{"id":"https://openalex.org/W2984506903","doi":"https://doi.org/10.18653/v1/d19-6215","title":"Building a De-identification System for Real Swedish Clinical Text Using Pseudonymised Clinical Text","display_name":"Building a De-identification System for Real Swedish Clinical Text Using Pseudonymised Clinical Text","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2984506903","doi":"https://doi.org/10.18653/v1/d19-6215","mag":"2984506903"},"language":"en","primary_location":{"id":"doi:10.18653/v1/d19-6215","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d19-6215","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Tenth International Workshop on Health Text Mining and Information Analysis (LOUHI 2019)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.18653/v1/d19-6215","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5089693494","display_name":"Hanna Berg","orcid":"https://orcid.org/0000-0003-2956-1701"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hanna Berg","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069577540","display_name":"Taridzo Chomutare","orcid":"https://orcid.org/0000-0003-3603-175X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Taridzo Chomutare","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5010279607","display_name":"Hercules Dalianis","orcid":"https://orcid.org/0000-0003-0165-9926"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hercules Dalianis","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4374,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.67948287,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9993000030517578,"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":0.9993000030517578,"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":0.9958000183105469,"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":0.9944000244140625,"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":0.7494675517082214},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.678554356098175},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.6437559127807617},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.6128555536270142},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5571209192276001},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.47717490792274475},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4687977433204651},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.44940185546875},{"id":"https://openalex.org/keywords/conditional-random-field","display_name":"Conditional random field","score":0.41316425800323486}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7494675517082214},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.678554356098175},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.6437559127807617},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.6128555536270142},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5571209192276001},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.47717490792274475},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4687977433204651},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.44940185546875},{"id":"https://openalex.org/C152565575","wikidata":"https://www.wikidata.org/wiki/Q1124538","display_name":"Conditional random field","level":2,"score":0.41316425800323486},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/d19-6215","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d19-6215","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Tenth International Workshop on Health Text Mining and Information Analysis (LOUHI 2019)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/d19-6215","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d19-6215","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Tenth International Workshop on Health Text Mining and Information Analysis (LOUHI 2019)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5299999713897705}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W328371757","https://openalex.org/W1034374084","https://openalex.org/W1558796178","https://openalex.org/W1995228216","https://openalex.org/W2015620729","https://openalex.org/W2124216778","https://openalex.org/W2137377614","https://openalex.org/W2151376632","https://openalex.org/W2155863877","https://openalex.org/W2211265567","https://openalex.org/W2296283641","https://openalex.org/W2314398369","https://openalex.org/W2621075239","https://openalex.org/W2624380710","https://openalex.org/W2896284100","https://openalex.org/W2963956191","https://openalex.org/W3039774111","https://openalex.org/W3080656935"],"related_works":["https://openalex.org/W4238897586","https://openalex.org/W435179959","https://openalex.org/W2619091065","https://openalex.org/W2059640416","https://openalex.org/W1490753184","https://openalex.org/W2284465472","https://openalex.org/W2291782699","https://openalex.org/W1993948687","https://openalex.org/W2000169967","https://openalex.org/W2112883198"],"abstract_inverted_index":{"This":[0],"article":[1],"presents":[2],"experiments":[3],"with":[4,18,104],"pseudonymised":[5,54,80,85,131,147],"Swedish":[6,148],"clinical":[7,16,149],"text":[8,17],"used":[9,43],"as":[10,75,77],"training":[11,25,132],"data":[12,26,55,74,81],"to":[13,22,27,44,125,141],"de-identify":[14],"real":[15,59,68,73],"the":[19,108,126,130],"future":[20],"aim":[21],"transfer":[23],"non-sensitive":[24],"other":[28],"hospitals.":[29],"Conditional":[30],"Random":[31],"Fields":[32],"(CFR)":[33],"and":[34,56,70,82,100,116,155],"Long":[35],"Short-Term":[36],"Memory":[37],"(LSTM)":[38],"machine":[39],"learning":[40],"algorithms":[41],"were":[42,51,64,121],"train":[45,142],"de-identification":[46],"models.":[47],"The":[48],"two":[49],"models":[50,63,144],"trained":[52,66,78],"on":[53,58,67,72,79,84,114,146],"evaluated":[57,71,83],"data.":[60,86,133],"For":[61],"benchmarking,":[62],"also":[65],"data,":[69,150],"well":[76],"CRF":[87],"showed":[88],"better":[89],"performance":[90],"for":[91],"some":[92,105],"PHI":[93],"information":[94,120],"like":[95],"Date":[96],"Part,":[97],"First":[98],"Name":[99],"Last":[101],"Name;":[102],"consistent":[103],"reports":[106],"in":[107,129],"literature.":[109],"In":[110],"contrast,":[111],"poor":[112],"performances":[113],"Location":[115],"Health":[117],"Care":[118],"Unit":[119],"noted,":[122],"partially":[123],"due":[124],"constrained":[127],"vocabulary":[128],"It":[134],"is":[135,139],"concluded":[136],"that":[137],"it":[138],"possible":[140],"transferable":[143],"based":[145],"but":[151],"even":[152],"small":[153],"narrative":[154],"distributional":[156],"variation":[157],"could":[158],"negatively":[159],"impact":[160],"performance.":[161]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}