{"id":"https://openalex.org/W7214646443","doi":"https://doi.org/10.64898/2026.09.24.754051","title":"Large language model-based bibliometric evaluation of population descriptors in human genetics","display_name":"Large language model-based bibliometric evaluation of population descriptors in human genetics","publication_year":2026,"publication_date":"2026-09-28","ids":{"openalex":"https://openalex.org/W7214646443","doi":"https://doi.org/10.64898/2026.09.24.754051","pmid":"https://pubmed.ncbi.nlm.nih.gov/42856267","pmcid":"https://www.ncbi.nlm.nih.gov/pmc/articles/13648457"},"language":"en","primary_location":{"id":"doi:10.64898/2026.09.24.754051","doi":"https://doi.org/10.64898/2026.09.24.754051","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.09.24.754051","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/09/28/2026.09.24.754051.full.pdf","source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.biorxiv.org/content/biorxiv/early/2026/09/28/2026.09.24.754051.full.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5081885552","display_name":"Stephanie M. Gogarten","orcid":"https://orcid.org/0000-0002-7231-9745","observed_orcids":["https://orcid.org/0000-0002-7231-9745"]},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]},{"id":"https://openalex.org/I4210089486","display_name":"Fred Hutch Cancer Center","ror":"https://ror.org/007ps6h72","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210089486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Stephanie M. Gogarten","raw_affiliation_strings":["Department of Biostatistics, University of Washington, Seattle, WA","Herbold Computational Biology Program, Public Health Sciences Division, Fred Hutchinson Cancer Center, Seattle, WA"],"raw_orcid":"https://orcid.org/0000-0002-7231-9745","affiliations":[{"raw_affiliation_string":"Department of Biostatistics, University of Washington, Seattle, WA","institution_ids":["https://openalex.org/I201448701"]},{"raw_affiliation_string":"Herbold Computational Biology Program, Public Health Sciences Division, Fred Hutchinson Cancer Center, Seattle, WA","institution_ids":["https://openalex.org/I4210089486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083040136","display_name":"Daphne Oluwaseun Martschenko","orcid":"https://orcid.org/0000-0002-9046-5893","observed_orcids":["https://orcid.org/0000-0002-9046-5893"]},"institutions":[{"id":"https://openalex.org/I4210137306","display_name":"Stanford Medicine","ror":"https://ror.org/03mtd9a03","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I4210137306","https://openalex.org/I97018004"]},{"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":"Daphne O. Martschenko","raw_affiliation_strings":["Department of Pediatrics, Stanford Medicine, Stanford, CA","Laurie J. Girand Center for Biomedical Ethics, Stanford Medicine, Stanford, CA"],"raw_orcid":"https://orcid.org/0000-0002-9046-5893","affiliations":[{"raw_affiliation_string":"Department of Pediatrics, Stanford Medicine, Stanford, CA","institution_ids":["https://openalex.org/I4210137306","https://openalex.org/I97018004"]},{"raw_affiliation_string":"Laurie J. Girand Center for Biomedical Ethics, Stanford Medicine, Stanford, CA","institution_ids":["https://openalex.org/I4210137306","https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Roshni Patel","orcid":"https://orcid.org/0000-0002-8574-031X","observed_orcids":["https://orcid.org/0000-0002-8574-031X"]},"institutions":[{"id":"https://openalex.org/I181233156","display_name":"University of Oregon","ror":"https://ror.org/0293rh119","country_code":"US","type":"education","lineage":["https://openalex.org/I181233156"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Roshni Patel","raw_affiliation_strings":["Department of Data Science, University of Oregon, Eugene, OR","Institute for Ecology and Evolution, University of Oregon, Eugene, OR"],"raw_orcid":"https://orcid.org/0000-0002-8574-031X","affiliations":[{"raw_affiliation_string":"Department of Data Science, University of Oregon, Eugene, OR","institution_ids":["https://openalex.org/I181233156"]},{"raw_affiliation_string":"Institute for Ecology and Evolution, University of