{"id":"https://openalex.org/W2725551975","doi":"https://doi.org/10.1371/journal.pcbi.1006106","title":"RIDDLE: Race and ethnicity Imputation from Disease history with Deep LEarning","display_name":"RIDDLE: Race and ethnicity Imputation from Disease history with Deep LEarning","publication_year":2018,"publication_date":"2018-04-26","ids":{"openalex":"https://openalex.org/W2725551975","doi":"https://doi.org/10.1371/journal.pcbi.1006106","mag":"2725551975","pmid":"https://pubmed.ncbi.nlm.nih.gov/29698408"},"language":"en","primary_location":{"id":"doi:10.1371/journal.pcbi.1006106","is_oa":true,"landing_page_url":"https://doi.org/10.1371/journal.pcbi.1006106","pdf_url":"https://journals.plos.org/ploscompbiol/article/file?id=10.1371/journal.pcbi.1006106&type=printable","source":{"id":"https://openalex.org/S86033158","display_name":"PLoS Computational Biology","issn_l":"1553-734X","issn":["1553-734X","1553-7358"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310315706","host_organization_name":"Public Library of Science","host_organization_lineage":["https://openalex.org/P4310315706"],"host_organization_lineage_names":["Public Library of Science"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"PLOS Computational Biology","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://journals.plos.org/ploscompbiol/article/file?id=10.1371/journal.pcbi.1006106&type=printable","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5045558915","display_name":"Ji-Sung Kim","orcid":"https://orcid.org/0000-0002-8966-529X"},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ji-Sung Kim","raw_affiliation_strings":["Department of Computer Science, Princeton University, Princeton, New Jersey, United States of America"],"raw_orcid":"https://orcid.org/0000-0002-8966-529X","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Princeton University, Princeton, New Jersey, United States of America","institution_ids":["https://openalex.org/I20089843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100618900","display_name":"Xin Gao","orcid":"https://orcid.org/0000-0002-7108-3574"},"institutions":[{"id":"https://openalex.org/I71920554","display_name":"King Abdullah University of Science and Technology","ror":"https://ror.org/01q3tbs38","country_code":"SA","type":"education","lineage":["https://openalex.org/I71920554"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Xin Gao","raw_affiliation_strings":["King Abdullah University of Science and Technology (KAUST), Computational Bioscience Research Center (CBRC), Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division, Thuwal, Saudi Arabia"],"raw_orcid":"https://orcid.org/0000-0002-7108-3574","affiliations":[{"raw_affiliation_string":"King Abdullah University of Science and Technology (KAUST), Computational Bioscience Research Center (CBRC), Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division, Thuwal, Saudi Arabia","institution_ids":["https://openalex.org/I71920554"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004739989","display_name":"Andrey Rzhetsky","orcid":"https://orcid.org/0000-0001-6959-7405"},"institutions":[{"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":"Andrey Rzhetsky","raw_affiliation_strings":["Institute for Genomics and Systems Biology, Computation Institute, Departments of Medicine and Human Genetics, University of Chicago, Chicago, Illinois, United States of America"],"raw_orcid":"https://orcid.org/0000-0001-6959-7405","affiliations":[{"raw_affiliation_string":"Institute for Genomics and Systems Biology, Computation Institute, Departments of Medicine and Human Genetics, University of Chicago, Chicago, Illinois, United States of America","institution_ids":["https://openalex.org/I40347166"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5004739989"],"corresponding_institution_ids":["https://openalex.org/I40347166"],"apc_list":{"value":2655,"currency":"USD","value_usd":2655},"apc_paid":{"value":2655,"currency":"USD","value_usd":2655},"fwci":2.0324,"has_fulltext":true,"cited_by_count":32,"citation_normalized_percentile":{"value":0.89559463,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"14","issue":"4","first_page":"e1006106","last_page":"e1006106"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13702","display_name":"Machine Learning in Healthcare","score":0.9922000169754028,"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":0.9922000169754028,"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/T10261","display_name":"Genetic Associations and