{"id":"https://openalex.org/W4410447908","doi":"https://doi.org/10.3233/shti250469","title":"German Medical NER with BERT and LLMs: The Impact of Training Data Size","display_name":"German Medical NER with BERT and LLMs: The Impact of Training Data Size","publication_year":2025,"publication_date":"2025-05-15","ids":{"openalex":"https://openalex.org/W4410447908","doi":"https://doi.org/10.3233/shti250469","pmid":"https://pubmed.ncbi.nlm.nih.gov/40380577"},"language":"en","primary_location":{"id":"doi:10.3233/shti250469","is_oa":true,"landing_page_url":"https://doi.org/10.3233/shti250469","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/SHTI250469","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":"book-chapter","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/SHTI250469","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5117573308","display_name":"Suteera Seeha","orcid":null},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Suteera Seeha","raw_affiliation_strings":["Institute of AI and Informatics in Medicine (AIIM), TUM University Hospital, Technical University of Munich, Munich, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of AI and Informatics in Medicine (AIIM), TUM University Hospital, Technical University of Munich, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000566469","display_name":"Szu\u2010Yuan Wu","orcid":"https://orcid.org/0000-0001-5637-558X"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Sihan Wu","raw_affiliation_strings":["Institute of AI and Informatics in Medicine (AIIM), TUM University Hospital, Technical University of Munich, Munich, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of AI and Informatics in Medicine (AIIM), TUM University Hospital, Technical University of Munich, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092749024","display_name":"Justin Hofenbitzer","orcid":"https://orcid.org/0009-0002-5024-5834"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Justin Hofenbitzer","raw_affiliation_strings":["Institute of AI and Informatics in Medicine (AIIM), TUM University Hospital, Technical University of Munich, Munich, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of AI and Informatics in Medicine (AIIM), TUM University Hospital, Technical University of Munich, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052168817","display_name":"Claudio Benzoni","orcid":null},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Claudio Benzoni","raw_affiliation_strings":["Institute of AI and Informatics in Medicine (AIIM), TUM University Hospital, Technical University of Munich, Munich, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of AI and Informatics in Medicine (AIIM), TUM University Hospital, Technical University of Munich, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106683712","display_name":"Peter Pallaoro","orcid":"https://orcid.org/0000-0003-4808-0700"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Peter Pallaoro","raw_affiliation_strings":["Institute of AI and Informatics in Medicine (AIIM), TUM University Hospital, Technical University of Munich, Munich, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of AI and Informatics in Medicine (AIIM), TUM University Hospital, Technical University of Munich, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029151960","display_name":"Raphael Scheible","orcid":"https://orcid.org/0000-0003-2067-5569"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Raphael Scheible","raw_affiliation_strings":["Institute of AI and Informatics in Medicine (AIIM), TUM University Hospital, Technical University of Munich, Munich, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of AI and Informatics in Medicine (AIIM), TUM University Hospital, Technical University of Munich, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039035898","display_name":"Martin Boeker","orcid":"https://orcid.org/0000-0003-2972-2042"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Martin Boeker","raw_affiliation_strings":["Institute of AI and Informatics in Medicine (AIIM), TUM University Hospital, Technical University of Munich, Munich, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of AI and Informatics in Medicine (AIIM), TUM University Hospital, Technical University of Munich, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029707385","display_name":"Luise Modersohn","orcid":"https://orcid.org/0000-0002-8258-4366"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Luise Modersohn","raw_affiliation_strings":["Institute of AI and Informatics in Medicine (AIIM), TUM University Hospital, Technical University of Munich, Munich, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of AI and Informatics in Medicine (AIIM), TUM University Hospital, Technical University of Munich, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I62916508"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.14056896,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"327","issue":null,"first_page":"798","last_page":"802"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9979000091552734,"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":0.9979000091552734,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9976999759674072,"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":0.9776999950408936,"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/german","display_name":"German","score":0.8754802346229553},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7230350971221924},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6551899313926697},{"id":"https://openalex.org/keywords/terminology","display_name":"Terminology","score":0.6393961906433105},{"id":"https://openalex.org/keywords/named-entity-recognition","display_name":"Named-entity