{"id":"https://openalex.org/W2989759966","doi":"https://doi.org/10.3233/shti190813","title":"Deep Learning Approaches Outperform Conventional Strategies in De-Identification of German Medical Reports","display_name":"Deep Learning Approaches Outperform Conventional Strategies in De-Identification of German Medical Reports","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2989759966","doi":"https://doi.org/10.3233/shti190813","mag":"2989759966","pmid":"https://pubmed.ncbi.nlm.nih.gov/31483261"},"language":"en","primary_location":{"id":"doi:10.3233/shti190813","is_oa":true,"landing_page_url":"https://doi.org/10.3233/shti190813","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/shti190813","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"]},{"id":"https://openalex.org/I2802164966","display_name":"University Hospital Heidelberg","ror":"https://ror.org/013czdx64","country_code":"DE","type":"healthcare","lineage":["https://openalex.org/I2802164966"]},{"id":"https://openalex.org/I4210127591","display_name":"German Centre for Cardiovascular Research","ror":"https://ror.org/031t5w623","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210127591","https://openalex.org/I4405256427"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Richter-Pechanski Phillip","raw_affiliation_strings":["Department of Internal Medicine III, University Hospital Heidelberg","German Center for Cardiovascular Research (DZHK) - Partner site Heidelberg/Mannheim","Section of Bioinformatics and Systems Cardiology, Klaus Tschira Institute for Integrative Computational Cardiology, Heidelberg"],"affiliations":[{"raw_affiliation_string":"Department of Internal Medicine III, University Hospital Heidelberg","institution_ids":["https://openalex.org/I2802164966","https://openalex.org/I223822909"]},{"raw_affiliation_string":"German Center for Cardiovascular Research (DZHK) - Partner site Heidelberg/Mannheim","institution_ids":["https://openalex.org/I4210127591"]},{"raw_affiliation_string":"Section of Bioinformatics and Systems Cardiology, Klaus Tschira Institute for Integrative Computational Cardiology, Heidelberg","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Amr Ali","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"]},{"id":"https://openalex.org/I2802164966","display_name":"University Hospital Heidelberg","ror":"https://ror.org/013czdx64","country_code":"DE","type":"healthcare","lineage":["https://openalex.org/I2802164966"]},{"id":"https://openalex.org/I4210127591","display_name":"German Centre for Cardiovascular Research","ror":"https://ror.org/031t5w623","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210127591","https://openalex.org/I4405256427"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Amr Ali","raw_affiliation_strings":["Department of Internal Medicine III, University Hospital Heidelberg","German Center for Cardiovascular Research (DZHK) - Partner site Heidelberg/Mannheim"],"affiliations":[{"raw_affiliation_string":"Department of Internal Medicine III, University Hospital Heidelberg","institution_ids":["https://openalex.org/I2802164966","https://openalex.org/I223822909"]},{"raw_affiliation_string":"German Center for Cardiovascular Research (DZHK) - Partner site Heidelberg/Mannheim","institution_ids":["https://openalex.org/I4210127591"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049262839","display_name":"Hugo A. Katus","orcid":"https://orcid.org/0000-0002-2293-2314"},"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"]},{"id":"https://openalex.org/I2802164966","display_name":"University Hospital Heidelberg","ror":"https://ror.org/013czdx64","country_code":"DE","type":"healthcare","lineage":["https://openalex.org/I2802164966"]},{"id":"https://openalex.org/I4210127591","display_name":"German Centre for Cardiovascular Research","ror":"https://ror.org/031t5w623","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210127591","https://openalex.org/I4405256427"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Katus Hugo A.","raw_affiliation_strings":["Department of Internal Medicine III, University Hospital Heidelberg","German Center for Cardiovascular Research (DZHK) - Partner site Heidelberg/Mannheim"],"affiliations":[{"raw_affiliation_string":"Department of Internal Medicine III, University Hospital Heidelberg","institution_ids":["https://openalex.org/I2802164966","https://openalex.org/I223822909"]},{"raw_affiliation_string":"German Center for Cardiovascular Research (DZHK) - Partner site Heidelberg/Mannheim","institution_ids":["https://openalex.org/I4210127591"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083154676","display_name":"Christoph Dieterich","orcid":"https://orcid.org/0000-0001-9468-6311"},"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"]},{"id":"https://openalex.org/I2802164966","display_name":"University Hospital Heidelberg","ror":"https://ror.org/013czdx64","country_code":"DE","type":"healthcare","lineage":["https://openalex.org/I2802164966"]},{"id":"https://openalex.org/I4210127591","display_name":"German Centre for Cardiovascular Research","ror":"https://ror.org/031t5w623","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210127591","https://openalex.org/I4405256427"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Dieterich Christoph","raw_affiliation_strings":["Department of Internal Medicine III, University Hospital Heidelberg","German Center for Cardiovascular Research (DZHK) - Partner site Heidelberg/Mannheim","Section of Bioinformatics and Systems Cardiology, Klaus Tschira Institute for Integrative Computational Cardiology, Heidelberg"],"affiliations":[{"raw_affiliation_string":"Department of Internal Medicine III, University Hospital Heidelberg","institution_ids":["https://openalex.org/I2802164966","https://openalex.org/I223822909"]},{"raw_affiliation_string":"German Center for Cardiovascular Research (DZHK) - Partner site Heidelberg/Mannheim","institution_ids":["https://openalex.org/I4210127591"]},{"raw_affiliation_string":"Section of Bioinformatics and Systems Cardiology, Klaus Tschira Institute for Integrative Computational