{"id":"https://openalex.org/W4413956602","doi":"https://doi.org/10.3233/shti251397","title":"Retrieval-Augmented Generation for ICD-10 Coding in German Clinical Texts \u2013 A Technical Case Report","display_name":"Retrieval-Augmented Generation for ICD-10 Coding in German Clinical Texts \u2013 A Technical Case Report","publication_year":2025,"publication_date":"2025-09-03","ids":{"openalex":"https://openalex.org/W4413956602","doi":"https://doi.org/10.3233/shti251397","pmid":"https://pubmed.ncbi.nlm.nih.gov/40899543"},"language":"en","primary_location":{"id":"doi:10.3233/shti251397","is_oa":true,"landing_page_url":"https://doi.org/10.3233/shti251397","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":"book-chapter","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.3233/shti251397","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5117460489","display_name":"Mario Krumscheid","orcid":null},"institutions":[{"id":"https://openalex.org/I2802623092","display_name":"Kempten University of Applied Sciences","ror":"https://ror.org/02m4p8096","country_code":"DE","type":"education","lineage":["https://openalex.org/I2802623092"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Mario Krumscheid","raw_affiliation_strings":["Bavarian Center for Digital Health and Social Care, Kempten, Germany","Department of Computer Science, Kempten University of Applied Sciences, Kempten, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bavarian Center for Digital Health and Social Care, Kempten, Germany","institution_ids":["https://openalex.org/I2802623092"]},{"raw_affiliation_string":"Department of Computer Science, Kempten University of Applied Sciences, Kempten, Germany","institution_ids":["https://openalex.org/I2802623092"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010580955","display_name":"Johannes Bl\u00f6mer","orcid":"https://orcid.org/0000-0002-6065-3535"},"institutions":[{"id":"https://openalex.org/I39343248","display_name":"Humboldt-Universit\u00e4t zu Berlin","ror":"https://ror.org/01hcx6992","country_code":"DE","type":"education","lineage":["https://openalex.org/I39343248"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Johannes Bl\u00f6mer","raw_affiliation_strings":["Charit\u00e9 \u2013 Universit\u00e4tsmedizin Berlin, Freie Universit\u00e4t Berlin and Humboldt-Universit\u00e4t zu Berlin, Berlin, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Charit\u00e9 \u2013 Universit\u00e4tsmedizin Berlin, Freie Universit\u00e4t Berlin and Humboldt-Universit\u00e4t zu Berlin, Berlin, Germany","institution_ids":["https://openalex.org/I39343248"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010409045","display_name":"Matthias Becker","orcid":"https://orcid.org/0000-0003-4358-1258"},"institutions":[{"id":"https://openalex.org/I2802623092","display_name":"Kempten University of Applied Sciences","ror":"https://ror.org/02m4p8096","country_code":"DE","type":"education","lineage":["https://openalex.org/I2802623092"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Matthias Becker","raw_affiliation_strings":["Bavarian Center for Digital Health and Social Care, Kempten, Germany","Department of Computer Science, Kempten University of Applied Sciences, Kempten, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bavarian Center for Digital Health and Social Care, Kempten, Germany","institution_ids":["https://openalex.org/I2802623092"]},{"raw_affiliation_string":"Department of Computer Science, Kempten University of Applied Sciences, Kempten, Germany","institution_ids":["https://openalex.org/I2802623092"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.815,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.93047054,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"331","issue":null,"first_page":"204","last_page":"212"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.5618000030517578,"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"}},"topics":[{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.5618000030517578,"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/T10028","display_name":"Topic Modeling","score":0.10830000042915344,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.06549999862909317,"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":0.8586277365684509},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6691938042640686},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5647587180137634},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.5381771922111511},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5285807251930237},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.48941078782081604},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.4608208239078522},{"id":"https://openalex.org/keywords/semantic-similarity","display_name":"Semantic