recognition","score":0.6227546334266663},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5383124947547913},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5213369131088257},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.4955397844314575},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4411110281944275},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4231767952442169},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.2725011110305786},{"id":"https://openalex.org/keywords/history","display_name":"History","score":0.13606789708137512},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.07797214388847351},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.061314523220062256}],"concepts":[{"id":"https://openalex.org/C154775046","wikidata":"https://www.wikidata.org/wiki/Q188","display_name":"German","level":2,"score":0.8754802346229553},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7230350971221924},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6551899313926697},{"id":"https://openalex.org/C547195049","wikidata":"https://www.wikidata.org/wiki/Q1725664","display_name":"Terminology","level":2,"score":0.6393961906433105},{"id":"https://openalex.org/C2779135771","wikidata":"https://www.wikidata.org/wiki/Q403574","display_name":"Named-entity recognition","level":3,"score":0.6227546334266663},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5383124947547913},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5213369131088257},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.4955397844314575},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4411110281944275},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4231767952442169},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2725011110305786},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.13606789708137512},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.07797214388847351},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.061314523220062256},{"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/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","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":[{"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":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","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":true},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009626","descriptor_name":"Terminology as Topic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009626","descriptor_name":"Terminology as Topic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D018875","descriptor_name":"Vocabulary, Controlled","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D018875","descriptor_name":"Vocabulary, Controlled","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":2,"locations":[{"id":"doi:10.3233/shti250469","is_oa":true,"landing_page_url":"https://doi.org/10.3233/shti250469","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/SHTI250469","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:40380577","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40380577","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":"Journal Article"}],"best_oa_location":{"id":"doi:10.3233/shti250469","is_oa":true,"landing_page_url":"https://doi.org/10.3233/shti250469","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/SHTI250469","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":[{"score":0.5199999809265137,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4410447908.pdf","grobid_xml":"https://content.openalex.org/works/W4410447908.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2350593162","https://openalex.org/W2390350206","https://openalex.org/W1969477129","https://openalex.org/W2921208823","https://openalex.org/W2353483812","https://openalex.org/W2131808775","https://openalex.org/W2130038259","https://openalex.org/W2360756181","https://openalex.org/W2983934248","https://openalex.org/W1605730749"],"abstract_inverted_index":{"Named":[0],"Entity":[1],"Recognition":[2],"(NER)":[3],"in":[4,22,45],"the":[5,14,33,46,57],"medical":[6,19,52],"domain":[7],"often":[8],"presents":[9],"significant":[10],"challenges":[11],"due":[12],"to":[13,68],"complexity":[15],"and":[16,41,65],"specificity":[17],"of":[18,35,48,59],"terminology,":[20],"especially":[21],"lower-resource":[23,70],"settings":[24],"where":[25],"annotated":[26,79],"data":[27,61],"is":[28],"scarce.":[29],"This":[30],"study":[31],"explores":[32],"performance":[34,67],"an":[36],"exemplary":[37],"large":[38],"language":[39],"model":[40,44],"a":[42],"BERT-based":[43],"context":[47],"NER":[49],"for":[50,63],"German":[51,78],"texts.":[53],"We":[54],"focus":[55],"on":[56,76,90],"impact":[58],"different":[60],"sizes":[62],"training":[64,100],"their":[66],"simulate":[69],"conditions.":[71],"Both":[72],"models":[73,86],"are":[74],"evaluated":[75],"two":[77],"corpora.":[80],"Our":[81],"results":[82],"reveal":[83],"that":[84],"both":[85,91],"perform":[87],"rather":[88],"similar":[89],"datasets,":[92],"with":[93,98],"LLaMA3.1":[94],"performing":[95],"slightly":[96],"better":[97],"less":[99],"material.":[101]},"counts_by_year":[],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2025-10-10T00:00:00"}
