{"id":"https://openalex.org/W2894037224","doi":"https://doi.org/10.3233/978-1-61499-896-9-165","title":"De-Identification of German Medical Admission Notes","display_name":"De-Identification of German Medical Admission Notes","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W2894037224","doi":"https://doi.org/10.3233/978-1-61499-896-9-165","mag":"2894037224","pmid":"https://pubmed.ncbi.nlm.nih.gov/30147065"},"language":"en","primary_location":{"id":"doi:10.3233/978-1-61499-896-9-165","is_oa":false,"landing_page_url":"https://doi.org/10.3233/978-1-61499-896-9-165","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":null,"license_id":null,"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":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5085813595","display_name":"Phillip Richter-Pechanski","orcid":"https://orcid.org/0000-0003-0121-373X"},"institutions":[{"id":"https://openalex.org/I223822909","display_name":"Heidelberg University","ror":"https://ror.org/038t36y30","country_code":"DE","type":"education","lineage":["https://openalex.org/I223822909"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Richter-Pechanski Phillip","raw_affiliation_strings":["Department of Computational Linguistics, University of Heidelberg, Heidelberg, Germany"],"affiliations":[{"raw_affiliation_string":"Department of Computational Linguistics, University of Heidelberg, Heidelberg, Germany","institution_ids":["https://openalex.org/I223822909"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011749347","display_name":"Stefan Riezler","orcid":null},"institutions":[{"id":"https://openalex.org/I223822909","display_name":"Heidelberg University","ror":"https://ror.org/038t36y30","country_code":"DE","type":"education","lineage":["https://openalex.org/I223822909"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Riezler Stefan","raw_affiliation_strings":["Department of Computational Linguistics, University of Heidelberg, Heidelberg, Germany"],"affiliations":[{"raw_affiliation_string":"Department of Computational Linguistics, University of Heidelberg, Heidelberg, Germany","institution_ids":["https://openalex.org/I223822909"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083154676","display_name":"Christoph Dieterich","orcid":"https://orcid.org/0000-0001-9468-6311"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dieterich Christoph","raw_affiliation_strings":["Section of Bioinformatics and Systems Cardiology, Klaus Tschira Institute for Integrative Computational Cardiology and Department of Internal Medicine III, University Hospital Heidelberg, German Center for Cardiovascular Research (DZHK) - Partner site Heidelberg/Mannheim"],"affiliations":[{"raw_affiliation_string":"Section of Bioinformatics and Systems Cardiology, Klaus Tschira Institute for Integrative Computational Cardiology and Department of Internal Medicine III, University Hospital Heidelberg, German Center for Cardiovascular Research (DZHK) - Partner site Heidelberg/Mannheim","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5085813595"],"corresponding_institution_ids":["https://openalex.org/I223822909"],"apc_list":null,"apc_paid":null,"fwci":1.8014,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.88647914,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"253","issue":null,"first_page":"165","last_page":"169"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9962999820709229,"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":0.9898999929428101,"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/computer-science","display_name":"Computer science","score":0.7677565217018127},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.7597259283065796},{"id":"https://openalex.org/keywords/spelling","display_name":"Spelling","score":0.7526592016220093},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6279267072677612},{"id":"https://openalex.org/keywords/german","display_name":"German","score":0.5972223281860352},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5827955007553101},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5034562945365906},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.45661821961402893},{"id":"https://openalex.org/keywords/named-entity-recognition","display_name":"Named-entity recognition","score":0.45463863015174866},{"id":"https://openalex.org/keywords/levenshtein-distance","display_name":"Levenshtein