{"id":"https://openalex.org/W4401379682","doi":"https://doi.org/10.3390/fi16080281","title":"Masketeer: An Ensemble-Based Pseudonymization Tool with Entity Recognition for German Unstructured Medical Free Text","display_name":"Masketeer: An Ensemble-Based Pseudonymization Tool with Entity Recognition for German Unstructured Medical Free Text","publication_year":2024,"publication_date":"2024-08-06","ids":{"openalex":"https://openalex.org/W4401379682","doi":"https://doi.org/10.3390/fi16080281"},"language":"en","primary_location":{"id":"doi:10.3390/fi16080281","is_oa":true,"landing_page_url":"https://doi.org/10.3390/fi16080281","pdf_url":"https://www.mdpi.com/1999-5903/16/8/281/pdf?version=1722934188","source":{"id":"https://openalex.org/S34838331","display_name":"Future Internet","issn_l":"1999-5903","issn":["1999-5903"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Future Internet","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/1999-5903/16/8/281/pdf?version=1722934188","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5080982101","display_name":"Martin Baumgartner","orcid":"https://orcid.org/0000-0002-6731-6873"},"institutions":[{"id":"https://openalex.org/I132118926","display_name":"Austrian Institute of Technology","ror":"https://ror.org/04knbh022","country_code":"AT","type":"facility","lineage":["https://openalex.org/I132118926"]},{"id":"https://openalex.org/I4092182","display_name":"Graz University of Technology","ror":"https://ror.org/00d7xrm67","country_code":"AT","type":"education","lineage":["https://openalex.org/I4092182"]}],"countries":["AT"],"is_corresponding":true,"raw_author_name":"Martin Baumgartner","raw_affiliation_strings":["Center for Health and Bioresources, AIT Austrian Institute of Technology, 8020 Graz, Austria","Institute of Neural Engineering, Graz University of Technology, 8010 Graz, Austria"],"affiliations":[{"raw_affiliation_string":"Center for Health and Bioresources, AIT Austrian Institute of Technology, 8020 Graz, Austria","institution_ids":["https://openalex.org/I132118926"]},{"raw_affiliation_string":"Institute of Neural Engineering, Graz University of Technology, 8010 Graz, Austria","institution_ids":["https://openalex.org/I4092182"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030072403","display_name":"Karl Kreiner","orcid":"https://orcid.org/0000-0001-6066-9708"},"institutions":[{"id":"https://openalex.org/I132118926","display_name":"Austrian Institute of Technology","ror":"https://ror.org/04knbh022","country_code":"AT","type":"facility","lineage":["https://openalex.org/I132118926"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Karl Kreiner","raw_affiliation_strings":["Center for Health and Bioresources, AIT Austrian Institute of Technology, 8020 Graz, Austria"],"affiliations":[{"raw_affiliation_string":"Center for Health and Bioresources, AIT Austrian Institute of Technology, 8020 Graz, Austria","institution_ids":["https://openalex.org/I132118926"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069821903","display_name":"Fabian Wiesm\u00fcller","orcid":"https://orcid.org/0000-0001-6567-7782"},"institutions":[{"id":"https://openalex.org/I132118926","display_name":"Austrian Institute of Technology","ror":"https://ror.org/04knbh022","country_code":"AT","type":"facility","lineage":["https://openalex.org/I132118926"]},{"id":"https://openalex.org/I4092182","display_name":"Graz University of Technology","ror":"https://ror.org/00d7xrm67","country_code":"AT","type":"education","lineage":["https://openalex.org/I4092182"]},{"id":"https://openalex.org/I4210104219","display_name":"Austrian Institute for Health Technology Assessment GmbH","ror":"https://ror.org/00v16df20","country_code":"AT","type":"nonprofit","lineage":["https://openalex.org/I4210104219"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Fabian Wiesm\u00fcller","raw_affiliation_strings":["Center for Health and Bioresources, AIT Austrian Institute of Technology, 8020 Graz, Austria","Institute of Neural Engineering, Graz University of Technology, 8010 Graz, Austria","Ludwig Boltzmann Institute for Digital Health and Prevention, 5020 Salzburg, Austria"],"affiliations":[{"raw_affiliation_string":"Center for Health and Bioresources, AIT Austrian Institute of Technology, 8020 Graz, Austria","institution_ids":["https://openalex.org/I132118926"]},{"raw_affiliation_string":"Institute of Neural Engineering, Graz University of Technology, 8010 Graz, Austria","institution_ids":["https://openalex.org/I4092182"]},{"raw_affiliation_string":"Ludwig Boltzmann Institute for Digital Health and Prevention, 5020 Salzburg, Austria","institution_ids":["https://openalex.org/I4210104219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066839719","display_name":"Dieter Hayn","orcid":"https://orcid.org/0000-0003-1822-9033"},"institutions":[{"id":"https://openalex.org/I132118926","display_name":"Austrian Institute of Technology","ror":"https://ror.org/04knbh022","country_code":"AT","type":"facility","lineage":["https://openalex.org/I132118926"]},{"id":"https://openalex.org/I4210104219","display_name":"Austrian Institute for Health Technology Assessment GmbH","ror":"https://ror.org/00v16df20","country_code":"AT","type":"nonprofit","lineage":["https://openalex.org/I4210104219"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Dieter