{"id":"https://openalex.org/W7113900579","doi":"https://doi.org/10.1145/3765612.3767193","title":"Retrieval-Reasoning Large Language Model-based Synthetic Clinical Trial Generation","display_name":"Retrieval-Reasoning Large Language Model-based Synthetic Clinical Trial Generation","publication_year":2025,"publication_date":"2025-10-12","ids":{"openalex":"https://openalex.org/W7113900579","doi":"https://doi.org/10.1145/3765612.3767193"},"language":null,"primary_location":{"id":"doi:10.1145/3765612.3767193","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3765612.3767193","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3765612.3767193","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 16th ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3765612.3767193","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Zerui Xu","orcid":"https://orcid.org/0009-0001-0237-6891"},"institutions":[{"id":"https://openalex.org/I39422238","display_name":"University of Illinois Chicago","ror":"https://ror.org/02mpq6x41","country_code":"US","type":"education","lineage":["https://openalex.org/I39422238"]},{"id":"https://openalex.org/I40347166","display_name":"University of Chicago","ror":"https://ror.org/024mw5h28","country_code":"US","type":"education","lineage":["https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Zerui Xu","raw_affiliation_strings":["University of Chicago, Chicago, IL, USA"],"affiliations":[{"raw_affiliation_string":"University of Chicago, Chicago, IL, USA","institution_ids":["https://openalex.org/I40347166","https://openalex.org/I39422238"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Fang Wu","orcid":"https://orcid.org/0000-0001-7240-3915"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fang Wu","raw_affiliation_strings":["Stanford University, Stanford, CA, USA"],"affiliations":[{"raw_affiliation_string":"Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yingzhou Lu","orcid":"https://orcid.org/0009-0008-7774-6018"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yingzhou Lu","raw_affiliation_strings":["Stanford University, Stanford, CA, USA"],"affiliations":[{"raw_affiliation_string":"Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yuanyuan Zhang","orcid":"https://orcid.org/0000-0002-0565-6813"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuanyuan Zhang","raw_affiliation_strings":["Purdue University, West Lafayette, IN, USA"],"affiliations":[{"raw_affiliation_string":"Purdue University, West Lafayette, IN, USA","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"last","author":{"id":null,"display_name":"Yue Zhao","orcid":"https://orcid.org/0000-0003-3401-4921"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yue Zhao","raw_affiliation_strings":["University of Southern California, Los Angeles, CA, USA"],"affiliations":[{"raw_affiliation_string":"University of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I39422238","https://openalex.org/I40347166"],"apc_list":null,"apc_paid":null,"fwci":2.7799,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.94231074,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13702","display_name":"Machine Learning in Healthcare","score":0.4699000120162964,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.4699000120162964,"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":0.09790000319480896,"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/T10028","display_name":"Topic Modeling","score":0.07569999992847443,"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/clinical-trial","display_name":"Clinical trial","score":0.6983000040054321},{"id":"https://openalex.org/keywords/synthetic-data","display_name":"Synthetic data","score":0.527899980545044},{"id":"https://openalex.org/keywords/real-world-data","display_name":"Real world data","score":0.45910000801086426},{"id":"https://openalex.org/keywords/timeline","display_name":"Timeline","score":0.4187000095844269},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.3727000057697296},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.36719998717308044},{"id":"https://openalex.org/keywords/data-manipulation-language","display_name":"Data manipulation language","score":0.3564999997615814}],"concepts":[{"id":"https://openalex.org/C535046627","wikidata":"https://www.wikidata.org/wiki/Q30612","display_name":"Clinical trial","level":2,"score":0.6983000040054321},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6410999894142151},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5716000199317932},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.565500020980835},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.527899980545044},{"id":"https://openalex.org/C3020493868","wikidata":"https://www.wikidata.org/wiki/Q55631277","display_name":"Real world data","level":2,"score":0.45910000801086426},{"id":"https://openalex.org/C4438859","wikidata":"https://www.wikidata.org/wiki/Q186117","display_name":"Timeline","level":2,"score":0.4187000095844269},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.3727000057697296},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.36719998717308044},{"id":"https://openalex.org/C56288433","wikidata":"https://www.wikidata.org/wiki/Q58673","display_name":"Data