{"id":"https://openalex.org/W4394975332","doi":"https://doi.org/10.1093/jamia/ocae073","title":"Distilling large language models for matching patients to clinical trials","display_name":"Distilling large language models for matching patients to clinical trials","publication_year":2024,"publication_date":"2024-04-19","ids":{"openalex":"https://openalex.org/W4394975332","doi":"https://doi.org/10.1093/jamia/ocae073","pmid":"https://pubmed.ncbi.nlm.nih.gov/38641416"},"language":"en","primary_location":{"id":"doi:10.1093/jamia/ocae073","is_oa":false,"landing_page_url":"https://doi.org/10.1093/jamia/ocae073","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/PMC11339497/pdf/ocae073.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5093526502","display_name":"Mauro Nievas","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mauro Nievas","raw_affiliation_strings":["Triomics Research, Triomics, Inc. , San Francisco, CA 94105, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Triomics Research, Triomics, Inc. , San Francisco, CA 94105, United States","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100606669","display_name":"Aditya Basu","orcid":"https://orcid.org/0000-0002-9760-0912"},"institutions":[{"id":"https://openalex.org/I4210134763","display_name":"Thrombosis Research Institute","ror":"https://ror.org/04e6jcd64","country_code":"IN","type":"nonprofit","lineage":["https://openalex.org/I4210134763"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Aditya Basu","raw_affiliation_strings":["Triomics Research, Triomics, Inc. , Bengaluru, Karnataka 560102, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Triomics Research, Triomics, Inc. , Bengaluru, Karnataka 560102, India","institution_ids":["https://openalex.org/I4210134763"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080116611","display_name":"Yanshan Wang","orcid":"https://orcid.org/0000-0003-4433-7839"},"institutions":[{"id":"https://openalex.org/I170201317","display_name":"University of Pittsburgh","ror":"https://ror.org/01an3r305","country_code":"US","type":"education","lineage":["https://openalex.org/I170201317"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yanshan Wang","raw_affiliation_strings":["Department of Health Information Management, University of Pittsburgh , Pittsburgh, PA 15260, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Health Information Management, University of Pittsburgh , Pittsburgh, PA 15260, United States","institution_ids":["https://openalex.org/I170201317"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044442880","display_name":"Hrituraj Singh","orcid":"https://orcid.org/0000-0003-3705-120X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hrituraj Singh","raw_affiliation_strings":["Triomics Research, Triomics, Inc. , San Francisco, CA 94105, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Triomics Research, Triomics, Inc. , San Francisco, CA 94105, United States","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5080116611"],"corresponding_institution_ids":["https://openalex.org/I170201317"],"apc_list":{"value":3967,"currency":"USD","value_usd":3967},"apc_paid":null,"fwci":5.6637,"has_fulltext":true,"cited_by_count":60,"citation_normalized_percentile":{"value":0.96489564,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"31","issue":"9","first_page":"1953","last_page":"1963"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.5674999952316284,"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"}},"topics":[{"id":"https://openalex.org/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.5674999952316284,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.30250000953674316,"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/T10350","display_name":"Electronic Health Records Systems","score":0.01549999974668026,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.6422920227050781},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6253335475921631},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5191078186035156},{"id":"https://openalex.org/keywords/clinical-trial","display_name":"Clinical trial","score":0.5171843767166138},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4552352726459503},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.33943426609039307},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3362012505531311},{"id":"https://openalex.org/keywords/medicine","display_name":"Medicine","score":0.2307908833026886},{"id":"https://openalex.org/keywords/pathology","display_name":"Pathology","score":0.07427012920379639}],"concepts":[{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.6422920227050781},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6253335475921631},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5191078186035156},{"id":"https://openalex.org/C535046627","wikidata":"https://www.wikidata.org/wiki/Q30612","display_name":"Clinical trial","level":2,"score":0.5171843767166138},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4552352726459503},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33943426609039307},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3362012505531311},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.2307908833026886},{"id":"https://openalex.org/C142724271","wikidata":"https://www.wikidata.org/wiki/Q7208","display_name":"Pathology","level":1,"score":0.07427012920379639}],"mesh":[{"descriptor_ui":"D002986","descriptor_name":"Clinical Trials as Topic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D002986","descriptor_name":"Clinical Trials as Topic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D002986","descriptor_name":"Clinical Trials as Topic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D002986","descriptor_name":"Clinical Trials as Topic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D002986","descriptor_name":"Clinical Trials as Topic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D002986","descriptor_name":"Clinical Trials as Topic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D002986","descriptor_name":"Clinical Trials as Topic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"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":false},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","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":false},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","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":false},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","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":false},{"descriptor_ui":"D011381","descriptor_name":"Programming