distance","score":0.4502054750919342},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1575765311717987}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7677565217018127},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.7597259283065796},{"id":"https://openalex.org/C2777801307","wikidata":"https://www.wikidata.org/wiki/Q2088390","display_name":"Spelling","level":2,"score":0.7526592016220093},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6279267072677612},{"id":"https://openalex.org/C154775046","wikidata":"https://www.wikidata.org/wiki/Q188","display_name":"German","level":2,"score":0.5972223281860352},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5827955007553101},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5034562945365906},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.45661821961402893},{"id":"https://openalex.org/C2779135771","wikidata":"https://www.wikidata.org/wiki/Q403574","display_name":"Named-entity recognition","level":3,"score":0.45463863015174866},{"id":"https://openalex.org/C2777515626","wikidata":"https://www.wikidata.org/wiki/Q496939","display_name":"Levenshtein distance","level":2,"score":0.4502054750919342},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1575765311717987},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","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":"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":"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":"D010343","descriptor_name":"Patient Admission","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D010343","descriptor_name":"Patient Admission","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D010343","descriptor_name":"Patient Admission","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":2,"locations":[{"id":"doi:10.3233/978-1-61499-896-9-165","is_oa":false,"landing_page_url":"https://doi.org/10.3233/978-1-61499-896-9-165","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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Studies in Health Technology and Informatics","raw_type":"book-chapter"},{"id":"pmid:30147065","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/30147065","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":null,"sustainable_development_goals":[{"score":0.800000011920929,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W202361227","https://openalex.org/W1034374084","https://openalex.org/W1262131959","https://openalex.org/W2128004504","https://openalex.org/W2156061936","https://openalex.org/W2158645702","https://openalex.org/W2251316980","https://openalex.org/W2538585973","https://openalex.org/W2621075239","https://openalex.org/W2787702162"],"related_works":["https://openalex.org/W2100947578","https://openalex.org/W2161008081","https://openalex.org/W1555832326","https://openalex.org/W4298186509","https://openalex.org/W2556702969","https://openalex.org/W217221262","https://openalex.org/W611030372","https://openalex.org/W1974418053","https://openalex.org/W2983934248","https://openalex.org/W1605730749"],"abstract_inverted_index":{"Medical":[0],"texts":[1,17,19,81],"are":[2],"a":[3,29,36,48,67,93,111,132],"vast":[4],"resource":[5],"for":[6,38,127,135],"medical":[7,18,40,80,140],"and":[8,43,62,89,117,143,151],"computational":[9],"research.":[10],"In":[11],"contrast":[12],"to":[13,21,28,103,107,125],"newswire":[14],"or":[15],"wikipedia":[16],"need":[20],"be":[22],"de-identified":[23],"before":[24],"making":[25],"them":[26],"accessible":[27],"wider":[30],"NLP":[31],"research":[32,137],"community.":[33],"We":[34],"created":[35],"prototype":[37,130],"German":[39,139],"text":[41,141],"de-identification":[42,142,160],"named":[44,94],"entity":[45,95],"recognition":[46,96],"using":[47,147],"three-step":[49],"approach.":[50],"First,":[51],"we":[52,65,91,119],"used":[53,66],"well":[54],"known":[55],"rule-based":[56],"models":[57,157],"based":[58,71,113],"on":[59,72,98,114,138],"regular":[60,115],"expressions":[61,116],"gazetteers,":[63],"second":[64],"spelling":[68,148],"variant":[69,149],"detector":[70],"Levenshtein":[73],"distance,":[74],"exploiting":[75],"the":[76,79],"fact":[77],"that":[78,146],"contain":[82],"semi-structured":[83],"headers":[84],"including":[85],"sensible":[86],"personal":[87],"data,":[88],"third":[90],"trained":[92,155],"model":[97],"out":[99,152],"of":[100,153],"domain":[101,154],"data":[102],"add":[104],"statistical":[105,156],"capabilities":[106],"our":[108],"prototype.":[109],"Using":[110],"baseline":[112],"gazetteers":[118],"could":[120,144],"improve":[121,159],"F2-score":[122],"from":[123],"78%":[124],"85%":[126],"de-identification.":[128],"Our":[129],"is":[131],"first":[133],"step":[134],"further":[136],"show":[145],"detection":[150],"can":[158],"performance":[161],"significantly.":[162]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}