{"id":"https://openalex.org/W7161380099","doi":"https://doi.org/10.1186/s13040-026-00562-0","title":"Automated candidate confounder scoping for adjustment in clinical research: a retrieval-augmented generation approach","display_name":"Automated candidate confounder scoping for adjustment in clinical research: a retrieval-augmented generation approach","publication_year":2026,"publication_date":"2026-05-16","ids":{"openalex":"https://openalex.org/W7161380099","doi":"https://doi.org/10.1186/s13040-026-00562-0","pmid":"https://pubmed.ncbi.nlm.nih.gov/42143370"},"language":"en","primary_location":{"id":"doi:10.1186/s13040-026-00562-0","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13040-026-00562-0","pdf_url":null,"source":{"id":"https://openalex.org/S84409260","display_name":"BioData Mining","issn_l":"1756-0381","issn":["1756-0381"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BioData Mining","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1186/s13040-026-00562-0","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5136313032","display_name":"Jingjing Li","orcid":null},"institutions":[{"id":"https://openalex.org/I4210090327","display_name":"Liuzhou Maternal and Child Health Hospital","ror":"https://ror.org/00fbwv278","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210090327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingjing Li","raw_affiliation_strings":["Liuzhou Maternity and Child Healthcare Hospital, Liuzhou, 545006, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Liuzhou Maternity and Child Healthcare Hospital, Liuzhou, 545006, China","institution_ids":["https://openalex.org/I4210090327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136288065","display_name":"Kesong Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I146584863","display_name":"Children's Medical Research Institute","ror":"https://ror.org/01bsaey45","country_code":"AU","type":"facility","lineage":["https://openalex.org/I146584863"]},{"id":"https://openalex.org/I165143802","display_name":"The University of Queensland","ror":"https://ror.org/00rqy9422","country_code":"AU","type":"education","lineage":["https://openalex.org/I165143802"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Kesong Wu","raw_affiliation_strings":["Ian Frazer Centre for Children's Immunotherapy Research, The University of Queensland, Brisbane, QLD, 4101, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ian Frazer Centre for Children's Immunotherapy Research, The University of Queensland, Brisbane, QLD, 4101, Australia","institution_ids":["https://openalex.org/I146584863","https://openalex.org/I165143802"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136307709","display_name":"Xiao Wang","orcid":"https://orcid.org/0000-0003-4512-8131"},"institutions":[{"id":"https://openalex.org/I4210126918","display_name":"GlyTech (United States)","ror":"https://ror.org/02pep9116","country_code":"US","type":"company","lineage":["https://openalex.org/I4210126918"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiao Wang","raw_affiliation_strings":["RYTECH, Wuhan, 430074, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"RYTECH, Wuhan, 430074, China","institution_ids":["https://openalex.org/I4210126918"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136295764","display_name":"Ruolin Tao","orcid":null},"institutions":[{"id":"https://openalex.org/I4210156804","display_name":"First Affiliated Hospital of Zhengzhou University","ror":"https://ror.org/056swr059","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210156804"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruolin Tao","raw_affiliation_strings":["The First Affiliated Hospital of Zhengzhou University, Zhengzhou, 450000, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The First Affiliated Hospital of Zhengzhou University, Zhengzhou, 450000, China","institution_ids":["https://openalex.org/I4210156804"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100686150","display_name":"Yinyao Ma","orcid":"https://orcid.org/0000-0002-2755-2169"},"institutions":[{"id":"https://openalex.org/I4210115919","display_name":"The People's Hospital of Guangxi Zhuang Autonomous Region","ror":"https://ror.org/02aa8kj12","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210115919"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yinyao Ma","raw_affiliation_strings":["People's Hospital of Guangxi Zhuang Autonomous Region, Nanning, 530016, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"People's Hospital of Guangxi Zhuang Autonomous Region, Nanning, 530016, China","institution_ids":["https://openalex.org/I4210115919"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038754214","display_name":"Hanlin Lv","orcid":"https://orcid.org/0000-0002-1876-7846"},"institutions":[{"id":"https://openalex.org/I4210126918","display_name":"GlyTech (United States)","ror":"https://ror.org/02pep9116","country_code":"US","type":"company","lineage":["https://openalex.org/I4210126918"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hanlin Lv","raw_affiliation_strings":["RYTECH, Wuhan, 430074, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"RYTECH, Wuhan, 430074, China","institution_ids":["https://openalex.org/I4210126918"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136320130","display_name":"Xueqian Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I4210123628","display_name":"Guangxi Zhuang Autonomous Region Brain Hospital","ror":"https://ror.org/02cgt3c05","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210123628"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xueqian