Cardiology, Heidelberg","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5085813595"],"corresponding_institution_ids":["https://openalex.org/I223822909","https://openalex.org/I2802164966","https://openalex.org/I4210127591"],"apc_list":null,"apc_paid":null,"fwci":3.5805,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.94749362,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"267","issue":null,"first_page":"101","last_page":"109"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9926999807357788,"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":0.9926999807357788,"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":0.9869999885559082,"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":0.9812999963760376,"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/conditional-random-field","display_name":"Conditional random field","score":0.7950570583343506},{"id":"https://openalex.org/keywords/german","display_name":"German","score":0.7704536318778992},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.759750485420227},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7512762546539307},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.7062357068061829},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7029591798782349},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4902942478656769},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.46283507347106934},{"id":"https://openalex.org/keywords/f1-score","display_name":"F1 score","score":0.4573192000389099},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.41783371567726135},{"id":"https://openalex.org/keywords/random-forest","display_name":"Random forest","score":0.41168728470802307},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.37899741530418396},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06347960233688354}],"concepts":[{"id":"https://openalex.org/C152565575","wikidata":"https://www.wikidata.org/wiki/Q1124538","display_name":"Conditional random field","level":2,"score":0.7950570583343506},{"id":"https://openalex.org/C154775046","wikidata":"https://www.wikidata.org/wiki/Q188","display_name":"German","level":2,"score":0.7704536318778992},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.759750485420227},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7512762546539307},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.7062357068061829},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7029591798782349},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4902942478656769},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.46283507347106934},{"id":"https://openalex.org/C148524875","wikidata":"https://www.wikidata.org/wiki/Q6975395","display_name":"F1 score","level":2,"score":0.4573192000389099},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.41783371567726135},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.41168728470802307},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37899741530418396},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06347960233688354},{"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},{"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/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"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":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000077321","descriptor_name":"Deep Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000077321","descriptor_name":"Deep Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000077321","descriptor_name":"Deep Learning","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":"D057286","descriptor_name":"Electronic Health Records","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":false},{"descriptor_ui":"D057286","descriptor_name":"Electronic Health Records","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.3233/shti190813","is_oa":true,"landing_page_url":"https://doi.org/10.3233/shti190813","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:31483261","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/31483261","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/shti190813","is_oa":true,"landing_page_url":"https://doi.org/10.3233/shti190813","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":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.8100000023841858}],"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/W3006655138","https://openalex.org/W3085947683","https://openalex.org/W2957763665","https://openalex.org/W4281685698","https://openalex.org/W2098332568","https://openalex.org/W3201257042","https://openalex.org/W4402437224","https://openalex.org/W2250713385","https://openalex.org/W2013112444"],"abstract_inverted_index":{"One":[0],"of":[1,14,34,42,75,106,127,176],"the":[2,12,28,62,80,135,147],"major":[3],"obstacles":[4],"for":[5,30,61,104,115,145],"research":[6],"on":[7,22,37,54,65],"German":[8,38,66,107,177],"medical":[9,16,24,39,67,77,108,178],"reports":[10,68,78],"is":[11],"lack":[13],"de-identified":[15],"corpora.":[17],"Previous":[18],"de-identification":[19,35,105,116,175],"tasks":[20],"focused":[21],"non-German":[23],"texts,":[25],"which":[26],"raised":[27],"demand":[29],"an":[31,112],"in-depth":[32],"evaluation":[33,114],"methods":[36,53,88,131,168],"texts.":[40],"Because":[41],"remarkable":[43],"advancements":[44],"in":[45,152,174],"natural":[46],"language":[47],"processing":[48],"using":[49,69,89],"supervised":[50],"machine":[51,129,166],"learning":[52,87,130,167],"limited":[55],"training":[56],"data,":[57],"we":[58],"evaluated":[59],"them":[60],"first":[63],"time":[64],"our":[70],"annotated":[71],"data":[72],"set":[73],"consisting":[74],"113":[76],"from":[79,141],"cardiology":[81],"domain.":[82],"We":[83,110],"applied":[84],"state-of-the-art":[85,165],"deep":[86],"pre-trained":[90],"models":[91],"as":[92,132],"input":[93],"to":[94,143],"a":[95,133,171],"bidirectional":[96],"LSTM":[97],"network":[98],"and":[99,117,125,158],"well-established":[100],"conditional":[101,136],"random":[102,137],"fields":[103],"reports.":[109,179],"performed":[111],"extensive":[113],"multiclass":[118],"named":[119],"entity":[120],"recognition.":[121],"Using":[122],"rule":[123],"based":[124],"out":[126],"domain":[128],"baseline,":[134],"field":[138],"improved":[139],"F2-score":[140,153],"70":[142],"93%":[144],"de-identification,":[146],"neural":[148],"approach":[149],"reached":[150],"96%":[151],"while":[154],"keeping":[155],"balanced":[156],"precision":[157],"recall":[159],"rates.":[160],"These":[161],"results":[162],"show,":[163],"that":[164],"can":[169],"play":[170],"crucial":[172],"role":[173]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":5}],"updated_date":"2026-04-16T08:26:57.006410","created_date":"2025-10-10T00:00:00"}