id":"https://openalex.org/I181369854","display_name":"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg","ror":"https://ror.org/00f7hpc57","country_code":"DE","type":"education","lineage":["https://openalex.org/I181369854"]},{"id":"https://openalex.org/I4210088053","display_name":"Universit\u00e4tsklinikum Erlangen","ror":"https://ror.org/0030f2a11","country_code":"DE","type":"healthcare","lineage":["https://openalex.org/I4210088053"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jakob Faller","raw_affiliation_strings":["GeMTeX Consortium of the German Medical Informatics Initiative","Medical Center for Information and Communication Technology, Universit\u00e4tsklinikum Erlangen, Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg, Erlangen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"GeMTeX Consortium of the German Medical Informatics Initiative","institution_ids":[]},{"raw_affiliation_string":"Medical Center for Information and Communication Technology, Universit\u00e4tsklinikum Erlangen, Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg, Erlangen, Germany","institution_ids":["https://openalex.org/I4210088053","https://openalex.org/I181369854"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029707385","display_name":"Luise Modersohn","orcid":"https://orcid.org/0000-0002-8258-4366"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Luise Modersohn","raw_affiliation_strings":["GeMTeX Consortium of the German Medical Informatics Initiative","Institute of Artificial Intelligence and Informatics in Medicine, Medical Center rechts der Isar, Technical University Munich, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"GeMTeX Consortium of the German Medical Informatics Initiative","institution_ids":[]},{"raw_affiliation_string":"Institute of Artificial Intelligence and Informatics in Medicine, Medical Center rechts der Isar, Technical University Munich, Germany","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024563193","display_name":"Andrea Riedel","orcid":"https://orcid.org/0009-0006-9389-9482"},"institutions":[{"id":"https://openalex.org/I181369854","display_name":"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg","ror":"https://ror.org/00f7hpc57","country_code":"DE","type":"education","lineage":["https://openalex.org/I181369854"]},{"id":"https://openalex.org/I4210088053","display_name":"Universit\u00e4tsklinikum Erlangen","ror":"https://ror.org/0030f2a11","country_code":"DE","type":"healthcare","lineage":["https://openalex.org/I4210088053"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Andrea Riedel","raw_affiliation_strings":["GeMTeX Consortium of the German Medical Informatics Initiative","Medical Center for Information and Communication Technology, Universit\u00e4tsklinikum Erlangen, Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg, Erlangen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"GeMTeX Consortium of the German Medical Informatics Initiative","institution_ids":[]},{"raw_affiliation_string":"Medical Center for Information and Communication Technology, Universit\u00e4tsklinikum Erlangen, Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg, Erlangen, Germany","institution_ids":["https://openalex.org/I4210088053","https://openalex.org/I181369854"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044841280","display_name":"Udo Hahn","orcid":"https://orcid.org/0000-0002-5052-0245"},"institutions":[{"id":"https://openalex.org/I926574661","display_name":"Leipzig University","ror":"https://ror.org/03s7gtk40","country_code":"DE","type":"education","lineage":["https://openalex.org/I926574661"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Udo Hahn","raw_affiliation_strings":["GeMTeX Consortium of the German Medical Informatics Initiative","Institute for Medical Informatics, Statistics, and Epidemiology, Leipzig University, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"GeMTeX Consortium of the German Medical Informatics Initiative","institution_ids":[]},{"raw_affiliation_string":"Institute for Medical Informatics, Statistics, and Epidemiology, Leipzig University, Germany","institution_ids":["https://openalex.org/I926574661"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036975170","display_name":"R. Taft Kiser","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rebekka Kiser","raw_affiliation_strings":["Institute of Artificial Intelligence and Informatics in Medicine, Medical Center rechts der Isar, Technical University Munich, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Artificial Intelligence and Informatics in Medicine, Medical Center rechts der Isar, Technical University Munich, Germany","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039035898","display_name":"Martin Boeker","orcid":"https://orcid.org/0000-0003-2972-2042"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Martin Boeker","raw_affiliation_strings":["GeMTeX Consortium of the German Medical Informatics Initiative","Institute of Artificial Intelligence and Informatics in Medicine, Medical Center rechts der Isar, Technical University