Epidemiology","score":0.9796000123023987,"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/T10515","display_name":"Cancer-related molecular mechanisms research","score":0.972100019454956,"subfield":{"id":"https://openalex.org/subfields/1306","display_name":"Cancer Research"},"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/ethnic-group","display_name":"Ethnic group","score":0.7372551560401917},{"id":"https://openalex.org/keywords/race","display_name":"Race (biology)","score":0.5473405122756958},{"id":"https://openalex.org/keywords/confounding","display_name":"Confounding","score":0.5369467735290527},{"id":"https://openalex.org/keywords/imputation","display_name":"Imputation (statistics)","score":0.5056400299072266},{"id":"https://openalex.org/keywords/random-forest","display_name":"Random forest","score":0.5014278888702393},{"id":"https://openalex.org/keywords/logistic-regression","display_name":"Logistic regression","score":0.48038250207901},{"id":"https://openalex.org/keywords/population","display_name":"Population","score":0.46373310685157776},{"id":"https://openalex.org/keywords/disease","display_name":"Disease","score":0.4276331663131714},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42213958501815796},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.42136022448539734},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.416394978761673},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.4158439636230469},{"id":"https://openalex.org/keywords/medicine","display_name":"Medicine","score":0.37334221601486206},{"id":"https://openalex.org/keywords/demography","display_name":"Demography","score":0.32767608761787415},{"id":"https://openalex.org/keywords/missing-data","display_name":"Missing data","score":0.2640281915664673},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.20612472295761108},{"id":"https://openalex.org/keywords/environmental-health","display_name":"Environmental health","score":0.12584340572357178},{"id":"https://openalex.org/keywords/pathology","display_name":"Pathology","score":0.1254672408103943}],"concepts":[{"id":"https://openalex.org/C137403100","wikidata":"https://www.wikidata.org/wiki/Q41710","display_name":"Ethnic group","level":2,"score":0.7372551560401917},{"id":"https://openalex.org/C76509639","wikidata":"https://www.wikidata.org/wiki/Q918036","display_name":"Race (biology)","level":2,"score":0.5473405122756958},{"id":"https://openalex.org/C77350462","wikidata":"https://www.wikidata.org/wiki/Q1125472","display_name":"Confounding","level":2,"score":0.5369467735290527},{"id":"https://openalex.org/C58041806","wikidata":"https://www.wikidata.org/wiki/Q1660484","display_name":"Imputation (statistics)","level":3,"score":0.5056400299072266},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.5014278888702393},{"id":"https://openalex.org/C151956035","wikidata":"https://www.wikidata.org/wiki/Q1132755","display_name":"Logistic regression","level":2,"score":0.48038250207901},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.46373310685157776},{"id":"https://openalex.org/C2779134260","wikidata":"https://www.wikidata.org/wiki/Q12136","display_name":"Disease","level":2,"score":0.4276331663131714},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42213958501815796},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.42136022448539734},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.416394978761673},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.4158439636230469},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.37334221601486206},{"id":"https://openalex.org/C149923435","wikidata":"https://www.wikidata.org/wiki/Q37732","display_name":"Demography","level":1,"score":0.32767608761787415},{"id":"https://openalex.org/C9357733","wikidata":"https://www.wikidata.org/wiki/Q6878417","display_name":"Missing data","level":2,"score":0.2640281915664673},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.20612472295761108},{"id":"https://openalex.org/C99454951","wikidata":"https://www.wikidata.org/wiki/Q932068","display_name":"Environmental