{"id":"https://openalex.org/W2991314401","doi":"https://doi.org/10.3233/shti190212","title":"Annotating German Clinical Documents for De-Identification","display_name":"Annotating German Clinical Documents for De-Identification","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2991314401","doi":"https://doi.org/10.3233/shti190212","mag":"2991314401","pmid":"https://pubmed.ncbi.nlm.nih.gov/31437914"},"language":"en","primary_location":{"id":"doi:10.3233/shti190212","is_oa":true,"landing_page_url":"https://doi.org/10.3233/shti190212","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":"https://doi.org/10.3233/shti190212","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5007387434","display_name":"Tobias Kolditz","orcid":null},"institutions":[{"id":"https://openalex.org/I76198965","display_name":"Friedrich Schiller University Jena","ror":"https://ror.org/05qpz1x62","country_code":"DE","type":"education","lineage":["https://openalex.org/I76198965"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Kolditz Tobias","raw_affiliation_strings":["Jena University Language & Information Engineering (JULIE) Lab, Friedrich Schiller University Jena, Jena, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Jena University Language & Information Engineering (JULIE) Lab, Friedrich Schiller University Jena, Jena, Germany","institution_ids":["https://openalex.org/I76198965"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042587817","display_name":"Christina Lohr","orcid":"https://orcid.org/0000-0001-9889-162X"},"institutions":[{"id":"https://openalex.org/I76198965","display_name":"Friedrich Schiller University Jena","ror":"https://ror.org/05qpz1x62","country_code":"DE","type":"education","lineage":["https://openalex.org/I76198965"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Lohr Christina","raw_affiliation_strings":["Jena University Language & Information Engineering (JULIE) Lab, Friedrich Schiller University Jena, Jena, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Jena University Language & Information Engineering (JULIE) Lab, Friedrich Schiller University Jena, Jena, Germany","institution_ids":["https://openalex.org/I76198965"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041627156","display_name":"Johannes Hellrich","orcid":null},"institutions":[{"id":"https://openalex.org/I76198965","display_name":"Friedrich Schiller University Jena","ror":"https://ror.org/05qpz1x62","country_code":"DE","type":"education","lineage":["https://openalex.org/I76198965"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Hellrich Johannes","raw_affiliation_strings":["Jena University Language & Information Engineering (JULIE) Lab, Friedrich Schiller University Jena, Jena, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Jena University Language & Information Engineering (JULIE) Lab, Friedrich Schiller University Jena, Jena, Germany","institution_ids":["https://openalex.org/I76198965"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029707385","display_name":"Luise Modersohn","orcid":"https://orcid.org/0000-0002-8258-4366"},"institutions":[{"id":"https://openalex.org/I76198965","display_name":"Friedrich Schiller University Jena","ror":"https://ror.org/05qpz1x62","country_code":"DE","type":"education","lineage":["https://openalex.org/I76198965"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Modersohn Luise","raw_affiliation_strings":["Jena University Language & Information Engineering (JULIE) Lab, Friedrich Schiller University Jena, Jena, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Jena University Language & Information Engineering (JULIE) Lab, Friedrich Schiller University Jena, Jena, Germany","institution_ids":["https://openalex.org/I76198965"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066848465","display_name":"Boris Betz","orcid":"https://orcid.org/0009-0001-1888-6546"},"institutions":[{"id":"https://openalex.org/I4210134900","display_name":"Jena University Hospital","ror":"https://ror.org/035rzkx15","country_code":"DE","type":"healthcare","lineage":["https://openalex.org/I4210134900"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Betz Boris","raw_affiliation_strings":["Institute of Clinical Chemistry and Laboratory Diagnostics, Jena University Hospital, Jena, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Clinical Chemistry and Laboratory Diagnostics, Jena University Hospital, Jena, Germany","institution_ids":["https://openalex.org/I4210134900"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076530707","display_name":"Michael Kiehntopf","orcid":null},"institutions":[{"id":"https://openalex.org/I4210134900","display_name":"Jena University Hospital","ror":"https://ror.org/035rzkx15","country_code":"DE","type":"healthcare","lineage":["https://openalex.org/I4210134900"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Kiehntopf Michael","raw_affiliation_strings":["Institute of Clinical Chemistry and Laboratory Diagnostics, Jena University Hospital, Jena, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Clinical Chemistry and Laboratory Diagnostics, Jena University Hospital, Jena, Germany","institution_ids":["https://openalex.org/I4210134900"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044841280","display_name":"Udo Hahn","orcid":"https://orcid.org/0000-0002-5052-0245"},"institutions":[{"id":"https://openalex.org/I76198965","display_name":"Friedrich Schiller University Jena","ror":"https://ror.org/05qpz1x62","country_code":"DE","type":"education","lineage":["https://openalex.org/I76198965"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Hahn