manipulation language","level":2,"score":0.3564999997615814},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3506999909877777},{"id":"https://openalex.org/C47487241","wikidata":"https://www.wikidata.org/wiki/Q5227230","display_name":"Data access","level":2,"score":0.33009999990463257},{"id":"https://openalex.org/C2776187449","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Natural language generation","level":3,"score":0.3262999951839447},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.32109999656677246},{"id":"https://openalex.org/C91632574","wikidata":"https://www.wikidata.org/wiki/Q15088675","display_name":"Data curation","level":2,"score":0.30059999227523804},{"id":"https://openalex.org/C19527891","wikidata":"https://www.wikidata.org/wiki/Q1120908","display_name":"Medical physics","level":1,"score":0.29350000619888306},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2791999876499176},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.27810001373291016},{"id":"https://openalex.org/C72634772","wikidata":"https://www.wikidata.org/wiki/Q386824","display_name":"Data integration","level":2,"score":0.2687999904155731},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.26010000705718994},{"id":"https://openalex.org/C163763905","wikidata":"https://www.wikidata.org/wiki/Q17075943","display_name":"Precision medicine","level":2,"score":0.25429999828338623}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3765612.3767193","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3765612.3767193","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3765612.3767193","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 16th ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3765612.3767193","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3765612.3767193","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3765612.3767193","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 16th ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7113900579.pdf","grobid_xml":"https://content.openalex.org/works/W7113900579.grobid-xml"},"referenced_works_count":15,"referenced_works":["https://openalex.org/W2615117870","https://openalex.org/W2736368095","https://openalex.org/W2911489562","https://openalex.org/W2934399013","https://openalex.org/W3103102495","https://openalex.org/W3156857592","https://openalex.org/W3166254754","https://openalex.org/W3197418972","https://openalex.org/W4210389911","https://openalex.org/W4285138744","https://openalex.org/W4290927873","https://openalex.org/W4306893570","https://openalex.org/W4392978897","https://openalex.org/W4405427526","https://openalex.org/W4405427539"],"related_works":[],"abstract_inverted_index":{"Machine":[0],"learning":[1],"(ML)":[2],"holds":[3],"great":[4],"promise":[5],"for":[6,161],"clinical":[7,30,50,72,106,143,166],"applications":[8],"but":[9],"is":[10,170],"often":[11],"hindered":[12],"by":[13],"limited":[14],"access":[15],"to":[16,20,47,69,86,98,139],"high-quality":[17],"data":[18,93,154,163],"due":[19],"privacy":[21],"concerns,":[22],"high":[23],"costs,":[24],"and":[25,94],"long":[26],"timelines":[27],"associated":[28],"with":[29,67,76],"trials.":[31],"While":[32],"large":[33],"language":[34],"models":[35],"(LLMs)":[36],"have":[37],"demonstrated":[38],"strong":[39],"performance":[40,141],"in":[41,165],"general-purpose":[42],"generation":[43,89],"tasks,":[44],"their":[45,132],"application":[46],"synthesizing":[48],"realistic":[49],"trials":[51,107,117],"remains":[52],"underexplored.":[53],"In":[54],"this":[55],"work,":[56],"we":[57],"propose":[58],"a":[59,83,95,123,158],"novel":[60],"Retrieval-Reasoning":[61],"framework":[62],"that":[63,113,135,151],"leverages":[64],"few-shot":[65],"prompting":[66],"LLMs":[68],"generate":[70],"synthetic":[71,116,127,153],"trial":[73,92,144],"reports":[74],"annotated":[75],"binary":[77],"success/failure":[78],"outcomes.":[79],"Our":[80,148],"approach":[81],"integrates":[82],"retrieval":[84],"module":[85,97],"ground":[87],"the":[88,109,114],"on":[90,104,126,142],"relevant":[91],"reasoning":[96],"ensure":[99],"domain-consistent":[100],"justifications.":[101],"Experiments":[102],"conducted":[103],"real":[105,120,129],"from":[108],"ClinicalTrials.gov":[110],"database":[111],"demonstrate":[112],"generated":[115],"effectively":[118],"augment":[119],"datasets.":[121],"Fine-tuning":[122],"BioBERT":[124],"classifier":[125],"data,":[128,130],"or":[131],"combination":[133],"shows":[134],"hybrid":[136],"fine-tuning":[137],"leads":[138],"improved":[140],"outcome":[145],"prediction":[146],"tasks.":[147],"results":[149],"suggest":[150],"LLM-based":[152],"can":[155],"serve":[156],"as":[157],"powerful":[159],"tool":[160],"privacy-preserving":[162],"augmentation":[164],"research.":[167],"The":[168],"code":[169],"available":[171],"at":[172],"https://github.com/XuZR3x/Retrieval_Reasoning_Clinical_Trial_Generation.":[173]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-09T07:00:12.390032","created_date":"2025-12-11T00:00:00"}