Hayn","raw_affiliation_strings":["Center for Health and Bioresources, AIT Austrian Institute of Technology, 8020 Graz, Austria","Ludwig Boltzmann Institute for Digital Health and Prevention, 5020 Salzburg, Austria"],"affiliations":[{"raw_affiliation_string":"Center for Health and Bioresources, AIT Austrian Institute of Technology, 8020 Graz, Austria","institution_ids":["https://openalex.org/I132118926"]},{"raw_affiliation_string":"Ludwig Boltzmann Institute for Digital Health and Prevention, 5020 Salzburg, Austria","institution_ids":["https://openalex.org/I4210104219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010633320","display_name":"Christian Puelacher","orcid":"https://orcid.org/0000-0003-3206-6349"},"institutions":[{"id":"https://openalex.org/I143397708","display_name":"Innsbruck Medical University","ror":"https://ror.org/03pt86f80","country_code":"AT","type":"education","lineage":["https://openalex.org/I143397708"]},{"id":"https://openalex.org/I4210162546","display_name":"University Hospital Innsbruck","ror":"https://ror.org/05wjv2104","country_code":"AT","type":"healthcare","lineage":["https://openalex.org/I4210162546"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Christian Puelacher","raw_affiliation_strings":["Department of Internal Medicine III, Cardiology and Angiology, University Hospital Innsbruck, Medical University Innsbruck, 6020 Innsbruck, Austria"],"affiliations":[{"raw_affiliation_string":"Department of Internal Medicine III, Cardiology and Angiology, University Hospital Innsbruck, Medical University Innsbruck, 6020 Innsbruck, Austria","institution_ids":["https://openalex.org/I4210162546","https://openalex.org/I143397708"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007533806","display_name":"G. Schreier","orcid":"https://orcid.org/0000-0003-3724-4255"},"institutions":[{"id":"https://openalex.org/I132118926","display_name":"Austrian Institute of Technology","ror":"https://ror.org/04knbh022","country_code":"AT","type":"facility","lineage":["https://openalex.org/I132118926"]},{"id":"https://openalex.org/I4092182","display_name":"Graz University of Technology","ror":"https://ror.org/00d7xrm67","country_code":"AT","type":"education","lineage":["https://openalex.org/I4092182"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"G\u00fcnter Schreier","raw_affiliation_strings":["Center for Health and Bioresources, AIT Austrian Institute of Technology, 8020 Graz, Austria","Institute of Neural Engineering, Graz University of Technology, 8010 Graz, Austria"],"affiliations":[{"raw_affiliation_string":"Center for Health and Bioresources, AIT Austrian Institute of Technology, 8020 Graz, Austria","institution_ids":["https://openalex.org/I132118926"]},{"raw_affiliation_string":"Institute of Neural Engineering, Graz University of Technology, 8010 Graz, Austria","institution_ids":["https://openalex.org/I4092182"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5080982101"],"corresponding_institution_ids":["https://openalex.org/I132118926","https://openalex.org/I4092182"],"apc_list":{"value":1400,"currency":"CHF","value_usd":1515},"apc_paid":{"value":1400,"currency":"CHF","value_usd":1515},"fwci":1.3759,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.83995819,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":"16","issue":"8","first_page":"281","last_page":"281"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9968000054359436,"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":0.9968000054359436,"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/T13629","display_name":"Text Readability and Simplification","score":0.9957000017166138,"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":0.9955000281333923,"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":0.9213619828224182},{"id":"https://openalex.org/keywords/german","display_name":"German","score":0.6542169451713562},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5115357637405396},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5000159740447998},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3590136170387268},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.06081509590148926}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9213619828224182},{"id":"https://openalex.org/C154775046","wikidata":"https://www.wikidata.org/wiki/Q188","display_name":"German","level":2,"score":0.6542169451713562},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5115357637405396},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5000159740447998},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3590136170387268},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.06081509590148926},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.3390/fi16080281","is_oa":true,"landing_page_url":"https://doi.org/10.3390/fi16080281","pdf_url":"https://www.mdpi.com/1999-5903/16/8/281/pdf?version=1722934188","source":{"id":"https://openalex.org/S34838331","display_name":"Future Internet","issn_l":"1999-5903","issn":["1999-5903"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Future