{"id":"https://openalex.org/W4399280731","doi":"https://doi.org/10.1093/jamia/ocae133","title":"Fine-tuning large language models for rare disease concept normalization","display_name":"Fine-tuning large language models for rare disease concept normalization","publication_year":2024,"publication_date":"2024-05-23","ids":{"openalex":"https://openalex.org/W4399280731","doi":"https://doi.org/10.1093/jamia/ocae133","pmid":"https://pubmed.ncbi.nlm.nih.gov/38829731"},"language":"en","primary_location":{"id":"doi:10.1093/jamia/ocae133","is_oa":false,"landing_page_url":"https://doi.org/10.1093/jamia/ocae133","pdf_url":null,"source":{"id":"https://openalex.org/S129839026","display_name":"Journal of the American Medical Informatics Association","issn_l":"1067-5027","issn":["1067-5027","1527-974X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of the American Medical Informatics Association","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC11339522/pdf/ocae133.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5068011488","display_name":"Andy Wang","orcid":"https://orcid.org/0009-0007-2323-1505"},"institutions":[{"id":"https://openalex.org/I2800966798","display_name":"Peddie School","ror":"https://ror.org/00mpmjk72","country_code":"US","type":"education","lineage":["https://openalex.org/I2800966798"]},{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andy Wang","raw_affiliation_strings":["Department of Biomedical Informatics, Columbia University , New York, NY 10032, United States","Peddie School , Hightstown, NJ 08520, United States"],"raw_orcid":"https://orcid.org/0009-0007-2323-1505","affiliations":[{"raw_affiliation_string":"Department of Biomedical Informatics, Columbia University , New York, NY 10032, United States","institution_ids":["https://openalex.org/I78577930"]},{"raw_affiliation_string":"Peddie School , Hightstown, NJ 08520, United States","institution_ids":["https://openalex.org/I2800966798"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100331534","display_name":"Cong Liu","orcid":"https://orcid.org/0000-0001-6024-3037"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cong Liu","raw_affiliation_strings":["Department of Biomedical Informatics, Columbia University , New York, NY 10032, United States"],"raw_orcid":"https://orcid.org/0000-0001-6024-3037","affiliations":[{"raw_affiliation_string":"Department of Biomedical Informatics, Columbia University , New York, NY 10032, United States","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113676623","display_name":"Jingye Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jingye Yang","raw_affiliation_strings":["Department of Mathematics, University of Pennsylvania , Philadelphia, PA 19104, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mathematics, University of Pennsylvania , Philadelphia, PA 19104, United States","institution_ids":["https://openalex.org/I79576946"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009604048","display_name":"Chunhua Weng","orcid":"https://orcid.org/0000-0002-9624-0214"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Chunhua Weng","raw_affiliation_strings":["Department of Biomedical Informatics, Columbia University , New York, NY 10032, United States"],"raw_orcid":"https://orcid.org/0000-0002-9624-0214","affiliations":[{"raw_affiliation_string":"Department of Biomedical Informatics, Columbia University , New York, NY 10032, United States","institution_ids":["https://openalex.org/I78577930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5009604048"],"corresponding_institution_ids":["https://openalex.org/I78577930"],"apc_list":{"value":3967,"currency":"USD","value_usd":3967},"apc_paid":null,"fwci":15.1903,"has_fulltext":true,"cited_by_count":35,"citation_normalized_percentile":{"value":0.99324253,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"31","issue":"9","first_page":"2076","last_page":"2083"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11642","display_name":"Genomics and Rare Diseases","score":0.5985999703407288,"subfield":{"id":"https://openalex.org/subfields/1311","display_name":"Genetics"},"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/T11642","display_name":"Genomics and Rare Diseases","score":0.5985999703407288,"subfield":{"id":"https://openalex.org/subfields/1311","display_name":"Genetics"},"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.250900000333786,"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":0.08129999786615372,"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":0.767493486404419},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.7513054609298706},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7286134958267212},{"id":"https://openalex.org/keywords/fine-tuning","display_name":"Fine-tuning","score":0.7139898538589478},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.7078462839126587},{"id":"https://openalex.org/keywords/identifier","display_name":"Identifier","score":0.620965301990509},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5520732402801514},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5070886611938477},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.48138096928596497},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.07574298977851868}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.767493486404419},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.7513054609298706},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7286134958267212},{"id":"https://openalex.org/C157524613","wikidata":"https://www.wikidata.org/wiki/Q2828883","display_name":"Fine-tuning","level":2,"score":0.7139898538589478},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.7078462839126587},{"id":"https://openalex.org/C