Munich, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"GeMTeX Consortium of the German Medical Informatics Initiative","institution_ids":[]},{"raw_affiliation_string":"Institute of Artificial Intelligence and Informatics in Medicine, Medical Center rechts der Isar, Technical University Munich, Germany","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042672161","display_name":"Frank Meineke","orcid":null},"institutions":[{"id":"https://openalex.org/I926574661","display_name":"Leipzig University","ror":"https://ror.org/03s7gtk40","country_code":"DE","type":"education","lineage":["https://openalex.org/I926574661"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Frank Meineke","raw_affiliation_strings":["GeMTeX Consortium of the German Medical Informatics Initiative","Institute for Medical Informatics, Statistics, and Epidemiology, Leipzig University, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"GeMTeX Consortium of the German Medical Informatics Initiative","institution_ids":[]},{"raw_affiliation_string":"Institute for Medical Informatics, Statistics, and Epidemiology, Leipzig University, Germany","institution_ids":["https://openalex.org/I926574661"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5042587817"],"corresponding_institution_ids":["https://openalex.org/I926574661"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.33737824,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"317","issue":null,"first_page":"171","last_page":"179"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.475600004196167,"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"}},"topics":[{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.475600004196167,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.15060000121593475,"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/T10028","display_name":"Topic Modeling","score":0.05380000174045563,"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/german","display_name":"German","score":0.8520099520683289},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.8311852216720581},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.807512640953064},{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.7597001791000366},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7266237735748291},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.6831158995628357},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.47056862711906433},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4528913199901581},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.37156209349632263},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3076395094394684},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.16240987181663513},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.08425679802894592}],"concepts":[{"id":"https://openalex.org/C154775046","wikidata":"https://www.wikidata.org/wiki/Q188","display_name":"German","level":2,"score":0.8520099520683289},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.8311852216720581},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.807512640953064},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.7597001791000366},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7266237735748291},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.6831158995628357},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.47056862711906433},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4528913199901581},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.37156209349632263},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3076395094394684},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.16240987181663513},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08425679802894592},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[{"descriptor_ui":"D003219","descriptor_name":"Confidentiality","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003219","descriptor_name":"Confidentiality","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003219","descriptor_name":"Confidentiality","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003219","descriptor_name":"Confidentiality","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D005858","descriptor_name":"Germany","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D005858","descriptor_name":"Germany","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D005858","descriptor_name":"Germany","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D005858","descriptor_name":"Germany","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":"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":false},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","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":false},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010865","descriptor_name":"Pilot Projects","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010865","descriptor_name":"Pilot Projects","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010865","descriptor_name":"Pilot