Oregon, Eugene, OR","institution_ids":["https://openalex.org/I181233156"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002455648","display_name":"Nasa Sinnott-Armstrong","orcid":"https://orcid.org/0000-0003-4490-0601","observed_orcids":["https://orcid.org/0000-0003-4490-0601"]},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]},{"id":"https://openalex.org/I4210089486","display_name":"Fred Hutch Cancer Center","ror":"https://ror.org/007ps6h72","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210089486"]},{"id":"https://openalex.org/I4210135134","display_name":"Brotman Baty Institute","ror":"https://ror.org/03jxvbk42","country_code":"US","type":"facility","lineage":["https://openalex.org/I4210135134"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Nasa Sinnott-Armstrong","raw_affiliation_strings":["Brotman Baty Institute, University of Washington, Seattle, WA","Department of Genome Sciences, University of Washington, Seattle, WA","Herbold Computational Biology Program, Public Health Sciences Division, Fred Hutchinson Cancer Center, Seattle, WA"],"raw_orcid":"https://orcid.org/0000-0003-4490-0601","affiliations":[{"raw_affiliation_string":"Brotman Baty Institute, University of Washington, Seattle, WA","institution_ids":["https://openalex.org/I201448701","https://openalex.org/I4210135134"]},{"raw_affiliation_string":"Department of Genome Sciences, University of Washington, Seattle, WA","institution_ids":["https://openalex.org/I201448701"]},{"raw_affiliation_string":"Herbold Computational Biology Program, Public Health Sciences Division, Fred Hutchinson Cancer Center, Seattle, WA","institution_ids":["https://openalex.org/I4210089486"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5002455648"],"corresponding_institution_ids":["https://openalex.org/I201448701","https://openalex.org/I4210089486","https://openalex.org/I4210135134"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12749","display_name":"Race, Genetics, and Society","score":0.9955999851226807,"subfield":{"id":"https://openalex.org/subfields/3314","display_name":"Anthropology"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T12749","display_name":"Race, Genetics, and Society","score":0.9955999851226807,"subfield":{"id":"https://openalex.org/subfields/3314","display_name":"Anthropology"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10102","display_name":"scientometrics and bibliometrics research","score":0.0015999999595806003,"subfield":{"id":"https://openalex.org/subfields/3309","display_name":"Library and Information Sciences"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10261","display_name":"Genetic Associations and Epidemiology","score":0.00139999995008111,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/genome-wide-association-study","display_name":"genome-wide association study","score":0.8080000281333923},{"id":"https://openalex.org/keywords/gwas-catalog","display_name":"GWAS Catalog","score":0.7990000247955322},{"id":"https://openalex.org/keywords/human-genetics-research","display_name":"human genetic research","score":0.5099999904632568}],"concepts":[{"id":"https://openalex.org/C9354725","wikidata":"https://www.wikidata.org/wiki/Q286017","display_name":"Operationalization","level":2,"score":0.6342999935150146},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.5784000158309937},{"id":"https://openalex.org/C47042493","wikidata":"https://www.wikidata.org/wiki/Q265799","display_name":"Human genetics","level":3,"score":0.5228999853134155},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.5188000202178955},{"id":"https://openalex.org/C2779473830","wikidata":"https://www.wikidata.org/wiki/Q1540899","display_name":"MEDLINE","level":2,"score":0.4194999933242798},{"id":"https://openalex.org/C189206191","wikidata":"https://www.wikidata.org/wiki/Q222046","display_name":"Genomics","level":4,"score":0.41620001196861267},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.4041999876499176},{"id":"https://openalex.org/C555299818","wikidata":"https://www.wikidata.org/wiki/Q15709513","display_name":"Statistical genetics","level":5,"score":0.3953999876976013},{"id":"https://openalex.org/C40583040","wikidata":"https://www.wikidata.org/wiki/Q1502105","display_name":"Human genetic