{"id":"https://openalex.org/W4413052409","doi":"https://doi.org/10.3233/shti251229","title":"Constructing a High-Quality English and Korean Medical Corpus for Medical Large Language Model","display_name":"Constructing a High-Quality English and Korean Medical Corpus for Medical Large Language Model","publication_year":2025,"publication_date":"2025-08-07","ids":{"openalex":"https://openalex.org/W4413052409","doi":"https://doi.org/10.3233/shti251229","pmid":"https://pubmed.ncbi.nlm.nih.gov/40776246"},"language":"en","primary_location":{"id":"doi:10.3233/shti251229","is_oa":true,"landing_page_url":"https://doi.org/10.3233/shti251229","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":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.3233/shti251229","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5033131822","display_name":"Chansik Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I87111246","display_name":"Catholic University of Korea","ror":"https://ror.org/01fpnj063","country_code":"KR","type":"education","lineage":["https://openalex.org/I87111246"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Chansik Kim","raw_affiliation_strings":["Department of Medical Informatics, College of Medicine, The Catholic University of Korea, Seoul, Republic of Korea","Department of Medical Sciences, College of Medicine, The Catholic University of Korea, Seoul, Republic of Korea"],"raw_orcid":"https://orcid.org/0009-0003-9727-2183","affiliations":[{"raw_affiliation_string":"Department of Medical Informatics, College of Medicine, The Catholic University of Korea, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I87111246"]},{"raw_affiliation_string":"Department of Medical Sciences, College of Medicine, The Catholic University of Korea, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I87111246"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102724677","display_name":"T Kim","orcid":"https://orcid.org/0000-0001-7381-8303"},"institutions":[{"id":"https://openalex.org/I87111246","display_name":"Catholic University of Korea","ror":"https://ror.org/01fpnj063","country_code":"KR","type":"education","lineage":["https://openalex.org/I87111246"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Tong Min Kim","raw_affiliation_strings":["Department of Medical Informatics, College of Medicine, The Catholic University of Korea, Seoul, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0001-7381-8303","affiliations":[{"raw_affiliation_string":"Department of Medical Informatics, College of Medicine, The Catholic University of Korea, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I87111246"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Youngron Lee","orcid":"https://orcid.org/0000-0003-1367-4381"},"institutions":[{"id":"https://openalex.org/I87111246","display_name":"Catholic University of Korea","ror":"https://ror.org/01fpnj063","country_code":"KR","type":"education","lineage":["https://openalex.org/I87111246"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Youngron Lee","raw_affiliation_strings":["Department of Medical Informatics, College of Medicine, The Catholic University of Korea, Seoul, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0003-1367-4381","affiliations":[{"raw_affiliation_string":"Department of Medical Informatics, College of Medicine, The Catholic University of Korea, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I87111246"]}]},{"author_position":"middle","author":{"id":null,"display_name":"DongGyu Kim","orcid":"https://orcid.org/0009-0002-2671-1831"},"institutions":[{"id":"https://openalex.org/I87111246","display_name":"Catholic University of Korea","ror":"https://ror.org/01fpnj063","country_code":"KR","type":"education","lineage":["https://openalex.org/I87111246"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"DongGyu Kim","raw_affiliation_strings":["Department of Medical Informatics, College of Medicine, The Catholic University of Korea, Seoul, Republic of Korea"],"raw_orcid":"https://orcid.org/0009-0002-2671-1831","affiliations":[{"raw_affiliation_string":"Department of Medical Informatics, College of Medicine, The Catholic University of Korea, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I87111246"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071412381","display_name":"Taehoon Ko","orcid":"https://orcid.org/0000-0002-4045-0036"},"institutions":[{"id":"https://openalex.org/I1313458441","display_name":"Catholic Medical Center","ror":"https://ror.org/00ng7yn96","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1313458441"]},{"id":"https://openalex.org/I87111246","display_name":"Catholic University of Korea","ror":"https://ror.org/01fpnj063","country_code":"KR","type":"education","lineage":["https://openalex.org/I87111246"]}],"countries":["KR","US"],"is_corresponding":false,"raw_author_name":"Taehoon Ko","raw_affiliation_strings":["CMC Institute for Basic Medical Science, The Catholic Medical Center of the Catholic University of Korea, Seoul, Republic of Korea","Department of Medical Informatics, College of Medicine, The Catholic University of Korea, Seoul, Republic of Korea","Department of Medical Sciences, College of Medicine, The Catholic University of Korea, Seoul, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0002-4045-0036","affiliations":[{"raw_affiliation_string":"CMC Institute for Basic Medical Science, The Catholic Medical Center of the Catholic University of Korea, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I87111246","https://openalex.org/I1313458441"]},{"raw_affiliation_string":"Department of Medical Informatics, College of Medicine, The Catholic University of Korea, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I87111246"]},{"raw_affiliation_string":"Department