{"id":"https://openalex.org/W2995636091","doi":null,"title":"Extracting Country-of-Origin from Electronic Health Records for Gene- Environment Studies as Part of the Epidemiologic Architecture for Genes Linked to Environment (EAGLE) Study.","display_name":"Extracting Country-of-Origin from Electronic Health Records for Gene- Environment Studies as Part of the Epidemiologic Architecture for Genes Linked to Environment (EAGLE) Study.","publication_year":2017,"publication_date":"2017-01-01","ids":{"openalex":"https://openalex.org/W2995636091","mag":"2995636091","pmid":"https://pubmed.ncbi.nlm.nih.gov/28815105","pmcid":"https://www.ncbi.nlm.nih.gov/pmc/articles/5543359"},"language":"en","primary_location":{"id":"pmh:oai:pubmedcentral.nih.gov:5543359","doi":null,"is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/5543359","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,"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":"AMIA Jt Summits Transl Sci Proc","raw_type":"Text"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/5543359","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5027840210","display_name":"Eric H. Farber\u2010Eger","orcid":"https://orcid.org/0000-0003-0281-3796","observed_orcids":["https://orcid.org/0000-0003-0281-3796"]},"institutions":[{"id":"https://openalex.org/I200719446","display_name":"Vanderbilt University","ror":"https://ror.org/02vm5rt34","country_code":"US","type":"education","lineage":["https://openalex.org/I200719446"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eric Farber-Eger","raw_affiliation_strings":["Center for Human Genetics Research, Vanderbilt University, Nashville, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Human Genetics Research, Vanderbilt University, Nashville, USA","institution_ids":["https://openalex.org/I200719446"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004271140","display_name":"Robert Goodloe","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I200719446","display_name":"Vanderbilt University","ror":"https://ror.org/02vm5rt34","country_code":"US","type":"education","lineage":["https://openalex.org/I200719446"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Robert Goodloe","raw_affiliation_strings":["Center for Human Genetics Research, Vanderbilt University, Nashville, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Human Genetics Research, Vanderbilt University, Nashville, USA","institution_ids":["https://openalex.org/I200719446"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jonathan Boston","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I200719446","display_name":"Vanderbilt University","ror":"https://ror.org/02vm5rt34","country_code":"US","type":"education","lineage":["https://openalex.org/I200719446"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jonathan Boston","raw_affiliation_strings":["Center for Human Genetics Research, Vanderbilt University, Nashville, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Human Genetics Research, Vanderbilt University, Nashville, USA","institution_ids":["https://openalex.org/I200719446"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066140517","display_name":"William S. Bush","orcid":"https://orcid.org/0000-0002-9729-6519","observed_orcids":["https://orcid.org/0000-0002-9729-6519"]},"institutions":[{"id":"https://openalex.org/I58956616","display_name":"Case Western Reserve University","ror":"https://ror.org/051fd9666","country_code":"US","type":"education","lineage":["https://openalex.org/I58956616"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"William S Bush","raw_affiliation_strings":["Department of Epidemiology and Biostatistics, Institute for Computational Biology, Case Western Reserve University, Cleveland, OH, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Epidemiology and Biostatistics, Institute for Computational Biology, Case Western Reserve University, Cleveland, OH, USA","institution_ids":["https://openalex.org/I58956616"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039699723","display_name":"Dana C. Crawford","orcid":"https://orcid.org/0000-0002-6437-6248","observed_orcids":["https://orcid.org/0000-0002-6437-6248"]},"institutions":[{"id":"https://openalex.org/I58956616","display_name":"Case Western Reserve University","ror":"https://ror.org/051fd9666","country_code":"US","type":"education","lineage":["https://openalex.org/I58956616"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dana C Crawford","raw_affiliation_strings":["Department of Epidemiology and Biostatistics, Institute for Computational Biology, Case Western Reserve University, Cleveland, OH, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Epidemiology and Biostatistics, Institute for Computational Biology, Case Western Reserve