{"id":"https://openalex.org/W7081243297","doi":"https://doi.org/10.5281/zenodo.15747389","title":"GraSCCo_PII_V2 - Graz Synthetic Clinical text Corpus with PII Annotations","display_name":"GraSCCo_PII_V2 - Graz Synthetic Clinical text Corpus with PII Annotations","publication_year":2025,"publication_date":"2025-09-07","ids":{"openalex":"https://openalex.org/W7081243297","doi":"https://doi.org/10.5281/zenodo.15747389"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.15747389","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.15747389","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"dataset"},"type":"dataset","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.15747389","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Lohr, Christina","orcid":"https://orcid.org/0000-0001-9889-162X"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Lohr, Christina","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0001-9889-162X","affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Matthies, Franz","orcid":"https://orcid.org/0000-0001-7196-506X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Matthies, Franz","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0001-7196-506X","affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Jakob, Faller","orcid":"https://orcid.org/0009-0002-8875-5426"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jakob, Faller","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0009-0002-8875-5426","affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Modersohn, Luise","orcid":"https://orcid.org/0000-0002-8258-4366"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Modersohn, Luise","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-8258-4366","affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Riedel, Andrea","orcid":"https://orcid.org/0009-0006-9389-9482"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Riedel, Andrea","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0009-0006-9389-9482","affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Hahn, Udo","orcid":"https://orcid.org/0000-0002-5052-0245"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hahn, Udo","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-5052-0245","affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Boeker, Martin","orcid":"https://orcid.org/0000-0003-2972-2042"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Boeker, Martin","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0003-2972-2042","affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Meineke, Frank","orcid":"https://orcid.org/0000-0002-9256-7543"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Meineke, Frank","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-9256-7543","affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Hofenbitzer, Justin","orcid":"https://orcid.org/0009-0002-5024-5834"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hofenbitzer, Justin","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0009-0002-5024-5834","affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Bild, Raffael","orcid":"https://orcid.org/0000-0002-7398-5598"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bild, Raffael","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-7398-5598","affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Prasser, Fabian","orcid":"https://orcid.org/0000-0003-3172-3095"},"institutions":[{"id":"https://openalex.org/I4210139777","display_name":"Berlin Institute of Health at Charit\u00e9 - Universit\u00e4tsmedizin Berlin","ror":"https://ror.org/0493xsw21","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210139777","https://openalex.org/I7877124"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Prasser, Fabian","raw_affiliation_strings":["Berlin Institute of Health at Charit\u00e9 - Universit\u00e4tsmedizin Berlin"],"raw_orcid":"https://orcid.org/0000-0003-3172-3095","affiliations":[{"raw_affiliation_string":"Berlin Institute of Health at Charit\u00e9 - Universit\u00e4tsmedizin Berlin","institution_ids":["https://openalex.org/I4210139777"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Shutsko, Aliaksandra","orcid":"https://orcid.org/0000-0002-7091-5084"},"institutions":[{"id":"https://openalex.org/I4210112663","display_name":"ZB MED - Information Centre for Life Sciences","ror":"https://ror.org/0259fwx54","country_code":"DE","type":"archive","lineage":["https://openalex.org/I4210112663"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Shutsko, Aliaksandra","raw_affiliation_strings":["ZB MED - Information Centre for Life Sciences"],"raw_orcid":"https://orcid.org/0000-0002-7091-5084","affiliations":[{"raw_affiliation_string":"ZB MED - Information Centre for Life Sciences","institution_ids":["https://openalex.org/I4210112663"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Abdelmalak, Abanoub","orcid":"https://orcid.org/0009-0001-0892-3614"},"institutions":[{"id":"https://openalex.org/I4210112663","display_name":"ZB MED - Information Centre for Life Sciences","ror":"https://ror.org/0259fwx54","country_code":"DE","type":"archive","lineage":["https://openalex.org/I4210112663"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Abdelmalak, Abanoub","raw_affiliation_strings":["ZB MED - Information Centre for Life Sciences"],"raw_orcid":"https://orcid.org/0009-0001-0892-3614","affiliations":[{"raw_affiliation_string":"ZB MED - Information Centre for Life Sciences","institution_ids":["https://openalex.org/I4210112663"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Hung, Nguyen Manh","orcid":"https://orcid.org/0000-0003-1389-0076"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hung, Nguyen Manh","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0003-1389-0076","affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Dieterich, Christoph","orcid":"https://orcid.org/0000-0001-9468-6311"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dieterich, Christoph","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0001-9468-6311","affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":15,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T12157","display_name":"Geochemistry and Geologic Mapping","score":0.6565999984741211,"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/T12157","display_name":"Geochemistry and