health","level":1,"score":0.12584340572357178},{"id":"https://openalex.org/C142724271","wikidata":"https://www.wikidata.org/wiki/Q7208","display_name":"Pathology","level":1,"score":0.1254672408103943},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[{"descriptor_ui":"D000069553","descriptor_name":"Supervised Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000069553","descriptor_name":"Supervised Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000069553","descriptor_name":"Supervised Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D005006","descriptor_name":"Ethnicity","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D005006","descriptor_name":"Ethnicity","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D005006","descriptor_name":"Ethnicity","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D005006","descriptor_name":"Ethnicity","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":true},{"descriptor_ui":"D005006","descriptor_name":"Ethnicity","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":true},{"descriptor_ui":"D005006","descriptor_name":"Ethnicity","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":true},{"descriptor_ui":"D005828","descriptor_name":"Genetics, Population","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":false},{"descriptor_ui":"D005828","descriptor_name":"Genetics, Population","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":false},{"descriptor_ui":"D005828","descriptor_name":"Genetics, Population","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D014644","descriptor_name":"Genetic Variation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D014644","descriptor_name":"Genetic Variation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D014644","descriptor_name":"Genetic Variation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015981","descriptor_name":"Epidemiologic Factors","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015981","descriptor_name":"Epidemiologic Factors","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015981","descriptor_name":"Epidemiologic Factors","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020022","descriptor_name":"Genetic Predisposition to Disease","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020022","descriptor_name":"Genetic Predisposition to Disease","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020022","descriptor_name":"Genetic Predisposition to Disease","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D044469","descriptor_name":"Racial Groups","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D044469","descriptor_name":"Racial Groups","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D044469","descriptor_name":"Racial Groups","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D044469","descriptor_name":"Racial Groups","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":true},{"descriptor_ui":"D044469","descriptor_name":"Racial Groups","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":true},{"descriptor_ui":"D044469","descriptor_name":"Racial Groups","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":true},{"descriptor_ui":"D057286","descriptor_name":"Electronic Health Records","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":false},{"descriptor_ui":"D057286","descriptor_name":"Electronic Health Records","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":false},{"descriptor_ui":"D057286","descriptor_name":"Electronic Health Records","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":false}],"locations_count":9,"locations":[{"id":"doi:10.1371/journal.pcbi.1006106","is_oa":true,"landing_page_url":"https://doi.org/10.1371/journal.pcbi.1006106","pdf_url":"https://journals.plos.org/ploscompbiol/article/file?id=10.1371/journal.pcbi.1006106&type=printable","source":{"id":"https://openalex.org/S86033158","display_name":"PLoS Computational Biology","issn_l":"1553-734X","issn":["1553-734X","1553-7358"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310315706","host_organization_name":"Public Library of Science","host_organization_lineage":["https://openalex.org/P4310315706"],"host_organization_lineage_names":["Public Library of Science"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"PLOS Computational Biology","raw_type":"journal-article"},{"id":"pmid:29698408","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/29698408","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":"PLoS computational biology","raw_type":null},{"id":"pmh:oai:arXiv.org:1707.01623","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1707.01623","pdf_url":"https://arxiv.org/pdf/1707.01623","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:uchicago.tind.io:6582","is_oa":true,"landing_page_url":"http://knowledge.uchicago.edu/record/6582","pdf_url":null,"source":{"id":"https://openalex.org/S4306402460","display_name":"Knowledge@UChicago (University of Chicago)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I40347166","host_organization_name":"University