Zhao","raw_affiliation_strings":["Chest Hospital of Guangxi Zhuang Autonomous Region, Liuzhou, 545005, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chest Hospital of Guangxi Zhuang Autonomous Region, Liuzhou, 545005, China","institution_ids":["https://openalex.org/I4210123628"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006720503","display_name":"Yu Lan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210123628","display_name":"Guangxi Zhuang Autonomous Region Brain Hospital","ror":"https://ror.org/02cgt3c05","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210123628"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Lan","raw_affiliation_strings":["Chest Hospital of Guangxi Zhuang Autonomous Region, Liuzhou, 545005, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chest Hospital of Guangxi Zhuang Autonomous Region, Liuzhou, 545005, China","institution_ids":["https://openalex.org/I4210123628"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136290511","display_name":"Lei Li","orcid":null},"institutions":[{"id":"https://openalex.org/I4210090971","display_name":"Southeast University","ror":"https://ror.org/00cf0ab87","country_code":"BD","type":"education","lineage":["https://openalex.org/I4210090971"]},{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["BD","CN"],"is_corresponding":true,"raw_author_name":"Lei Li","raw_affiliation_strings":["School of Life Science and Technology, Southeast University, Nanjing, 210096, China. lei.li@seu.edu.cn"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Life Science and Technology, Southeast University, Nanjing, 210096, China. lei.li@seu.edu.cn","institution_ids":["https://openalex.org/I4210090971","https://openalex.org/I76569877"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5136296050","display_name":"Lei Wang","orcid":"https://orcid.org/0000-0002-7584-8802"},"institutions":[{"id":"https://openalex.org/I1306686416","display_name":"RTX (United States)","ror":"https://ror.org/0354t7b78","country_code":"US","type":"company","lineage":["https://openalex.org/I1306686416"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Lei Wang","raw_affiliation_strings":["RYTECH, Wuhan, 430074, China. raywong2121@gmail.com"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"RYTECH, Wuhan, 430074, China. raywong2121@gmail.com","institution_ids":["https://openalex.org/I1306686416"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":10,"corresponding_author_ids":["https://openalex.org/A5136290511","https://openalex.org/A5136296050"],"corresponding_institution_ids":["https://openalex.org/I1306686416","https://openalex.org/I4210090971","https://openalex.org/I76569877"],"apc_list":{"value":2490,"currency":"USD","value_usd":2490},"apc_paid":{"value":2490,"currency":"USD","value_usd":2490},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.52165385,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"19","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.10620000213384628,"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"}},"topics":[{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.10620000213384628,"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/T10206","display_name":"Meta-analysis and systematic reviews","score":0.06790000200271606,"subfield":{"id":"https://openalex.org/subfields/1804","display_name":"Statistics, Probability and Uncertainty"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","score":0.04639999940991402,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/key","display_name":"Key (lock)","score":0.3725000023841858},{"id":"https://openalex.org/keywords/confounding","display_name":"Confounding","score":0.314300000667572},{"id":"https://openalex.org/keywords/medline","display_name":"MEDLINE","score":0.2793999910354614},{"id":"https://openalex.org/keywords/data-collection","display_name":"Data collection","score":0.2628999948501587}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6664999723434448},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4043000042438507},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3725000023841858},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.3257000148296356},{"id":"https://openalex.org/C77350462","wikidata":"https://www.wikidata.org/wiki/Q1125472","display_name":"Confounding","level":2,"score":0.314300000667572},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.30160000920295715},{"id":"https://openalex.org/C2779473830","wikidata":"https://www.wikidata.org/wiki/Q1540899","display_name":"MEDLINE","level":2,"score":0.2793999910354614},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.2628999948501587},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.24379999935626984},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.23170000314712524}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1186/s13040-026-00562-0","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13040-026-00562-0","pdf_url":null,"source":{"id":"https://openalex.org/S84409260","display_name":"BioData Mining","issn_l":"1756-0381","issn":["1756-0381"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BioData Mining","raw_type":"journal-article"},{"id":"pmid:42143370","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/42143370","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":"BioData mining","raw_type":null},{"id":"pmh:oai:doaj.org/article:09909fabd7e0488ca59069fc97574823","is_oa":false,"landing_page_url":"https://doaj.org/article/09909fabd7e0488ca59069fc97574823","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BioData