variation","level":5,"score":0.3774000108242035},{"id":"https://openalex.org/C106208931","wikidata":"https://www.wikidata.org/wiki/Q1098876","display_name":"Genome-wide association study","level":5,"score":0.3725999891757965},{"id":"https://openalex.org/C64474127","wikidata":"https://www.wikidata.org/wiki/Q1071953","display_name":"Medical genetics","level":3,"score":0.36880001425743103},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.3481999933719635},{"id":"https://openalex.org/C178315738","wikidata":"https://www.wikidata.org/wiki/Q603441","display_name":"Bibliometrics","level":2,"score":0.3418000042438507},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.32679998874664307},{"id":"https://openalex.org/C186413461","wikidata":"https://www.wikidata.org/wiki/Q744727","display_name":"Genetic association","level":5,"score":0.32330000400543213},{"id":"https://openalex.org/C2778149918","wikidata":"https://www.wikidata.org/wiki/Q3291156","display_name":"Population health","level":3,"score":0.3192000091075897},{"id":"https://openalex.org/C85721925","wikidata":"https://www.wikidata.org/wiki/Q31151","display_name":"Population genetics","level":3,"score":0.3075000047683716},{"id":"https://openalex.org/C138816342","wikidata":"https://www.wikidata.org/wiki/Q189603","display_name":"Public health","level":2,"score":0.2964000105857849},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.2842999994754791},{"id":"https://openalex.org/C3017944768","wikidata":"https://www.wikidata.org/wiki/Q1450463","display_name":"Poison control","level":2,"score":0.28380000591278076},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.28290000557899475},{"id":"https://openalex.org/C197077220","wikidata":"https://www.wikidata.org/wiki/Q720988","display_name":"Human genome","level":4,"score":0.2815999984741211},{"id":"https://openalex.org/C184356942","wikidata":"https://www.wikidata.org/wiki/Q830382","display_name":"Best practice","level":2,"score":0.27799999713897705},{"id":"https://openalex.org/C2992545694","wikidata":"https://www.wikidata.org/wiki/Q1071953","display_name":"Genomic medicine","level":2,"score":0.25999999046325684},{"id":"https://openalex.org/C2993807623","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genetic data","level":3,"score":0.259799987077713},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.25540000200271606}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.64898/2026.09.24.754051","doi":"https://doi.org/10.64898/2026.09.24.754051","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.09.24.754051","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/09/28/2026.09.24.754051.full.pdf","source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},{"id":"pmh:oai:pubmedcentral.nih.gov:13648457","doi":null,"is_oa":true,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/42856267/","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC13648457/pdf/nihpp-2026.09.24.754051v1.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,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"bioRxiv","raw_type":"Text"},{"id":"pmid:42856267","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/42856267","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,"listed_in":[],"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":"bioRxiv : the preprint server for biology","raw_type":"Journal Article"}],"best_oa_location":{"id":"doi:10.64898/2026.09.24.754051","doi":"https://doi.org/10.64898/2026.09.24.754051","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.09.24.754051","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/09/28/2026.09.24.754051.full.pdf","source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G9000862581","display_name":"An integrative omics approach to investigate gene-environment interaction in colorectal cancer risk","funder_award_id":"R01CA273198","funder_id":"https://openalex.org/F4320337351","funder_display_name":"National Cancer Institute"},{"id":"https://openalex.org/G9000873780","display_name":"Technology to understand genetic variant effects in context","funder_award_id":"RM1HG010461","funder_id":"https://openalex.org/F4320337348","funder_display_name":"National Human Genome Research Institute"}],"funders":[{"id":"https://openalex.org/F4320337348","display_name":"National