of Chicago","host_organization_lineage":["https://openalex.org/I40347166"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://knowledge.uchicago.edu/record/6582","raw_type":"Text"},{"id":"pmh:oai:RePEc:plo:pcbi00:1006106","is_oa":false,"landing_page_url":"https://journals.plos.org/ploscompbiol/article?id=10.1371/journal.pcbi.1006106","pdf_url":null,"source":{"id":"https://openalex.org/S4306401271","display_name":"RePEc: Research Papers in Economics","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I77793887","host_organization_name":"Federal Reserve Bank of St. Louis","host_organization_lineage":["https://openalex.org/I77793887"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},{"id":"pmh:oai:doaj.org/article:26cee1abe029436ebfc395331d19c120","is_oa":true,"landing_page_url":"https://doaj.org/article/26cee1abe029436ebfc395331d19c120","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":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"PLoS Computational Biology, Vol 14, Iss 4, p e1006106 (2018)","raw_type":"article"},{"id":"pmh:oai:europepmc.org:4875431","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/5940243","pdf_url":null,"source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"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":null,"raw_type":"Text"},{"id":"pmh:oai:figshare.com:article/6192692","is_oa":true,"landing_page_url":"https://figshare.com/articles/dataset/RIDDLE_Race_and_ethnicity_Imputation_from_Disease_history_with_Deep_LEarning/6192692","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"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":"","raw_type":"Dataset"},{"id":"pmh:oai:repository.kaust.edu.sa:10754/627696","is_oa":true,"landing_page_url":"http://hdl.handle.net/10754/627696","pdf_url":null,"source":{"id":"https://openalex.org/S4306401596","display_name":"King Abdullah University of Science and Technology Repository (King Abdullah University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I71920554","host_organization_name":"King Abdullah University of Science and Technology","host_organization_lineage":["https://openalex.org/I71920554"],"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":"","raw_type":"Article"}],"best_oa_location":{"id":"doi:10.1371/journal.pcbi.1006106","is_oa":true,"landing_page_url":"https://doi.org/10.1371/journal.pcbi.1006106","pdf_url":"https://journals.plos.org/ploscompbiol/article/file?id=10.1371/journal.pcbi.1006106&type=printable","source":{"id":"https://openalex.org/S86033158","display_name":"PLoS Computational Biology","issn_l":"1553-734X","issn":["1553-734X","1553-7358"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310315706","host_organization_name":"Public Library of Science","host_organization_lineage":["https://openalex.org/P4310315706"],"host_organization_lineage_names":["Public Library of Science"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"PLOS Computational Biology","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1120352242","display_name":null,"funder_award_id":"URF/1/3007-01","funder_id":"https://openalex.org/F4320322320","funder_display_name":"King Abdullah University of Science and Technology"},{"id":"https://openalex.org/G2930692464","display_name":null,"funder_award_id":"1P50MH094267","funder_id":"https://openalex.org/F4320337346","funder_display_name":"National Institute of Mental Health"},{"id":"https://openalex.org/G3591610545","display_name":null,"funder_award_id":"P50 MH094267","funder_id":"https://openalex.org/F4320337346","funder_display_name":"National Institute of Mental Health"},{"id":"https://openalex.org/G6055510217","display_name":null,"funder_award_id":"W911NF1410333","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G6063114943","display_name":null,"funder_award_id":"FCC/1/1976-04","funder_id":"https://openalex.org/F4320322320","funder_display_name":"King Abdullah University of Science and Technology"},{"id":"https://openalex.org/G6363724675","display_name":null,"funder_award_id":"R01HL122712","funder_id":"https://openalex.org/F4320337338","funder_display_name":"National Heart, Lung, and Blood Institute"}],"funders":[{"id":"https://openalex.org/F4320322320","display_name":"King Abdullah University of Science and Technology","ror":"https://ror.org/01q3tbs38"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"},{"id":"https://openalex.org/F4320337338","display_name":"National Heart, Lung, and Blood Institute","ror":"https://ror.org/012pb6c26"},{"id":"https://openalex.org/F4320337346","display_name":"National