similarity","score":0.4458749294281006},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.4343221187591553},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4289027750492096}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8586277365684509},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6691938042640686},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5647587180137634},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.5381771922111511},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5285807251930237},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.48941078782081604},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.4608208239078522},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.4458749294281006},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.4343221187591553},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4289027750492096},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"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":"D012660","descriptor_name":"Semantics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012660","descriptor_name":"Semantics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D018875","descriptor_name":"Vocabulary, Controlled","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D018875","descriptor_name":"Vocabulary, Controlled","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D038801","descriptor_name":"International Classification of Diseases","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D038801","descriptor_name":"International Classification of Diseases","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D057286","descriptor_name":"Electronic Health Records","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D057286","descriptor_name":"Electronic Health Records","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D059019","descriptor_name":"Clinical Coding","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D059019","descriptor_name":"Clinical Coding","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true}],"locations_count":2,"locations":[{"id":"doi:10.3233/shti251397","is_oa":true,"landing_page_url":"https://doi.org/10.3233/shti251397","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:40899543","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40899543","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/shti251397","is_oa":true,"landing_page_url":"https://doi.org/10.3233/shti251397","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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3024364549","https://openalex.org/W2591697403","https://openalex.org/W2944728705","https://openalex.org/W4206019083","https://openalex.org/W2048865712","https://openalex.org/W2904022177","https://openalex.org/W1976265003","https://openalex.org/W2370378377","https://openalex.org/W2359348847","https://openalex.org/W3011538607"],"abstract_inverted_index":{"INTRODUCTION:":[0],"Manual":[1],"ICD-10":[2],"coding":[3,22],"of":[4,23,103,118],"German":[5,134],"clinical":[6,150],"texts":[7],"is":[8],"time-consuming":[9],"and":[10,43,65,70,92,106,125,140,147],"error-prone.":[11],"This":[12],"project":[13],"aims":[14],"to":[15,144],"develop":[16],"a":[17,74,80,101],"semi-automated":[18],"pipeline":[19,86],"for":[20],"efficient":[21],"unstructured":[24],"medical":[25],"documentation.":[26],"STATE":[27],"OF":[28],"THE":[29],"ART:":[30],"Existing":[31],"approaches":[32],"often":[33],"rely":[34],"on":[35,46,132],"fine-tuned":[36],"language":[37],"models":[38],"that":[39],"require":[40],"large":[41],"datasets":[42],"perform":[44],"poorly":[45],"rare":[47],"codes,":[48],"particularly":[49],"in":[50,122,149],"low-resource":[51],"languages":[52],"such":[53],"as":[54],"German.":[55],"CONCEPT:":[56],"The":[57,85],"proposed":[58],"system":[59],"integrates":[60],"Named":[61],"Entity":[62],"Recognition,":[63],"semantic":[64,104,123],"lexical":[66],"retrieval,":[67],"abbreviation":[68,138],"resolution,":[69],"context-aware":[71,142],"normalization":[72],"within":[73],"Retrieval-Augmented":[75],"Generation":[76],"(RAG)":[77],"framework":[78],"using":[79],"compact":[81],"generative":[82,107],"model.":[83,95],"IMPLEMENTATION:":[84],"utilizes":[87],"Sentence-BERT":[88],"embeddings,":[89,135],"FAISS":[90],"indexing,":[91],"the":[93,110],"Mistral-Small-Instruct":[94],"ICD":[96],"codes":[97],"are":[98],"assigned":[99],"through":[100],"combination":[102],"similarity":[105],"refinement":[108],"among":[109],"top":[111],"retrieval":[112,124],"candidates.":[113],"LESSONS":[114],"LEARNED:":[115],"Major":[116],"sources":[117],"error":[119],"were":[120],"found":[121],"diagnosis":[126],"normalization.":[127],"Future":[128],"improvements":[129],"should":[130],"focus":[131],"domain-specific":[133],"more":[136],"robust":[137],"handling,":[139],"enhanced":[141],"prompting":[143],"increase":[145],"accuracy":[146],"usability":[148],"environments.":[151]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}
