{"id":"https://openalex.org/W4367669491","doi":null,"title":"A Representativeness-informed Model for Research Record Selection from Electronic Medical Record Systems.","display_name":"A Representativeness-informed Model for Research Record Selection from Electronic Medical Record Systems.","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4367669491","pmid":"https://pubmed.ncbi.nlm.nih.gov/37128377","pmcid":"https://www.ncbi.nlm.nih.gov/pmc/articles/10148281"},"language":"en","primary_location":{"id":"pmh:oai:pubmedcentral.nih.gov:10148281","doi":null,"is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/10148281","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC10148281/pdf/863.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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"AMIA Annu Symp 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://pmc.ncbi.nlm.nih.gov/articles/PMC10148281/pdf/863.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5047860357","display_name":"Victor A. Borza","orcid":"https://orcid.org/0000-0002-5807-3996","observed_orcids":["https://orcid.org/0000-0002-5807-3996"]},"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":"Victor A Borza","raw_affiliation_strings":["Vanderbilt University, Nashville, TN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Vanderbilt University, Nashville, TN","institution_ids":["https://openalex.org/I200719446"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091523988","display_name":"Ellen Wright Clayton","orcid":"https://orcid.org/0000-0002-0308-4110","observed_orcids":["https://orcid.org/0000-0002-0308-4110"]},"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":"Ellen Wright Clayton","raw_affiliation_strings":["Vanderbilt University, Nashville, TN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Vanderbilt University, Nashville, TN","institution_ids":["https://openalex.org/I200719446"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087192873","display_name":"Murat Kantarc\u0131o\u011flu","orcid":"https://orcid.org/0000-0001-9795-9063","observed_orcids":["https://orcid.org/0000-0001-9795-9063"]},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Murat Kantarcioglu","raw_affiliation_strings":["University of Texas at Dallas, Richardson, TX"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Texas at Dallas, Richardson, TX","institution_ids":["https://openalex.org/I162577319"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038669899","display_name":"Yevgeniy Vorobeychik","orcid":"https://orcid.org/0000-0003-2471-5345","observed_orcids":["https://orcid.org/0000-0003-2471-5345"]},"institutions":[{"id":"https://openalex.org/I204465549","display_name":"Washington University in St. Louis","ror":"https://ror.org/01yc7t268","country_code":"US","type":"education","lineage":["https://openalex.org/I204465549"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yevgeniy Vorobeychik","raw_affiliation_strings":["Washington University in St. Louis; St. Louis, MO"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Washington University in St. Louis; St. Louis, MO","institution_ids":["https://openalex.org/I204465549"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090647314","display_name":"Bradley Malin","orcid":"https://orcid.org/0000-0003-3040-5175","observed_orcids":["https://orcid.org/0000-0003-3040-5175"]},"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":"Bradley A Malin","raw_affiliation_strings":["Vanderbilt University, Nashville, TN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Vanderbilt University, Nashville, TN","institution_ids":["https://openalex.org/I200719446"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3319,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.51185979,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":97},"biblio":{"volume":"2022","issue":null,"first_page":"259","last_page":"268"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13702","display_name":"Machine Learning in Healthcare","score":0.420199990272522,"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":0.420199990272522,"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":0.32589998841285706,"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"}},{"id":"https://openalex.org/T14400","display_name":"Medical Coding and Health Information","score":0.05990000069141388,"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/representativeness","display_name":"representativeness","score":0.7879999876022339},{"id":"https://openalex.org/keywords/electronic-health-records","display_name":"electronic health records","score":0.7739999890327454},{"id":"https://openalex.org/keywords/cohort-selection","display_name":"cohort selection","score":0.777999997138977},{"id":"https://openalex.org/keywords/recruitment-bias","display_name":"recruitment bias","score":0.5329999923706055},{"id":"https://openalex.org/keywords/underrepresented-groups","display_name":"underrepresented groups","score":0.746999979019165},{"id":"https://openalex.org/keywords/minority-groups","display_name":"minority