{"id":"https://openalex.org/W4413039989","doi":"https://doi.org/10.3233/shti250923","title":"Performance of Open-Source Large Language Models to Extract Symptoms from Clinical Notes","display_name":"Performance of Open-Source Large Language Models to Extract Symptoms from Clinical Notes","publication_year":2025,"publication_date":"2025-08-07","ids":{"openalex":"https://openalex.org/W4413039989","doi":"https://doi.org/10.3233/shti250923","pmid":"https://pubmed.ncbi.nlm.nih.gov/40775941"},"language":"en","primary_location":{"id":"doi:10.3233/shti250923","is_oa":true,"landing_page_url":"https://doi.org/10.3233/shti250923","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/shti250923","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5118729626","display_name":"Yunbing Bai","orcid":null},"institutions":[{"id":"https://openalex.org/I223532165","display_name":"University of Utah","ror":"https://ror.org/03r0ha626","country_code":"US","type":"education","lineage":["https://openalex.org/I223532165"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yunbing Bai","raw_affiliation_strings":["Department of Biomedical Informatics, School of Medicine, University of Utah, Salt Lake City, Utah"],"raw_orcid":"https://orcid.org/0009-0005-4910-4497","affiliations":[{"raw_affiliation_string":"Department of Biomedical Informatics, School of Medicine, University of Utah, Salt Lake City, Utah","institution_ids":["https://openalex.org/I223532165"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080703401","display_name":"Wanting Cui","orcid":"https://orcid.org/0000-0001-7341-363X"},"institutions":[{"id":"https://openalex.org/I223532165","display_name":"University of Utah","ror":"https://ror.org/03r0ha626","country_code":"US","type":"education","lineage":["https://openalex.org/I223532165"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wanting Cui","raw_affiliation_strings":["Department of Biomedical Informatics, School of Medicine, University of Utah, Salt Lake City, Utah"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Biomedical Informatics, School of Medicine, University of Utah, Salt Lake City, Utah","institution_ids":["https://openalex.org/I223532165"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086304704","display_name":"Joseph Finkelstein","orcid":"https://orcid.org/0000-0002-8084-7441"},"institutions":[{"id":"https://openalex.org/I223532165","display_name":"University of Utah","ror":"https://ror.org/03r0ha626","country_code":"US","type":"education","lineage":["https://openalex.org/I223532165"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Joseph Finkelstein","raw_affiliation_strings":["Department of Biomedical Informatics, School of Medicine, University of Utah, Salt Lake City, Utah"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Biomedical Informatics, School of Medicine, University of Utah, Salt Lake City, Utah","institution_ids":["https://openalex.org/I223532165"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5118729626"],"corresponding_institution_ids":["https://openalex.org/I223532165"],"apc_list":null,"apc_paid":null,"fwci":4.1459,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.93880593,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":"329","issue":null,"first_page":"663","last_page":"667"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9833999872207642,"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":0.9833999872207642,"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":0.9280999898910522,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.9136000275611877,"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/open-source","display_name":"Open source","score":0.6771348714828491},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6307953000068665},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4812436103820801},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.26116418838500977},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.09720718860626221}],"concepts":[{"id":"https://openalex.org/C3018397939","wikidata":"https://www.wikidata.org/wiki/Q3644502","display_name":"Open source","level":3,"score":0.6771348714828491},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6307953000068665},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4812436103820801},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.26116418838500977},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.09720718860626221}],"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":"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":"D038801","descriptor_name":"International Classification of Diseases","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":false},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":"Q000379","qualifier_name":"methods","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":"D063189","descriptor_name":"Symptom Assessment","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D063189","descriptor_name":"Symptom Assessment","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true}],"locations_count":2,"locations":[{"id":"doi:10.3233/shti250923","is_oa":true,"landing_page_url":"https://doi.org/10.3233/shti250923","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:40775941","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40775941","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/shti250923","is_oa":true,"landing_page_url":"https://doi.org/10.3233/shti250923","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"In":[0],"this":[1],"study,":[2],"we":[3],"examined":[4],"how":[5],"well":[6,125],"the":[7,31,49,63,99],"open-source":[8],"foundational":[9],"large":[10],"language":[11],"models":[12],"(LLMs)":[13],"can":[14],"extract":[15],"symptoms":[16],"and":[17,69,75,87,105,115,132],"signs":[18],"(S&S),":[19],"along":[20],"with":[21,41,53],"their":[22,72],"corresponding":[23],"ICD-10":[24,89,139],"codes,":[25],"from":[26],"clinical":[27],"notes":[28,38],"found":[29],"in":[30],"public":[32],"MTSamples":[33],"dataset.":[34],"The":[35],"dataset":[36],"comprising":[37],"of":[39,62,113,119,130,136],"patients":[40],"genitourinary":[42],"conditions":[43],"was":[44,79],"manually":[45],"annotated":[46],"to":[47],"compare":[48],"S&S":[50,85,122],"extraction":[51,86],"results":[52],"outputs":[54],"generated":[55],"by":[56],"LLMs.":[57],"We":[58],"assessed":[59],"three":[60],"versions":[61],"Llama":[64,67,96],"model-Llama":[65],"3.1-13B,":[66],"3.3-70B,":[68],"Me-Llama-13B-focusing":[70],"on":[71,81],"consistency,":[73,107],"runtime,":[74],"performance.":[76],"Each":[77],"model":[78],"tested":[80],"two":[82],"tasks:":[83],"(1)":[84],"(2)":[88],"code":[90,140],"generation.":[91,141],"Our":[92],"findings":[93],"indicate":[94],"that":[95],"3.3-70B":[97],"performed":[98],"best":[100],"overall.":[101],"With":[102],"fast":[103],"runtime":[104],"high":[106],"it":[108],"achieved":[109],"an":[110,116,127,133],"average":[111,117,128,134],"recall":[112,129],"0.87":[114],"precision":[118,135],"0.71":[120,131],"for":[121,138],"extraction,":[123],"as":[124,126],"0.54":[137]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