154504017","wikidata":"https://www.wikidata.org/wiki/Q853614","display_name":"Identifier","level":2,"score":0.620965301990509},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5520732402801514},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5070886611938477},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.48138096928596497},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.07574298977851868},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"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/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}],"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":"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":"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":"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":"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":"D010641","descriptor_name":"Phenotype","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D010641","descriptor_name":"Phenotype","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D010641","descriptor_name":"Phenotype","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D010641","descriptor_name":"Phenotype","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D010641","descriptor_name":"Phenotype","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D010641","descriptor_name":"Phenotype","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D010641","descriptor_name":"Phenotype","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D010641","descriptor_name":"Phenotype","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D010641","descriptor_name":"Phenotype","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D010641","descriptor_name":"Phenotype","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},{"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},{"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},{"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},{"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},{"descriptor_ui":"D035583","descriptor_name":"Rare Diseases","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D035583","descriptor_name":"Rare Diseases","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D035583","descriptor_name":"Rare Diseases","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D035583","descriptor_name":"Rare Diseases","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D035583","descriptor_name":"Rare Diseases","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D035583","descriptor_name":"Rare Diseases","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D035583","descriptor_name":"Rare Diseases","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D035583","descriptor_name":"Rare Diseases","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D035583","descriptor_name":"Rare Diseases","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D035583","descriptor_name":"Rare Diseases","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D064229","descriptor_name":"Biological Ontologies","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D064229","descriptor_name":"Biological Ontologies","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D064229","descriptor_name":"Biological Ontologies","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D064229","descriptor_name":"Biological Ontologies","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D064229","descriptor_name":"Biological Ontologies","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D064229","descriptor_name":"Biological Ontologies","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D064229","descriptor_name":"Biological Ontologies","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D064229","descriptor_name":"Biological Ontologies","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D064229","descriptor_name":"Biological Ontologies","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D064229","descriptor_name":"Biological Ontologies","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":3,"locations":[{"id":"doi:10.1093/jamia/ocae133","is_oa":false,"landing_page_url":"https://doi.org/10.1093/jamia/ocae133","pdf_url":null,"source":{"id":"https://openalex.org/S129839026","display_name":"Journal of the American Medical Informatics Association","issn_l":"1067-5027","issn":["1067-5027","1527-974X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of the American Medical Informatics Association","raw_type":"journal-article"},{"id":"pmid:38829731","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/38829731","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":"Journal of the American Medical Informatics Association : JAMIA","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:11339522","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/11339522","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC11339522/pdf/ocae133.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"J Am Med Inform Assoc","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:pubmedcentral.nih.gov:11339522","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/11339522","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC11339522/pdf/ocae133.