groups","score":0.828000009059906},{"id":"https://openalex.org/keywords/information-theoretic-measures","display_name":"information measures","score":0.753000020980835},{"id":"https://openalex.org/keywords/demographic-representation","display_name":"demographic representation","score":0.46000000834465027},{"id":"https://openalex.org/keywords/research-generalizability","display_name":"research generalizability","score":0.4860000014305115}],"concepts":[{"id":"https://openalex.org/C37381756","wikidata":"https://www.wikidata.org/wiki/Q20203288","display_name":"Representativeness heuristic","level":2,"score":0.981259822845459},{"id":"https://openalex.org/C195910791","wikidata":"https://www.wikidata.org/wiki/Q1324077","display_name":"Medical record","level":2,"score":0.6021833419799805},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5903376340866089},{"id":"https://openalex.org/C72563966","wikidata":"https://www.wikidata.org/wiki/Q1303415","display_name":"Cohort","level":2,"score":0.5422474145889282},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5391280055046082},{"id":"https://openalex.org/C142210648","wikidata":"https://www.wikidata.org/wiki/Q1266546","display_name":"Record linkage","level":3,"score":0.5101476311683655},{"id":"https://openalex.org/C40423286","wikidata":"https://www.wikidata.org/wiki/Q284172","display_name":"Selection bias","level":2,"score":0.4723471403121948},{"id":"https://openalex.org/C3018060332","wikidata":"https://www.wikidata.org/wiki/Q10871684","display_name":"Electronic medical record","level":2,"score":0.45148685574531555},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.44380050897598267},{"id":"https://openalex.org/C2780084366","wikidata":"https://www.wikidata.org/wiki/Q37732","display_name":"Demographics","level":2,"score":0.43905505537986755},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.43547219038009644},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.35881567001342773},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3525635004043579},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3496186137199402},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.33186495304107666},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.2663763165473938},{"id":"https://openalex.org/C149923435","wikidata":"https://www.wikidata.org/wiki/Q37732","display_name":"Demography","level":1,"score":0.20494696497917175},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.19525429606437683},{"id":"https://openalex.org/C108827166","wikidata":"https://www.wikidata.org/wiki/Q175975","display_name":"Internet privacy","level":1,"score":0.16020610928535461},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.12185788154602051},{"id":"https://openalex.org/C99454951","wikidata":"https://www.wikidata.org/wiki/Q932068","display_name":"Environmental health","level":1,"score":0.10970938205718994},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.10278645157814026},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1009874939918518},{"id":"https://openalex.org/C126838900","wikidata":"https://www.wikidata.org/wiki/Q77604","display_name":"Radiology","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000079803","descriptor_name":"Data Management","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":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016208","descriptor_name":"Databases, Factual","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D057286","descriptor_name":"Electronic Health Records","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":2,"locations":[{"id":"pmh:oai:pubmedcentral.nih.gov:10148281","doi":null,"is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/10148281","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC10148281/pdf/863.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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"AMIA Annu Symp Proc","raw_type":"Text"},{"id":"pmid:37128377","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/37128377","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 ... Annual Symposium proceedings. AMIA Symposium","raw_type":"Journal Article"}],"best_oa_location":{"id":"pmh:oai:pubmedcentral.nih.gov:10148281","doi":null,"is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/10148281","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC10148281/pdf/863.