University, Cleveland, OH, USA","institution_ids":["https://openalex.org/I58956616"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1545,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.54691759,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":93},"biblio":{"volume":"2017","issue":null,"first_page":"50","last_page":"57"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10261","display_name":"Genetic Associations and Epidemiology","score":0.45019999146461487,"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"}},"topics":[{"id":"https://openalex.org/T10261","display_name":"Genetic Associations and Epidemiology","score":0.45019999146461487,"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"}},{"id":"https://openalex.org/T12749","display_name":"Race, Genetics, and Society","score":0.1696999967098236,"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.1428000032901764,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/country-of-origin","display_name":"country of origin","score":0.8569999933242798},{"id":"https://openalex.org/keywords/acculturation","display_name":"acculturation","score":0.9580000042915344},{"id":"https://openalex.org/keywords/gene-environment-interaction","display_name":"gene-environment interaction","score":0.8669999837875366},{"id":"https://openalex.org/keywords/electronic-health-records","display_name":"electronic health records","score":0.9539999961853027},{"id":"https://openalex.org/keywords/clinical-narratives","display_name":"clinical text","score":0.6380000114440918},{"id":"https://openalex.org/keywords/regular-expressions","display_name":"regular expressions","score":0.6919999718666077},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"natural language processing","score":0.6700000166893005},{"id":"https://openalex.org/keywords/biorepository","display_name":"biorepository","score":0.6980000138282776},{"id":"https://openalex.org/keywords/african-americans","display_name":"African Americans","score":0.652999997138977},{"id":"https://openalex.org/keywords/hispanic-americans","display_name":"Hispanic Americans","score":0.7089999914169312},{"id":"https://openalex.org/keywords/asians","display_name":"Asians","score":0.6380000114440918},{"id":"https://openalex.org/keywords/migration-patterns","display_name":"migration patterns","score":0.6470000147819519},{"id":"https://openalex.org/keywords/data-cleaning","display_name":"data cleaning","score":0.45899999141693115},{"id":"https://openalex.org/keywords/genetic-association-studies","display_name":"genetic association studies","score":0.6259999871253967}],"concepts":[{"id":"https://openalex.org/C2779101040","wikidata":"https://www.wikidata.org/wiki/Q3373417","display_name":"Country of origin","level":2,"score":0.5701476335525513},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.5365028381347656},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.46900415420532227},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.35756993293762207},{"id":"https://openalex.org/C149923435","wikidata":"https://www.wikidata.org/wiki/Q37732","display_name":"Demography","level":1,"score":0.3290497064590454},{"id":"https://openalex.org/C99454951","wikidata":"https://www.wikidata.org/wiki/Q932068","display_name":"Environmental health","level":1,"score":0.21662235260009766},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.21528419852256775},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.11539244651794434},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:pubmedcentral.nih.gov:5543359","doi":null,"is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/5543359","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,"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":"AMIA Jt Summits Transl Sci Proc","raw_type":"Text"},{"id":"pmid:28815105","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/28815105","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":"AMIA Joint Summits on Translational Science proceedings. AMIA Joint Summits on Translational Science","raw_type":"Journal Article"},{"id":"mag:2995636091","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/28815105","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":null,"is_accepted":false,"is_published":false,"raw_source_name":"PubMed","raw_type":null}],"best_oa_location":{"id":"pmh:oai:pubmedcentral.nih.gov:5543359","doi":null,"is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/5543359","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,"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":"AMIA Jt Summits Transl Sci Proc","raw_type":"Text"},"sustainable_development_goals":[{"score":0.6240000128746033,"id":"https://metadata.un.org/sdg/3","display_name":"Good health and well-being"}],"study_designs":[],"awards":[{"id":"https://openalex.org/G6628171993","display_name":"The Vanderbilt Institute for Clinical and Translational Research (VICTR) UL1","funder_award_id":"UL1RR024975","funder_id":"https://openalex.org/F4320337375","funder_display_name":"National Center for Research Resources"},{"id":"https://openalex.org/G7773456091","display_name":"The Vanderbilt Institute for Clinical and Translational Research (VICTR)","funder_award_id":"UL1TR000445","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G8327342359","display_name":"Epidemiologic Architecture for Genes Linked to Environment (EAGLE)","funder_award_id":"U01HG004798","funder_id":"https://openalex.org/F4320337348","funder_display_name":"National Human Genome Research Institute"}],"funders":[{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320337348","display_name":"National Human Genome Research Institute","ror":"https://ror.org/00baak391"},{"id":"https://openalex.org/F4320337375","display_name":"National Center for Research Resources","ror":"https://ror.org/04pw6fb54"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1534672942","https://openalex.org/W1904660238","https://openalex.org/W1985941759","https://openalex.org/W2006776184","https://openalex.org/W2017406452","https://openalex.org/W2031828491","https://openalex.org/W2050697524","https://openalex.org/W2065051848","https://openalex.org/W2069499899","https://openalex.org/W2073640336","https://openalex.org/W2079824338","https://openalex.org/W2081315887","https://openalex.org/W2084620846","https://openalex.org/W2100429291","https://openalex.org/W2107862628","https://openalex.org/W2111202666","https://openalex.org/W2117446594","https://openalex.org/W2152410429","https://openalex.org/W2155836039","https://openalex.org/W2156443053","https://openalex.org/W2157752701","https://openalex.org/W2159268255","https://openalex.org/W2171777347","https://openalex.org/W2270172181","https://openalex.org/W2554715427"],"related_works":["https://openalex.org/W2902537416","https://openalex.org/W1552885745","https://openalex.org/W2056191085","https://openalex.org/W4361283299","https://openalex.org/W2933568281","https://openalex.org/W2982225266","https://openalex.org/W6921719687","https://openalex.org/W7130923824","https://openalex.org/W2972498194","https://openalex.org/W2369344278"],"abstract_inverted_index":{"We":[0,49,86],"describe":[1],"here":[2],"the":[3,26,39,53,62,123,159,164,171,187,198,205],"extraction":[4],"of":[5,38,70,73,108,114,119,122,148,158,170,177,186],"country-of-origin,":[6],"an":[7,202],"acculturation":[8],"variable":[9],"relevant":[10],"for":[11,29,89,129,140,220],"gene-environment":[12],"studies,":[13],"in":[14,67,105],"a":[15,35,68,120,146,155,180],"biorepository":[16],"linked":[17],"to":[18,32,135,154,197],"de-identified":[19],"electronic":[20],"health":[21],"records":[22],"(EHRs)":[23],"assessed":[24],"by":[25],"Epidemiologic":[27],"Architecture":[28,41],"Genes":[30],"Linked":[31],"Environment":[33],"(EAGLE),":[34],"study":[36],"site":[37],"Population":[40],"using":[42,58],"Genomics":[43],"and":[44,83,99,102,132],"Epidemiology":[45],"(PAGE)":[46],"I":[47],"study.":[48],"extracted":[50,215],"country-of-origin":[51,125,138,156,182,211],"from":[52,216],"unstructured":[54,217],"clinical":[55,115,218],"free":[56],"text":[57,219],"regular":[59],"expressions":[60],"within":[61],"MySQL":[63],"relational":[64],"database":[65],"system":[66],"cohort":[69],"15,863":[71],"subjects":[72,151,178],"mostly":[74],"non-European":[75],"descent":[76],"(including":[77,93],"11,519":[78],"African":[79],"Americans,":[80],"1,702":[81],"Hispanics,":[82],"1,118":[84],"Asians).":[85],"performed":[87],"searches":[88],"231":[90],"world":[91],"countries":[92,188],"independent":[94],"sovereign":[95],"states,":[96],"dependent":[97],"areas,":[98],"disputed":[100],"territories)":[101],"common":[103],"misspellings":[104],">14":[106],"gigabytes":[107],"data":[109,130,144,209],"including":[110],">13":[111],"billion":[112],"characters":[113],"text.":[116],"Manual":[117],"review":[118],"fraction":[121],"initial":[124],"assignments":[126],"established":[127],"rules":[128],"cleaning":[131],"quality":[133],"control":[134],"achieve":[136],"final":[137],"status":[139],"each":[141],"subject.":[142],"After":[143],"cleaning,":[145],"total":[147],"1,911/15,893":[149],"(12.02%)":[150],"were":[152],"assigned":[153,167,189],"outside":[157,169],"United":[160,172,199],"States.":[161],"Mexico":[162],"was":[163],"most":[165],"commonly":[166],"country":[168],"States":[173,200],"(264":[174],"subjects;":[175],"13.8%":[176],"with":[179,201],"foreign":[181],"assignment).":[183],"The":[184],"distribution":[185],"followed":[190],"expectations":[191],"based":[192],"on":[193,204],"known":[194],"migration":[195],"patterns":[196],"emphasis":[203],"southeastern":[206],"region.":[207],"These":[208],"suggest":[210],"can":[212],"be":[213],"successfully":[214],"downstream":[221],"genetic":[222],"association":[223],"studies.":[224]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2019-12-26T00:00:00"}