{"id":"https://openalex.org/W4401821895","doi":"https://doi.org/10.3233/shti240497","title":"Automation of Trainable Datasets Generation for Medical-Specific Language Model: Using MIMIC-IV Discharge Notes","display_name":"Automation of Trainable Datasets Generation for Medical-Specific Language Model: Using MIMIC-IV Discharge Notes","publication_year":2024,"publication_date":"2024-08-22","ids":{"openalex":"https://openalex.org/W4401821895","doi":"https://doi.org/10.3233/shti240497","pmid":"https://pubmed.ncbi.nlm.nih.gov/39176825"},"language":"en","primary_location":{"id":"doi:10.3233/shti240497","is_oa":true,"landing_page_url":"http://dx.doi.org/10.3233/shti240497","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/SHTI240497","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://ebooks.iospress.nl/pdf/doi/10.3233/SHTI240497","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5057796553","display_name":"Youngrong 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":"Youngrong Lee","raw_affiliation_strings":["Department of Medical Informatics, College of Medicine, The Catholic University of Korea, 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, Republic of Korea","institution_ids":["https://openalex.org/I87111246"]}]},{"author_position":"middle","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 Biomedicine & Health Sciences, College of Medicine, The Catholic University of Korea, Republic of Korea","Department of Medical Informatics, College of Medicine, The Catholic University of Korea, Republic of Korea"],"raw_orcid":"https://orcid.org/0009-0003-9727-2183","affiliations":[{"raw_affiliation_string":"Department of Biomedicine & Health Sciences, College of Medicine, The Catholic University of Korea, Republic of Korea","institution_ids":["https://openalex.org/I87111246"]},{"raw_affiliation_string":"Department of Medical Informatics, College of Medicine, The Catholic University of Korea, 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/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":true,"raw_author_name":"Taehoon Ko","raw_affiliation_strings":["Department of Biomedicine & Health Sciences, College of Medicine, The Catholic University of Korea, Republic of Korea","Department of Medical Informatics, College of Medicine, The Catholic University of Korea, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0002-4045-0036","affiliations":[{"raw_affiliation_string":"Department of Biomedicine & Health Sciences, College of Medicine, The Catholic University of Korea, Republic of Korea","institution_ids":["https://openalex.org/I87111246"]},{"raw_affiliation_string":"Department of Medical Informatics, College of Medicine, The Catholic University of Korea, Republic of Korea","institution_ids":["https://openalex.org/I87111246"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5071412381"],"corresponding_institution_ids":["https://openalex.org/I87111246"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.29072832,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"316","issue":null,"first_page":"650","last_page":"651"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9940000176429749,"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":0.9940000176429749,"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/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.9704999923706055,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.95169997215271,"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":0.7925685048103333},{"id":"https://openalex.org/keywords/automation","display_name":"Automation","score":0.6165871024131775},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5685000419616699},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5674340724945068},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5306179523468018},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.49598345160484314},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.43685126304626465},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.43451589345932007},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.34117424488067627}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7925685048103333},{"id":"https://openalex.org/C115901376","wikidata":"https://www.wikidata.org/wiki/Q184199","display_name":"Automation","level":2,"score":0.6165871024131775},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5685000419616699},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5674340724945068},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5306179523468018},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.49598345160484314},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.43685126304626465},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.43451589345932007},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.34117424488067627},{"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/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[{"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":"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":"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":"D010351","descriptor_name":"Patient Discharge","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010351","descriptor_name":"Patient Discharge","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010351","descriptor_name":"Patient Discharge","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010351","descriptor_name":"Patient Discharge","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},{"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":"D063886","descriptor_name":"Patient Discharge Summaries","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D063886","descriptor_name":"Patient Discharge Summaries","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D063886","descriptor_name":"Patient Discharge Summaries","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D063886","descriptor_name":"Patient Discharge Summaries","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.3233/shti240497","is_oa":true,"landing_page_url":"http://dx.doi.org/10.3233/shti240497","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/SHTI240497","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:39176825","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/39176825","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/shti240497","is_oa":true,"landing_page_url":"http://dx.doi.org/10.3233/shti240497","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/SHTI240497","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":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7799999713897705}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4401821895.pdf"},"referenced_works_count":3,"referenced_works":["https://openalex.org/W2154652894","https://openalex.org/W4221159410","https://openalex.org/W4312091890"],"related_works":["https://openalex.org/W2519676117","https://openalex.org/W2218202131","https://openalex.org/W84108837","https://openalex.org/W2155740880","https://openalex.org/W2131713426","https://openalex.org/W4253249845","https://openalex.org/W2125452230","https://openalex.org/W2148444631","https://openalex.org/W1988425686","https://openalex.org/W971421295"],"abstract_inverted_index":{"This":[0],"study":[1,21,102],"introduces":[2],"a":[3,23,94],"novel":[4],"approach":[5],"for":[6,11,110],"generating":[7,47],"machine-generated":[8],"instruction":[9,48],"datasets":[10],"fine-tuning":[12],"medical-specialized":[13],"language":[14],"models":[15],"using":[16,51],"MIMIC-IV":[17],"discharge":[18,30],"records.":[19],"The":[20,39,63,101],"created":[22],"large-scale":[24],"text":[25],"dataset":[26,40,65,82,108],"comprising":[27],"instructions,":[28],"cropped":[29],"notes":[31],"as":[32],"inputs,":[33],"and":[34,49,93,98],"outputs":[35],"in":[36,113],"JSONL":[37],"format.":[38],"was":[41],"generated":[42,64,81],"through":[43],"three":[44],"main":[45],"stages,":[46],"output":[50],"seed":[52,74],"tasks":[53,75,112],"provided":[54],"by":[55,59,90],"medical":[56,115],"experts,":[57],"followed":[58],"invalid":[60],"data":[61],"filtering.":[62],"consisted":[66],"of":[67,76,79,106],"51,385":[68],"sets,":[69],"with":[70,85],"mean":[71],"ROUGE":[72],"between":[73],"0.185.":[77],"Evaluation":[78],"the":[80,104,114],"were":[83],"promising,":[84],"high":[86],"validity":[87],"rates":[88],"determined":[89],"both":[91],"GPT-3.5":[92],"human":[95],"annotator":[96],"(88.0%":[97],"88.5%":[99],"respectively).":[100],"highlights":[103],"potential":[105],"automating":[107],"creation":[109],"NLP":[111],"domain.":[116]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