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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"AMIA Annu Symp Proc","raw_type":"Text"},"sustainable_development_goals":[{"score":0.7578999996185303,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"},{"score":0.46810001134872437,"display_name":"Good health and well-being","id":"https://metadata.un.org/sdg/3"}],"study_designs":[],"awards":[{"id":"https://openalex.org/G2615776415","display_name":null,"funder_award_id":"UL1TR002243","funder_id":"https://openalex.org/F4320316438","funder_display_name":"Georgia Clinical and Translational Science Alliance"},{"id":"https://openalex.org/G3220570226","display_name":"FAI: FairGame: An Audit-Driven Game Theoretic Framework for Development and Certification of Fair AI","funder_award_id":"1939677","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3834006785","display_name":"Medical Scientist Training Program","funder_award_id":"T32GM007347","funder_id":"https://openalex.org/F4320337354","funder_display_name":"National Institute of General Medical Sciences"},{"id":"https://openalex.org/G4410787187","display_name":null,"funder_award_id":"UL1 TR002243","funder_id":"https://openalex.org/F4320313998","funder_display_name":"Vanderbilt University Medical Center"},{"id":"https://openalex.org/G6246474086","display_name":null,"funder_award_id":"T32GM007347","funder_id":"https://openalex.org/F4320313998","funder_display_name":"Vanderbilt University Medical Center"},{"id":"https://openalex.org/G8613732148","display_name":"Genetic Privacy and Identity in Community Settings - GetPreCiSe","funder_award_id":"RM1HG009034","funder_id":"https://openalex.org/F4320337348","funder_display_name":"National Human Genome Research Institute"},{"id":"https://openalex.org/G9000872578","display_name":"Vanderbilt Institute for Clinical and Translational Research (VICTR)","funder_award_id":"UL1TR002243","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320313998","display_name":"Vanderbilt University Medical Center","ror":"https://ror.org/05dq2gs74"},{"id":"https://openalex.org/F4320316438","display_name":"Georgia Clinical and Translational Science Alliance","ror":"https://ror.org/034hw7m59"},{"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/F4320337354","display_name":"National Institute of General Medical Sciences","ror":"https://ror.org/04q48ey07"},{"id":"https://openalex.org/F4320337472","display_name":"National Center for Advancing Translational Sciences","ror":"https://ror.org/04pw6fb54"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4367669491.pdf","grobid_xml":"https://content.openalex.org/works/W4367669491.grobid-xml"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W1939947548","https://openalex.org/W1949221783","https://openalex.org/W2005534705","https://openalex.org/W2065974896","https://openalex.org/W2091142866","https://openalex.org/W2120411377","https://openalex.org/W2128304333","https://openalex.org/W2139998668","https://openalex.org/W2559791548","https://openalex.org/W2606228909","https://openalex.org/W2615995104","https://openalex.org/W2741416490","https://openalex.org/W2900081888","https://openalex.org/W2911193641","https://openalex.org/W2967910810","https://openalex.org/W2981869278","https://openalex.org/W3003173448","https://openalex.org/W3013689372","https://openalex.org/W3046004977","https://openalex.org/W3191500986","https://openalex.org/W3202137438","https://openalex.org/W3210872821","https://openalex.org/W4225961394"],"related_works":["https://openalex.org/W4406302084","https://openalex.org/W2785875883","https://openalex.org/W2164242317","https://openalex.org/W3020046452","https://openalex.org/W4401374090","https://openalex.org/W7202197260","https://openalex.org/W3197919347","https://openalex.org/W2109347377","https://openalex.org/W2128336280","https://openalex.org/W2976952205"],"abstract_inverted_index":{"Scientific":[0],"and":[1,14,23,52,101,109],"clinical":[2],"studies":[3],"have":[4],"a":[5,43,58,89,129,134],"long":[6],"history":[7],"of":[8,12,85,136],"bias":[9],"in":[10,75],"recruitment":[11],"underprivileged":[13],"minority":[15],"populations.":[16],"This":[17],"underrepresentation":[18],"leads":[19],"to":[20,56,82,112],"inaccurate,":[21],"inapplicable,":[22],"non-generalizable":[24],"results.":[25],"Electronic":[26],"medical":[27],"record":[28,61,74],"(EMR)":[29],"systems,":[30],"which":[31,116],"now":[32],"drive":[33],"much":[34],"research,":[35],"often":[36],"poorly":[37],"represent":[38],"these":[39],"groups.":[40],"We":[41,78],"introduce":[42],"method":[44,81],"for":[45],"quantifying":[46],"representativeness":[47,103],"using":[48],"information":[49],"theoretic":[50],"measures":[51],"an":[53],"algorithmic":[54],"approach":[55,131],"select":[57,83],"more":[59,143],"representative":[60],"cohort":[62,135],"than":[63],"random":[64,113],"selection":[65,114],"when":[66],"resource":[67],"limitations":[68],"preclude":[69],"researchers":[70],"from":[71,88],"reviewing":[72],"every":[73],"the":[76,96,121],"database.":[77],"apply":[79],"this":[80],"cohorts":[84],"2,000-20,000":[86],"records":[87,137],"large":[90],"(2M+":[91],"records)":[92],"EMR":[93,122],"database":[94,123],"at":[95],"Vanderbilt":[97],"University":[98],"Medical":[99],"Center":[100],"assess":[102],"based":[104],"on":[105,118],"age,":[106],"ethnicity,":[107],"race,":[108],"gender.":[110],"Compared":[111],"-":[115,125],"will":[117],"average":[119],"mirror":[120],"demographics":[124],"we":[126],"find":[127],"that":[128,138],"representativeness-informed":[130],"can":[132],"compose":[133],"is":[139],"approximately":[140],"5.8":[141],"times":[142],"representative.":[144]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":1}],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2023-05-03T00:00:00"}