Udo","raw_affiliation_strings":["Jena University Language & Information Engineering (JULIE) Lab, Friedrich Schiller University Jena, Jena, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Jena University Language & Information Engineering (JULIE) Lab, Friedrich Schiller University Jena, Jena, Germany","institution_ids":["https://openalex.org/I76198965"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.204,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.90857971,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"264","issue":null,"first_page":"203","last_page":"207"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9722999930381775,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9722999930381775,"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/T12790","display_name":"Nursing Diagnosis and Documentation","score":0.9140999913215637,"subfield":{"id":"https://openalex.org/subfields/2910","display_name":"Issues, ethics and legal aspects"},"field":{"id":"https://openalex.org/fields/29","display_name":"Nursing"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9039000272750854,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.912686824798584},{"id":"https://openalex.org/keywords/german","display_name":"German","score":0.7528521418571472},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7204060554504395},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.6978880763053894},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.6749834418296814},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6449871063232422},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5531927347183228},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.4903535842895508},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.4698951244354248},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3916338384151459},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.33578675985336304},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1176115870475769}],"concepts":[{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.912686824798584},{"id":"https://openalex.org/C154775046","wikidata":"https://www.wikidata.org/wiki/Q188","display_name":"German","level":2,"score":0.7528521418571472},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7204060554504395},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.6978880763053894},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.6749834418296814},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6449871063232422},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5531927347183228},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.4903535842895508},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.4698951244354248},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3916338384151459},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.33578675985336304},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1176115870475769},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"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/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000068240","descriptor_name":"Data Anonymization","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000068240","descriptor_name":"Data Anonymization","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000068240","descriptor_name":"Data Anonymization","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":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":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","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}],"locations_count":2,"locations":[{"id":"doi:10.3233/shti190212","is_oa":true,"landing_page_url":"https://doi.org/10.3233/shti190212","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:31437914","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/31437914","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}],"best_oa_location":{"id":"doi:10.3233/shti190212","is_oa":true,"landing_page_url":"https://doi.org/10.3233/shti190212","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2315527029","https://openalex.org/W2361861616","https://openalex.org/W2065387230","https://openalex.org/W2323937687","https://openalex.org/W2263699433","https://openalex.org/W2377979023","https://openalex.org/W648995381","https://openalex.org/W3033791384","https://openalex.org/W2141885522","https://openalex.org/W2776312268"],"abstract_inverted_index":{"We":[0],"devised":[1],"annotation":[2,35,55],"guidelines":[3],"for":[4,64],"the":[5,45,51],"de-identification":[6,66],"of":[7,15,42,54],"German":[8],"clinical":[9],"documents":[10],"and":[11,19,48,77],"assembled":[12],"a":[13,62,72],"corpus":[14],"1,106":[16],"discharge":[17],"summaries":[18],"transfer":[20],"letters":[21],"with":[22],"44K":[23],"annotated":[24],"protected":[25],"health":[26],"information":[27],"(PHI)":[28],"items.":[29],"After":[30],"three":[31],"iteration":[32],"rounds,":[33],"our":[34,68],"team":[36],"finally":[37],"reached":[38],"an":[39],"inter-annotator":[40],"agreement":[41],"0.96":[43],"on":[44,50,67,84],"instance":[46],"level":[47,53],"0.97":[49],"token":[52],"(averaged":[56],"pair-wise":[57],"F1":[58,79],"score).":[59],"To":[60],"establish":[61],"baseline":[63],"automatic":[65],"corpus,":[69],"we":[70],"trained":[71],"recurrent":[73],"neural":[74],"network":[75],"(RNN)":[76],"achieved":[78],"scores":[80],"greater":[81],"than":[82],"0.9":[83],"most":[85],"major":[86],"PHI":[87],"categories.":[88]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