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"J Am Med Inform Assoc","raw_type":"Text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.8100000023841858,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G1649907073","display_name":null,"funder_award_id":"R01 HG013031","funder_id":"https://openalex.org/F4320337348","funder_display_name":"National Human Genome Research Institute"},{"id":"https://openalex.org/G192135554","display_name":null,"funder_award_id":"HG012655","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G1998495554","display_name":null,"funder_award_id":"LM012895","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G5503662962","display_name":null,"funder_award_id":"U01 HG008680","funder_id":"https://openalex.org/F4320337348","funder_display_name":"National Human Genome Research Institute"},{"id":"https://openalex.org/G5763468455","display_name":null,"funder_award_id":"R01 HG012655","funder_id":"https://openalex.org/F4320337348","funder_display_name":"National Human Genome Research Institute"},{"id":"https://openalex.org/G5850758212","display_name":null,"funder_award_id":"HG013031","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G6987032315","display_name":null,"funder_award_id":"R01 LM012895","funder_id":"https://openalex.org/F4320337372","funder_display_name":"U.S. National Library of Medicine"}],"funders":[{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320337348","display_name":"National Human Genome Research Institute","ror":"https://ror.org/00baak391"},{"id":"https://openalex.org/F4320337372","display_name":"U.S. National Library of Medicine","ror":"https://ror.org/0060t0j89"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4399280731.pdf"},"referenced_works_count":33,"referenced_works":["https://openalex.org/W106471462","https://openalex.org/W1550258693","https://openalex.org/W1829450080","https://openalex.org/W2012361142","https://openalex.org/W2014474824","https://openalex.org/W2107651176","https://openalex.org/W2122402213","https://openalex.org/W2604401930","https://openalex.org/W2799806969","https://openalex.org/W2807640626","https://openalex.org/W2810528414","https://openalex.org/W2886173545","https://openalex.org/W2888828233","https://openalex.org/W2946102094","https://openalex.org/W2970597249","https://openalex.org/W3031191781","https://openalex.org/W3036263923","https://openalex.org/W3044247947","https://openalex.org/W3092486910","https://openalex.org/W3160596727","https://openalex.org/W4252076394","https://openalex.org/W4321351832","https://openalex.org/W4365511667","https://openalex.org/W4384918448","https://openalex.org/W4385848332","https://openalex.org/W4388037391","https://openalex.org/W6604396416","https://openalex.org/W6632766574","https://openalex.org/W6638492565","https://openalex.org/W6763701032","https://openalex.org/W6779563547","https://openalex.org/W6850507425","https://openalex.org/W6854866820"],"related_works":["https://openalex.org/W4378651134","https://openalex.org/W4252684102","https://openalex.org/W2591697403","https://openalex.org/W2352307597","https://openalex.org/W3023285645","https://openalex.org/W3037551068","https://openalex.org/W3023594376","https://openalex.org/W4287802662","https://openalex.org/W3154646238","https://openalex.org/W4309877123"],"abstract_inverted_index":{"OBJECTIVE:":[0],"We":[1,35],"aim":[2],"to":[3,41,163,198,227,239],"develop":[4],"a":[5,24,95,220,243],"novel":[6],"method":[7],"for":[8,45,86,109,138,222],"rare":[9],"disease":[10],"concept":[11],"normalization":[12,110],"by":[13],"fine-tuning":[14,115,205],"Llama":[15,83],"2,":[16],"an":[17,37,92],"open-source":[18],"large":[19],"language":[20],"model":[21,181,188],"(LLM),":[22],"using":[23,94],"domain-specific":[25],"corpus":[26],"sourced":[27,54,172],"from":[28,55,173,211,232],"the":[29,56,73,106,114,147,150,179,186,204,223],"Human":[30],"Phenotype":[31],"Ontology":[32],"(HPO).":[33],"METHODS:":[34],"developed":[36],"in-house":[38],"template-based":[39],"script":[40],"generate":[42],"two":[43],"corpora":[44],"fine-tuning.":[46,169],"The":[47,64],"first":[48],"(NAME)":[49],"contains":[50],"standardized":[51],"HPO":[52,57,68,136,174],"names,":[53],"vocabularies,":[58],"along":[59],"with":[60,166],"their":[61],"corresponding":[62],"identifiers.":[63,79],"second":[65],"(NAME+SYN)":[66,165],"includes":[67],"names":[69],"and":[70,90,100,154,158,214],"half":[71],"of":[72,97,152,225],"concept's":[74],"synonyms":[75],"as":[76,78,176],"well":[77],"Subsequently,":[80],"we":[81],"fine-tuned":[82,194],"2":[84],"(Llama2-7B)":[85],"each":[87],"sentence":[88,98],"set":[89],"conducted":[91],"evaluation":[93],"range":[96],"prompts":[99],"various":[101],"phenotype":[102,107,139,148,200],"terms.":[103,140,216],"RESULTS:":[104],"When":[105,141],"terms":[108,171,201,210],"were":[111,144],"included":[112],"in":[113,134,146,203,242],"corpora,":[116],"both":[117],"models":[118,195],"demonstrated":[119],"nearly":[120],"perfect":[121],"performance,":[122],"averaging":[123],"over":[124],"99%":[125],"accuracy.":[126,191],"In":[127],"comparison,":[128],"ChatGPT-3.5":[129],"has":[130],"only":[131],"\u223c20%":[132],"accuracy":[133,151],"identifying":[135],"IDs":[137],"single-character":[142],"typos":[143],"introduced":[145],"terms,":[149],"NAME":[153,180],"NAME+SYN":[155,187],"is":[156],"10.2%":[157],"36.1%,":[159],"respectively,":[160],"but":[161],"increases":[162],"61.8%":[164],"additional":[167],"typo-specific":[168],"For":[170],"vocabularies":[175],"unseen":[177,202],"synonyms,":[178,209],"achieved":[182,189],"11.2%":[183],"accuracy,":[184],"while":[185,235],"92.7%":[190],"CONCLUSION:":[192],"Our":[193,217],"demonstrate":[196],"ability":[197],"normalize":[199],"corpus,":[206],"including":[207],"misspellings,":[208],"other":[212],"ontologies,":[213],"laymen's":[215],"approach":[218],"provides":[219],"solution":[221],"use":[224],"LLMs":[226],"identify":[228],"named":[229],"medical":[230],"entities":[231],"clinical":[233],"narratives,":[234],"successfully":[236],"normalizing":[237],"them":[238],"standard":[240],"concepts":[241],"controlled":[244],"vocabulary.":[245]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":22},{"year":2024,"cited_by_count":9}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}