Internet","raw_type":"journal-article"},{"id":"pmh:oai:RePEc:gam:jftint:v:16:y:2024:i:8:p:281-:d:1450823","is_oa":false,"landing_page_url":"https://www.mdpi.com/1999-5903/16/8/281/","pdf_url":null,"source":{"id":"https://openalex.org/S4306401271","display_name":"RePEc: Research Papers in Economics","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I77793887","host_organization_name":"Federal Reserve Bank of St. Louis","host_organization_lineage":["https://openalex.org/I77793887"],"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"},{"id":"pmh:oai:doaj.org/article:4106c93784784af5af91dd18292ff231","is_oa":true,"landing_page_url":"https://doaj.org/article/4106c93784784af5af91dd18292ff231","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Future Internet, Vol 16, Iss 8, p 281 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3390/fi16080281","is_oa":true,"landing_page_url":"https://doi.org/10.3390/fi16080281","pdf_url":"https://www.mdpi.com/1999-5903/16/8/281/pdf?version=1722934188","source":{"id":"https://openalex.org/S34838331","display_name":"Future Internet","issn_l":"1999-5903","issn":["1999-5903"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Future Internet","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6700000166893005}],"awards":[],"funders":[{"id":"https://openalex.org/F4320326164","display_name":"Medizinische Universit\u00e4t Innsbruck","ror":"https://ror.org/03pt86f80"},{"id":"https://openalex.org/F4320327491","display_name":"Universit\u00e4t Innsbruck","ror":"https://ror.org/054pv6659"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4401379682.pdf"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W862773120","https://openalex.org/W1856966722","https://openalex.org/W2015620729","https://openalex.org/W2028231943","https://openalex.org/W2174900611","https://openalex.org/W2559662148","https://openalex.org/W2744160972","https://openalex.org/W2800915472","https://openalex.org/W2894037224","https://openalex.org/W2948647869","https://openalex.org/W2970511757","https://openalex.org/W2984506903","https://openalex.org/W2989759966","https://openalex.org/W2991314401","https://openalex.org/W3017330637","https://openalex.org/W3023341615","https://openalex.org/W3087011118","https://openalex.org/W4234664880","https://openalex.org/W4280635059","https://openalex.org/W4365514966","https://openalex.org/W4383223222","https://openalex.org/W4386576849","https://openalex.org/W4389518173","https://openalex.org/W4392148687","https://openalex.org/W6623860439","https://openalex.org/W6638832512","https://openalex.org/W6770338987","https://openalex.org/W6838982192","https://openalex.org/W6859008605"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2315527029","https://openalex.org/W2065387230","https://openalex.org/W2323937687","https://openalex.org/W648995381","https://openalex.org/W3033791384","https://openalex.org/W2141885522","https://openalex.org/W2776312268","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Background:":[0],"The":[1,106],"recent":[2],"rise":[3],"of":[4,67,112,116,175],"large":[5,138,164],"language":[6,139,165],"models":[7,140,166],"has":[8],"triggered":[9],"renewed":[10],"interest":[11],"in":[12,82],"medical":[13,26,42,60,147],"free":[14,27,43,148],"text":[15,28,44,129,149],"data,":[16],"which":[17],"holds":[18],"critical":[19],"information":[20],"about":[21],"patients":[22],"and":[23,102,114,131,152],"diseases.":[24],"However,":[25,157],"is":[29,35,39,45],"also":[30],"highly":[31],"sensitive.":[32],"Therefore,":[33],"de-identification":[34,160],"typically":[36],"required":[37],"but":[38],"complicated":[40],"since":[41],"mostly":[46],"unstructured.":[47],"With":[48],"the":[49,85,136,172],"Masketeer":[50],"algorithm,":[51],"we":[52,96,177],"present":[53],"an":[54,65,98],"effective":[55],"tool":[56],"to":[57,71,74,145,169,179],"de-identify":[58,146],"German":[59],"text.":[61],"Methods:":[62],"We":[63],"used":[64],"ensemble":[66],"different":[68],"masking":[69],"classes":[70],"remove":[72],"references":[73],"identifiable":[75],"data":[76],"from":[77],"over":[78],"35,000":[79],"clinical":[80],"notes":[81],"accordance":[83],"with":[84,109,126,189],"HIPAA":[86],"Safe":[87],"Harbor":[88],"Guidelines.":[89],"To":[90],"retain":[91],"additional":[92],"context":[93],"for":[94,183],"readers,":[95],"implemented":[97],"entity":[99],"recognition":[100],"scheme":[101],"corpus-wide":[103],"pseudonymization.":[104],"Results:":[105],"algorithm":[107,187],"performed":[108],"a":[110,184],"sensitivity":[111],"0.943":[113],"specificity":[115],"0.933.":[117],"Further":[118],"performance":[119],"analyses":[120],"showed":[121],"linear":[122],"runtime":[123],"complexity":[124],"(O(n))":[125],"both":[127],"increasing":[128],"length":[130],"corpus":[132],"size.":[133],"Conclusions:":[134],"In":[135,171],"future,":[137],"will":[141],"likely":[142],"be":[143],"able":[144],"more":[150],"effectively":[151],"thoroughly":[153],"than":[154],"handcrafted":[155],"rules.":[156],"such":[158],"gold-standard":[159],"tools":[161],"based":[162],"on":[163],"are":[167],"yet":[168],"emerge.":[170],"current":[173],"absence":[174],"such,":[176],"hope":[178],"provide":[180],"best":[181],"practices":[182],"robust":[185],"rule-based":[186],"designed":[188],"expert":[190],"domain":[191],"knowledge.":[192]},"counts_by_year":[{"year":2025,"cited_by_count":4}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}