Geologic Mapping","score":0.6565999984741211,"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/T13067","display_name":"Geological Modeling and Analysis","score":0.026200000196695328,"subfield":{"id":"https://openalex.org/subfields/1906","display_name":"Geochemistry and Petrology"},"field":{"id":"https://openalex.org/fields/19","display_name":"Earth and Planetary Sciences"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T14311","display_name":"Electrical and Electromagnetic Research","score":0.019700000062584877,"subfield":{"id":"https://openalex.org/subfields/3107","display_name":"Atomic and Molecular Physics, and Optics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.7382000088691711},{"id":"https://openalex.org/keywords/german","display_name":"German","score":0.5580000281333923},{"id":"https://openalex.org/keywords/json","display_name":"JSON","score":0.536899983882904},{"id":"https://openalex.org/keywords/guideline","display_name":"Guideline","score":0.35920000076293945},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.3497999906539917},{"id":"https://openalex.org/keywords/systematized-nomenclature-of-medicine","display_name":"Systematized Nomenclature of Medicine","score":0.2766000032424927}],"concepts":[{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.7382000088691711},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5813000202178955},{"id":"https://openalex.org/C154775046","wikidata":"https://www.wikidata.org/wiki/Q188","display_name":"German","level":2,"score":0.5580000281333923},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5497999787330627},{"id":"https://openalex.org/C2780416260","wikidata":"https://www.wikidata.org/wiki/Q2063","display_name":"JSON","level":2,"score":0.536899983882904},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4846000075340271},{"id":"https://openalex.org/C2780182762","wikidata":"https://www.wikidata.org/wiki/Q1630279","display_name":"Guideline","level":2,"score":0.35920000076293945},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.3497999906539917},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.34209999442100525},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3359000086784363},{"id":"https://openalex.org/C44681071","wikidata":"https://www.wikidata.org/wiki/Q4048820","display_name":"Systematized Nomenclature of Medicine","level":4,"score":0.2766000032424927},{"id":"https://openalex.org/C206497026","wikidata":"https://www.wikidata.org/wiki/Q1753883","display_name":"SNOMED CT","level":3,"score":0.27619999647140503},{"id":"https://openalex.org/C2779473830","wikidata":"https://www.wikidata.org/wiki/Q1540899","display_name":"MEDLINE","level":2,"score":0.27079999446868896},{"id":"https://openalex.org/C145642194","wikidata":"https://www.wikidata.org/wiki/Q870895","display_name":"Health informatics","level":3,"score":0.2531999945640564},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.25220000743865967}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5281/zenodo.15747389","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.15747389","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"dataset"}],"best_oa_location":{"id":"doi:10.5281/zenodo.15747389","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.15747389","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"dataset"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"GraSCCo_PII_V2":[0],"-":[1,128,146,169],"Graz":[2],"Synthetic":[3],"Clinical":[4,135],"text":[5],"Corpus":[6],"with":[7,148,202],"Personally":[8],"Identifiable":[9],"Informations":[10],"Additional":[11],"source":[12,157],"of:":[13],"Lohr":[14,123,159],"C,":[15,43,124,160],"Faller":[16,163],"J,":[17,25,29,33,49,164],"Riedel":[18],"A,":[19],"Nguyen":[20],"HM,":[21],"Wolfien":[22],"M,":[23,41,51,53],"Hofenbitzer":[24],"Modersohn":[26,119],"L,":[27,120],"Romberg":[28],"Prasser":[30],"F,":[31,47,162],"Omeirat":[32],"Wen":[34],"Y,":[35],"Galusch":[36],"O,":[37],"Hahn":[38,125],"U,":[39],"Seiferling":[40],"Dieterich":[42],"Kl\u00fcgl":[44],"P,":[45],"Matthies":[46,161],"Kind":[48],"Boeker":[50],"L\u00f6ffler":[52],"Meineke":[54],"F.":[55],"GeMTeX's":[56],"De-Identification":[57,175],"in":[58,196,219],"Action:":[59],"Lessons":[60],"Learned":[61],"&":[62],"Devil's":[63],"Details.":[64],"Stud":[65,138,184],"Health":[66,139,185],"Technol":[67,140,186],"Inform.":[68,141,187],"2025":[69],"Sep":[70],"3;331:274-282.":[71],"doi:":[72],"10.3233/SHTI251406.":[73],"PMID:":[74],"40899551.":[75],"(https://pubmed.ncbi.nlm.nih.gov/40899551/)":[76],"GraSCCo":[77,112],"is":[78],"a":[79],"collection":[80],"of":[81,158,176],"artificially":[82],"generated":[83],"semi-structured":[84],"and":[85,198,214],"unstructured":[86],"German-language":[87],"clinical":[88],"summaries.":[89],"These":[90],"summaries":[91],"are":[92],"formulated":[93],"as":[94,152,155],"letters":[95],"from":[96],"the":[97,100,174,177,194,203,209],"hospital":[98],"to":[99],"patient's":[101],"GP":[102],"after":[103],"in-patient":[104],"or":[105],"out-patient":[106],"care.":[107],"Details:":[108],"Stefan":[109],"Schulz.":[110],"(2022).":[111],"(Version":[113],"v1)":[114],"[Data":[115],"set].":[116],"Zenodo.":[117],"https://doi.org/10.5281/zenodo.6539131":[118],"Schulz":[121],"S,":[122],"U.":[126],"GRASCCO":[127,168],"The":[129],"First":[130,144],"Publicly":[131],"Shareable,":[132],"Multiply-Alienated":[133],"German":[134,178],"Text":[136,180],"Corpus.":[137,183],"2022;296:66-72.":[142],"doi:10.3233/SHTI220805":[143],"Version":[145],"GraSSCo":[147],"PHI":[149],"(now":[150],"named":[151],"PII)":[153],"annotations":[154,195],"external":[156],"et":[165],"al.":[166],"De-Identifying":[167],"A":[170],"Pilot":[171],"Study":[172],"for":[173,217],"Medical":[179],"Project":[181],"(GeMTeX)":[182],"2024;317:171-179.":[188],"doi:10.3233/SHTI240853":[189],"(https://pubmed.ncbi.nlm.nih.gov/39234720/)":[190],"This":[191],"repository":[192],"contains":[193],"XMI":[197],"JSON":[199],"exports":[200],"created":[201],"INCEpTION":[204],"annotation":[205,210],"platform":[206],"(https://inception-project.github.io/),":[207],"also":[208,222],"guideline":[211],"document,":[212],"TypeSystem.xml":[213],"layer.json":[215],"(needed":[216],"import":[218],"INCEpTION),":[220],"see":[221],"https://github.com/dkpro/dkpro-cassis.":[223]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}