Institute of Mental Health","ror":"https://ror.org/04xeg9z08"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2725551975.pdf","grobid_xml":"https://content.openalex.org/works/W2725551975.grobid-xml"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W21426482","https://openalex.org/W1522301498","https://openalex.org/W1553892357","https://openalex.org/W1576278180","https://openalex.org/W1677182931","https://openalex.org/W1806891645","https://openalex.org/W1967960963","https://openalex.org/W1985419223","https://openalex.org/W2001371486","https://openalex.org/W2004119037","https://openalex.org/W2004910511","https://openalex.org/W2039261631","https://openalex.org/W2041848287","https://openalex.org/W2065974896","https://openalex.org/W2082568986","https://openalex.org/W2095705004","https://openalex.org/W2117926937","https://openalex.org/W2123147099","https://openalex.org/W2147616017","https://openalex.org/W2156228897","https://openalex.org/W2159819284","https://openalex.org/W2210465059","https://openalex.org/W2271840356","https://openalex.org/W2346578521","https://openalex.org/W2530081842","https://openalex.org/W2605409611","https://openalex.org/W2919115771","https://openalex.org/W3102476541","https://openalex.org/W3140592896","https://openalex.org/W6600880498"],"related_works":["https://openalex.org/W2994176440","https://openalex.org/W2510575233","https://openalex.org/W2481749367","https://openalex.org/W3193043704","https://openalex.org/W830718730","https://openalex.org/W4386259002","https://openalex.org/W4396689146","https://openalex.org/W4200112873","https://openalex.org/W2955796858","https://openalex.org/W2004826645"],"abstract_inverted_index":{"Anonymized":[0],"electronic":[1],"medical":[2,132],"records":[3],"are":[4,33,46,135,166],"an":[5],"increasingly":[6],"popular":[7],"source":[8],"of":[9,137,145,153,179,195],"research":[10],"data.":[11],"However,":[12],"these":[13,143],"datasets":[14],"often":[15],"lack":[16],"race":[17,30,43,138,158,170],"and":[18,31,40,44,66,80,102,130,139,159,171,181,186,192,207],"ethnicity":[19,32,45,172],"information.":[20],"This":[21],"creates":[22],"problems":[23],"for":[24,36,63,107,168],"researchers":[25],"modeling":[26],"human":[27],"disease,":[28],"as":[29,204],"powerful":[34],"confounders":[35],"many":[37],"health":[38],"exposures":[39],"treatment":[41],"outcomes;":[42],"closely":[47],"linked":[48],"to":[49,120,127,148,216],"population-specific":[50],"genetic":[51,212],"variation.":[52],"We":[53,116,141],"showed":[54],"that":[55,93,163],"deep":[56],"neural":[57,124],"networks":[58],"generate":[59],"more":[60],"accurate":[61],"estimates":[62],"missing":[64],"racial":[65,185],"ethnic":[67,187],"information":[68],"than":[69],"competing":[70],"methods":[71],"(e.g.,":[72],"logistic":[73],"regression,":[74],"random":[75],"forest,":[76],"support":[77],"vector":[78],"machines,":[79],"gradient-boosted":[81],"decision":[82],"trees).":[83],"RIDDLE":[84],"yielded":[85],"significantly":[86],"better":[87],"classification":[88],"performance":[89],"across":[90,184],"all":[91],"metrics":[92],"were":[94],"considered:":[95],"accuracy,":[96],"cross-entropy":[97],"loss":[98],"(error),":[99],"precision,":[100],"recall,":[101],"area":[103],"under":[104],"the":[105,122],"curve":[106],"receiver":[108],"operating":[109],"characteristic":[110],"plots":[111],"(all":[112],"p":[113],"<":[114],"10-9).":[115],"made":[117],"specific":[118],"efforts":[119],"interpret":[121],"trained":[123],"network":[125],"models":[126],"identify,":[128],"quantify,":[129],"visualize":[131],"features":[133,147],"which":[134,214],"predictive":[136],"ethnicity.":[140,160],"used":[142],"characterizations":[144],"informative":[146,167],"perform":[149],"a":[150,176],"systematic":[151],"comparison":[152],"differential":[154],"disease":[155],"patterns":[156],"by":[157],"The":[161],"fact":[162],"clinical":[164],"histories":[165],"imputing":[169],"could":[173],"reflect":[174],"(1)":[175],"skewed":[177],"distribution":[178],"blue-":[180],"white-collar":[182],"professions":[183],"groups,":[188],"(2)":[189],"uneven":[190],"accessibility":[191],"subjective":[193],"importance":[194],"prophylactic":[196],"health,":[197],"(3)":[198],"possible":[199],"variation":[200,213],"in":[201,210],"lifestyle,":[202],"such":[203],"dietary":[205],"habits,":[206],"(4)":[208],"differences":[209],"background":[211],"predispose":[215],"diseases.":[217]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":1}],"updated_date":"2026-05-06T08:25:59.206177","created_date":"2025-10-10T00:00:00"}