Human Genome Research Institute","ror":"https://ror.org/00baak391"},{"id":"https://openalex.org/F4320337351","display_name":"National Cancer Institute","ror":"https://ror.org/040gcmg81"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7214646443.pdf","grobid_xml":"https://content.openalex.org/works/W7214646443.grobid-xml"},"referenced_works_count":28,"referenced_works":["https://openalex.org/W2116868464","https://openalex.org/W2154643978","https://openalex.org/W2531587846","https://openalex.org/W2559028527","https://openalex.org/W2573712238","https://openalex.org/W2574499356","https://openalex.org/W2785412624","https://openalex.org/W2884940558","https://openalex.org/W2906964061","https://openalex.org/W2922534626","https://openalex.org/W2976146569","https://openalex.org/W2998553072","https://openalex.org/W3014681107","https://openalex.org/W3046092183","https://openalex.org/W3134271116","https://openalex.org/W3171258943","https://openalex.org/W3205412600","https://openalex.org/W3217582756","https://openalex.org/W4211005061","https://openalex.org/W4288045432","https://openalex.org/W4308616307","https://openalex.org/W4324284865","https://openalex.org/W4394603158","https://openalex.org/W4408336406","https://openalex.org/W4411981621","https://openalex.org/W4412767310","https://openalex.org/W7138907875","https://openalex.org/W7203605819"],"related_works":["https://openalex.org/W7167631576","https://openalex.org/W2005606081","https://openalex.org/W4392702578","https://openalex.org/W4309410063","https://openalex.org/W4224792605","https://openalex.org/W4394912772","https://openalex.org/W7095437421","https://openalex.org/W2171703627","https://openalex.org/W4411238465","https://openalex.org/W4253265805"],"abstract_inverted_index":{"Abstract":[0],"As":[1],"the":[2,35,75,89,98,119,136,166,169,174,199],"use":[3,79,88,99],"of":[4,38,80,100,168,181,201],"population":[5,81,101],"descriptors":[6,82,102],"such":[7],"as":[8,93,178],"race,":[9],"ethnicity,":[10],"and":[11,41,53,68,77,126,142],"ancestry":[12],"have":[13,22],"become":[14],"increasingly":[15],"common":[16],"in":[17,33,51,83,103,154,198],"modern":[18],"genetics":[19],"research,":[20],"there":[21],"been":[23],"growing":[24],"calls":[25],"to":[26,73,96,130,156],"critically":[27],"examine":[28],"their":[29],"use.":[30],"Most":[31],"notably,":[32],"2023,":[34],"National":[36],"Academies":[37],"Science,":[39],"Engineering,":[40],"Medicine":[42],"(NASEM)":[43],"published":[44,139],"a":[45,94,110,179,187],"report":[46,92,158,171,175],"titled":[47],"Using":[48],"Population":[49],"Descriptors":[50],"Genetics":[52],"Genomics":[54],"Research:":[55],"A":[56],"New":[57],"Framework":[58],"for":[59,71,113,189,196],"an":[60,123],"Evolving":[61],"Field":[62],",":[63],"which":[64],"included":[65],"eight":[66],"specific":[67],"actionable":[69],"recommendations":[70,121,159],"researchers":[72],"implement":[74],"ethical":[76],"accurate":[78],"genetic":[84],"research.":[85],"Here,":[86],"we":[87],"2023":[90],"NASEM":[91,157,170],"benchmark":[95],"analyze":[97],"genome-wide":[104],"association":[105],"studies":[106],"(GWAS).":[107],"We":[108,150,191],"develop":[109],"general":[111],"toolkit":[112],"large":[114],"language":[115],"model-based":[116],"bibliometrics,":[117],"operationalize":[118],"report\u2019s":[120],"into":[122],"evaluation":[124],"framework,":[125],"apply":[127],"this":[128],"framework":[129],"evaluate":[131],"all":[132],"4,007":[133],"papers":[134],"from":[135],"GWAS":[137],"Catalog":[138],"between":[140],"2007":[141],"2025":[143],"with":[144],"full":[145],"text":[146],"available":[147],"on":[148],"PubMedCentral.":[149],"find":[151],"significant":[152],"improvements":[153,164],"adherence":[155],"over":[160],"time.":[161],"However,":[162],"most":[163],"predate":[165],"publication":[167],"itself,":[172],"suggesting":[173],"functioned":[176],"primarily":[177],"synthesis":[180],"existing":[182],"best":[183],"practices":[184],"rather":[185],"than":[186],"catalyst":[188],"change.":[190],"conclude":[192],"by":[193],"highlighting":[194],"opportunities":[195],"growth":[197],"field":[200],"human":[202],"genetics.":[203]},"counts_by_year":[],"updated_date":"2026-11-09T13:22:03.289127","created_date":"2026-09-29T00:00:00"}