Languages","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011381","descriptor_name":"Programming Languages","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011381","descriptor_name":"Programming Languages","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011381","descriptor_name":"Programming Languages","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011381","descriptor_name":"Programming Languages","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011381","descriptor_name":"Programming Languages","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011381","descriptor_name":"Programming Languages","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D018579","descriptor_name":"Patient Selection","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D018579","descriptor_name":"Patient Selection","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D018579","descriptor_name":"Patient Selection","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D018579","descriptor_name":"Patient Selection","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D018579","descriptor_name":"Patient Selection","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D018579","descriptor_name":"Patient Selection","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D018579","descriptor_name":"Patient Selection","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":3,"locations":[{"id":"doi:10.1093/jamia/ocae073","is_oa":false,"landing_page_url":"https://doi.org/10.1093/jamia/ocae073","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:38641416","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/38641416","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:11339497","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/11339497","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC11339497/pdf/ocae073.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:11339497","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/11339497","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC11339497/pdf/ocae073.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":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.7900000214576721}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4394975332.pdf"},"referenced_works_count":24,"referenced_works":["https://openalex.org/W57180090","https://openalex.org/W231452340","https://openalex.org/W2016920401","https://openalex.org/W2051326280","https://openalex.org/W2081656751","https://openalex.org/W2110983945","https://openalex.org/W2114847203","https://openalex.org/W2142862978","https://openalex.org/W2165067209","https://openalex.org/W2270764879","https://openalex.org/W2296023454","https://openalex.org/W2470268543","https://openalex.org/W2783310654","https://openalex.org/W2911661483","https://openalex.org/W2974214648","https://openalex.org/W4224039413","https://openalex.org/W4292779060","https://openalex.org/W4366368023","https://openalex.org/W4381587418","https://openalex.org/W4384071683","https://openalex.org/W4386120650","https://openalex.org/W4402667025","https://openalex.org/W6778883912","https://openalex.org/W6857900327"],"related_works":["https://openalex.org/W1972035260","https://openalex.org/W4393234404","https://openalex.org/W4301594054","https://openalex.org/W2794488505","https://openalex.org/W2961085424","https://openalex.org/W2330369487","https://openalex.org/W3125889879","https://openalex.org/W2906196243","https://openalex.org/W3124422538","https://openalex.org/W2295467472"],"abstract_inverted_index":{"OBJECTIVE:":[0],"The":[1,41,101,144,176],"objective":[2],"of":[3,12,30,82,132,138,149,156],"this":[4,110,194],"study":[5,42,127,177],"is":[6],"to":[7,33,152],"systematically":[8],"examine":[9],"the":[10,28,80,129,135,147,154,179,196,201],"efficacy":[11],"both":[13],"proprietary":[14,120,157,173],"(GPT-3.5,":[15],"GPT-4)":[16],"and":[17,51,63,75,112,167,191,200],"open-source":[18,83,105,150,182],"large":[19],"language":[20],"models":[21,151,158],"(LLMs)":[22],"(LLAMA":[23],"7B,":[24],"13B,":[25],"70B)":[26],"in":[27,36,67,134,141,184,193],"context":[29],"matching":[31],"patients":[32],"clinical":[34,72],"trials":[35],"healthcare.":[37],"MATERIALS":[38],"AND":[39],"METHODS:":[40],"employs":[43],"a":[44,56,85],"multifaceted":[45],"evaluation":[46,198],"framework,":[47],"incorporating":[48],"extensive":[49],"automated":[50],"human-centric":[52],"assessments":[53],"along":[54],"with":[55,118,171],"detailed":[57],"error":[58],"analysis":[59],"for":[60,181,207],"each":[61],"model,":[62],"assesses":[64],"LLMs'":[65],"capabilities":[66],"analyzing":[68],"patient":[69],"eligibility":[70],"against":[71],"trial's":[73],"inclusion":[74],"exclusion":[76],"criteria.":[77],"To":[78,187],"improve":[79],"adaptability":[81],"LLMs,":[84,106],"specialized":[86],"synthetic":[87,113],"dataset":[88,199],"was":[89],"created":[90],"using":[91],"GPT-4,":[92],"facilitating":[93],"effective":[94],"fine-tuning":[95],"under":[96],"constrained":[97],"data":[98],"conditions.":[99],"RESULTS:":[100],"findings":[102],"indicate":[103],"that":[104],"when":[107,159],"fine-tuned":[108,160,202],"on":[109],"limited":[111],"dataset,":[114],"achieve":[115],"performance":[116,155],"parity":[117],"their":[119],"counterparts,":[121],"such":[122],"as":[123],"GPT-3.5.":[124],"DISCUSSION:":[125],"This":[126],"highlights":[128],"recent":[130],"success":[131],"LLMs":[133,183],"high-stakes":[136],"domain":[137],"healthcare,":[139],"specifically":[140],"patient-trial":[142,185],"matching.":[143,186],"research":[145,190],"demonstrates":[146],"potential":[148],"match":[153],"appropriately,":[161],"addressing":[162],"challenges":[163],"like":[164],"cost,":[165],"privacy,":[166],"reproducibility":[168],"concerns":[169],"associated":[170],"closed-source":[172],"LLMs.":[174],"CONCLUSION:":[175],"underscores":[178],"opportunity":[180],"encourage":[188],"further":[189],"applications":[192],"field,":[195],"annotated":[197],"LLM,":[203],"Trial-LLAMA,":[204],"are":[205],"released":[206],"public":[208],"use.":[209]},"counts_by_year":[{"year":2026,"cited_by_count":12},{"year":2025,"cited_by_count":34},{"year":2024,"cited_by_count":14}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}