of Medical Sciences, College of Medicine, The Catholic University of Korea, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I87111246"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.34315157,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"329","issue":null,"first_page":"1816","last_page":"1817"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.854200005531311,"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":0.854200005531311,"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/T10350","display_name":"Electronic Health Records Systems","score":0.8034999966621399,"subfield":{"id":"https://openalex.org/subfields/3605","display_name":"Health Information Management"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.7281000018119812,"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/json","display_name":"JSON","score":0.8148863315582275},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6536968946456909},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5809235572814941},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.5804073214530945},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.5292588472366333},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.5253621339797974},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.4764305055141449},{"id":"https://openalex.org/keywords/english-language","display_name":"English language","score":0.4357627034187317},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4064183533191681},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3452121913433075},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.28817200660705566},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.28426796197891235},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.16399317979812622},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.09892141819000244}],"concepts":[{"id":"https://openalex.org/C2780416260","wikidata":"https://www.wikidata.org/wiki/Q2063","display_name":"JSON","level":2,"score":0.8148863315582275},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6536968946456909},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5809235572814941},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5804073214530945},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5292588472366333},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.5253621339797974},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.4764305055141449},{"id":"https://openalex.org/C2987496018","wikidata":"https://www.wikidata.org/wiki/Q1860","display_name":"English language","level":2,"score":0.4357627034187317},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4064183533191681},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3452121913433075},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.28817200660705566},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.28426796197891235},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.16399317979812622},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.09892141819000244},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000098342","descriptor_name":"Large Language Models","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000098342","descriptor_name":"Large Language Models","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":"D007802","descriptor_name":"Language","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007802","descriptor_name":"Language","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":"D014175","descriptor_name":"Translating","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D014175","descriptor_name":"Translating","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019303","descriptor_name":"Multilingualism","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D019303","descriptor_name":"Multilingualism","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D056910","descriptor_name":"Republic of Korea","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D056910","descriptor_name":"Republic of Korea","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"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}],"locations_count":2,"locations":[{"id":"doi:10.3233/shti251229","is_oa":true,"landing_page_url":"https://doi.org/10.3233/shti251229","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:40776246","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40776246","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/shti251229","is_oa":true,"landing_page_url":"https://doi.org/10.3233/shti251229","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/W2753132265","https://openalex.org/W4234766820","https://openalex.org/W4321232174","https://openalex.org/W3117520771","https://openalex.org/W2482048793","https://openalex.org/W4388027365","https://openalex.org/W2938860153","https://openalex.org/W4312551432","https://openalex.org/W2365783963","https://openalex.org/W3113257914"],"abstract_inverted_index":{"This":[0],"study":[1],"presents":[2],"a":[3],"high-quality":[4],"bilingual":[5],"(English":[6],"and":[7,29,40],"Korean)":[8],"medical":[9,52],"corpus":[10,43],"to":[11,27],"support":[12],"large-scale":[13],"language":[14],"models":[15],"in":[16,23,31],"healthcare.":[17],"Data":[18],"from":[19],"four":[20],"major":[21],"hospitals":[22],"Korea":[24],"were":[25],"converted":[26],"Markdown":[28],"organized":[30],"JSON":[32],"for":[33,50],"efficient":[34],"use.":[35],"Evaluation":[36],"metrics":[37],"ensured":[38],"consistency":[39],"reliability.":[41],"The":[42],"serves":[44],"as":[45],"an":[46],"open,":[47],"multilingual":[48],"resource":[49],"developing":[51],"LLMs.":[53]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