Projects","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010865","descriptor_name":"Pilot Projects","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016494","descriptor_name":"Computer Security","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016494","descriptor_name":"Computer Security","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016494","descriptor_name":"Computer Security","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016494","descriptor_name":"Computer Security","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"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},{"descriptor_ui":"D057286","descriptor_name":"Electronic Health Records","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":3,"locations":[{"id":"doi:10.3233/shti240853","is_oa":true,"landing_page_url":"http://dx.doi.org/10.3233/shti240853","pdf_url":null,"source":{"id":"https://openalex.org/S4210179765","display_name":"Studies in health technology and informatics","issn_l":"0926-9630","issn":["0926-9630","1879-8365"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"book series"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Studies in Health Technology and Informatics","raw_type":"book-chapter"},{"id":"pmid:39234720","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/39234720","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":"Studies in health technology and informatics","raw_type":null},{"id":"pmh:oai:mediatum.ub.tum.de:node/1793346","is_oa":false,"landing_page_url":"https://mediatum.ub.tum.de/1793346","pdf_url":null,"source":{"id":"https://openalex.org/S4377196330","display_name":"mediaTUM  (Technical University of Munich)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I62916508","host_organization_name":"Technical University of Munich","host_organization_lineage":["https://openalex.org/I62916508"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.3233/shti240853","is_oa":true,"landing_page_url":"http://dx.doi.org/10.3233/shti240853","pdf_url":null,"source":{"id":"https://openalex.org/S4210179765","display_name":"Studies in health technology and informatics","issn_l":"0926-9630","issn":["0926-9630","1879-8365"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"book series"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Studies in Health Technology and Informatics","raw_type":"book-chapter"},"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.6299999952316284}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2315527029","https://openalex.org/W2392768766","https://openalex.org/W2058118494","https://openalex.org/W2361861616","https://openalex.org/W2065387230","https://openalex.org/W2382021449","https://openalex.org/W2323937687","https://openalex.org/W2095118173","https://openalex.org/W2263699433","https://openalex.org/W2104269053"],"abstract_inverted_index":{"INTRODUCTION:":[0],"The":[1],"German":[2,168],"Medical":[3],"Text":[4,124],"Project":[5],"(GeMTeX)":[6],"is":[7],"one":[8],"of":[9,23,27,35,71,80,106,117,143],"the":[10,21,24,33,40,45,48,62,77,102,107,119,164],"largest":[11],"infrastructure":[12],"efforts":[13],"targeting":[14],"German-language":[15],"clinical":[16,37,169],"documents.":[17],"We":[18],"here":[19],"introduce":[20],"architecture":[22],"de-identification":[25],"pipeline":[26,31],"GeMTeX.":[28],"METHODS:":[29],"This":[30,86],"comprises":[32],"export":[34],"raw":[36],"documents":[38],"from":[39],"local":[41],"hospital":[42],"information":[43,58],"system,":[44],"import":[46],"into":[47],"annotation":[49,135],"platform":[50],"INCEpTION,":[51],"fully":[52],"automatic":[53,78],"pre-tagging":[54],"with":[55,83,130,173],"protected":[56],"health":[57],"(PHI)":[59],"items":[60,82],"by":[61],"Averbis":[63],"Health":[64],"Discovery":[65],"pipeline,":[66],"a":[67,91,115],"manual":[68],"curation":[69],"step":[70],"these":[72],"pre-annotated":[73],"data,":[74],"and,":[75],"finally,":[76],"replacement":[79],"PHI":[81,131,156,174],"type-conformant":[84],"substitutes.":[85],"design":[87],"was":[88,128],"implemented":[89],"in":[90,133],"pilot":[92],"study":[93],"involving":[94],"six":[95],"annotators":[96],"and":[97,111],"two":[98],"curators":[99],"each":[100],"at":[101],"Data":[103],"Integration":[104],"Centers":[105],"University":[108],"Hospitals":[109],"Leipzig":[110],"Erlangen.":[112],"RESULTS:":[113],"As":[114],"proof":[116],"concept,":[118],"publicly":[120,166],"available":[121,167],"Graz":[122],"Synthetic":[123],"Clinical":[125],"Corpus":[126],"(GRASSCO)":[127],"enhanced":[129],"annotations":[132,157],"an":[134],"campaign":[136],"for":[137],"which":[138],"reasonable":[139],"inter-annotator":[140],"agreement":[141],"values":[142],"Krippendorff's":[144],"\u03b1":[145],"\u2248":[146],"0.97":[147],"can":[148],"be":[149],"reported.":[150],"CONCLUSION:":[151],"These":[152],"curated":[153],"1.4":[154],"K":[155],"are":[158],"released":[159],"as":[160],"open-source":[161],"data":[162],"constituting":[163],"first":[165],"language":[170],"text":[171],"corpus":[172],"metadata.":[175]},"counts_by_year":[],"updated_date":"2026-04-29T09:16:38.111599","created_date":"2025-10-10T00:00:00"}