Mining, Vol 19, Iss 1 (2026)","raw_type":"article"},{"id":"pmh:oai:pubmedcentral.nih.gov:13295572","is_oa":true,"landing_page_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC13295572/","pdf_url":null,"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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BioData Min","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1186/s13040-026-00562-0","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13040-026-00562-0","pdf_url":null,"source":{"id":"https://openalex.org/S84409260","display_name":"BioData Mining","issn_l":"1756-0381","issn":["1756-0381"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BioData Mining","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1606743198","display_name":null,"funder_award_id":"AB25069049","funder_id":"https://openalex.org/F4320336589","funder_display_name":"Guangxi Key Research and Development Program"}],"funders":[{"id":"https://openalex.org/F4320336589","display_name":"Guangxi Key Research and Development Program","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W2025309870","https://openalex.org/W2025872262","https://openalex.org/W2029938449","https://openalex.org/W2082995348","https://openalex.org/W2103881469","https://openalex.org/W2111722073","https://openalex.org/W2117446654","https://openalex.org/W2523396458","https://openalex.org/W2921495327","https://openalex.org/W3023409205","https://openalex.org/W3026298482","https://openalex.org/W3026780066","https://openalex.org/W3137465950","https://openalex.org/W4206657737","https://openalex.org/W4285588825","https://openalex.org/W4287597699","https://openalex.org/W4310964482","https://openalex.org/W4323928271","https://openalex.org/W4395026179","https://openalex.org/W4396768342","https://openalex.org/W4407978474","https://openalex.org/W4410039606","https://openalex.org/W4413094313","https://openalex.org/W7084113970"],"related_works":[],"abstract_inverted_index":{"BACKGROUND:":[0],"Identifying":[1],"confounding":[2],"variables":[3],"is":[4,15],"fundamental":[5],"for":[6,21,74,111,191],"robust":[7],"observational":[8,77,246],"studies,":[9],"yet":[10],"the":[11,166],"traditional":[12],"manual":[13],"process":[14],"a":[16,30,67,80,89,108,150,158,183,195,228],"time-consuming":[17],"and":[18,53,56,65,126,147,154,193,238,261],"subjective":[19],"barrier":[20],"researchers.":[22],"Recent":[23],"advances":[24],"in":[25,76,250],"Retrieval-Augmented":[26],"Generation":[27],"(RAG)":[28],"offer":[29],"promising":[31],"solution,":[32],"but":[33],"most":[34],"existing":[35],"systems":[36],"rely":[37],"on":[38,121],"full-text":[39],"access,":[40],"cloud-hosted":[41],"APIs,":[42],"or":[43,255],"manually":[44],"curated":[45],"knowledge":[46],"graphs,":[47],"raising":[48],"concerns":[49],"about":[50],"privacy,":[51],"copyright,":[52],"computational":[54],"cost,":[55],"making":[57],"local":[58,124],"deployment":[59],"difficult.":[60],"OBJECTIVE:":[61],"This":[62],"study":[63,247],"developed":[64],"evaluated":[66,127],"heuristic":[68],"tool":[69,87],"to":[70,243,258],"scope":[71],"candidate":[72,93,115,187,240],"confounders":[73,94,188],"adjustment":[75,192],"studies.":[78],"Using":[79],"locally":[81,229],"deployed,":[82,230],"abstract-only":[83,231],"RAG":[84,232],"architecture,":[85],"our":[86],"generates":[88],"traceable":[90,239],"shortlist":[91],"of":[92,114,185,197,221],"from":[95],"PICO":[96,131],"(Population,":[97],"Intervention,":[98],"Comparison,":[99],"Outcome)":[100],"queries":[101,132],"over":[102],"medical":[103],"abstracts.":[104],"METHODS:":[105],"We":[106],"implemented":[107],"three-stage":[109],"architecture":[110],"PICO-based":[112],"scoping":[113],"confounder.":[116],"The":[117],"pipeline":[118,167],"was":[119,138,155,208],"deployed":[120],"an":[122,216,225],"all-in-one":[123],"server":[125],"using":[128],"1,000":[129],"expert-curated":[130],"spanning":[133],"20":[134],"clinical":[135,148,218],"specialties.":[136],"Performance":[137],"assessed":[139],"along":[140],"four":[141],"dimensions-internal":[142],"consistency,":[143],"output":[144],"volume,":[145],"efficiency,":[146],"acceptance-by":[149],"multi-institutional":[151],"clinician":[152],"panel,":[153],"compared":[156],"with":[157,252],"graph-only":[159],"SemMedDB":[160],"baseline.":[161],"RESULTS:":[162],"Across":[163],"repeated":[164],"runs,":[165],"showed":[168],"high":[169],"internal":[170],"consistency":[171,175,179],"(candidate":[172],"confounder":[173,241],"list":[174],"94.6%\u00b18.7%;":[176],"PMID":[177],"set":[178],"79.4%\u00b123.5%).":[180],"It":[181],"suggested":[182],"median":[184,196],"6":[186],"(IQR":[189,201,211],"8)":[190],"retrieved":[194],"33":[198],"unique":[199],"PMIDs":[200],"7)":[202],"per":[203],"query.":[204],"Median":[205],"processing":[206],"time":[207],"44.50":[209],"s":[210],"31.72).":[212],"Expert":[213],"review":[214],"yielded":[215],"overall":[217],"acceptance":[219],"rate":[220],"87.12%.":[222],"CONCLUSIONS:":[223],"In":[224],"exploratory":[226],"capacity,":[227],"workflow":[233],"can":[234],"generate":[235],"clinically":[236],"interpretable":[237],"suggestions":[242],"support":[244],"early-stage":[245],"design,":[248],"particularly":[249],"settings":[251],"privacy":[253],"constraints":[254],"limited":[256],"access":[257],"full":[259],"texts":[260],"cloud":[262],"resources.":[263],"TRIAL":[264],"REGISTRATION:":[265],"NA.":[266]},"counts_by_year":[],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2026-05-17T00:00:00"}