{"id":"https://openalex.org/W2991577140","doi":"https://doi.org/10.3233/shti190248","title":"Detecting Systemic Data Quality Issues in Electronic Health Records","display_name":"Detecting Systemic Data Quality Issues in Electronic Health Records","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2991577140","doi":"https://doi.org/10.3233/shti190248","mag":"2991577140","pmid":"https://pubmed.ncbi.nlm.nih.gov/31437950"},"language":"en","primary_location":{"id":"doi:10.3233/shti190248","is_oa":true,"landing_page_url":"https://doi.org/10.3233/shti190248","pdf_url":null,"source":{"id":"https://openalex.org/S4210179765","display_name":"Studies in health technology and informatics","issn_l":"0926-9630","issn":["0926-9630","1879-8365"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"book series"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Studies in Health Technology and Informatics","raw_type":"book-chapter"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.3233/shti190248","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5051450267","display_name":"Casey Ta","orcid":"https://orcid.org/0000-0002-4679-805X"},"institutions":[{"id":"https://openalex.org/I2799503643","display_name":"Columbia University Irving Medical Center","ror":"https://ror.org/01esghr10","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2799503643"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ta Casey N.","raw_affiliation_strings":["Department of Biomedical Informatics, Columbia University Irving Medical Center, New York, NY, USA"],"affiliations":[{"raw_affiliation_string":"Department of Biomedical Informatics, Columbia University Irving Medical Center, New York, NY, USA","institution_ids":["https://openalex.org/I2799503643"]}]},{"author_position":"last","author":{"id":null,"display_name":"Weng Chunhua","orcid":null},"institutions":[{"id":"https://openalex.org/I2799503643","display_name":"Columbia University Irving Medical Center","ror":"https://ror.org/01esghr10","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2799503643"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Weng Chunhua","raw_affiliation_strings":["Department of Biomedical Informatics, Columbia University Irving Medical Center, New York, NY, USA"],"affiliations":[{"raw_affiliation_string":"Department of Biomedical Informatics, Columbia University Irving Medical Center, New York, NY, USA","institution_ids":["https://openalex.org/I2799503643"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5051450267"],"corresponding_institution_ids":["https://openalex.org/I2799503643"],"apc_list":null,"apc_paid":null,"fwci":4.1313,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.95683453,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"264","issue":null,"first_page":"383","last_page":"387"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13702","display_name":"Machine Learning in Healthcare","score":0.9898999929428101,"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":0.9898999929428101,"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/T11719","display_name":"Data Quality and Management","score":0.9889000058174133,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12246","display_name":"Chronic Disease Management Strategies","score":0.986299991607666,"subfield":{"id":"https://openalex.org/subfields/2713","display_name":"Epidemiology"},"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/cluster-analysis","display_name":"Cluster analysis","score":0.6866819858551025},{"id":"https://openalex.org/keywords/aggregate","display_name":"Aggregate (composite)","score":0.5985330939292908},{"id":"https://openalex.org/keywords/medical-diagnosis","display_name":"Medical diagnosis","score":0.5594757199287415},{"id":"https://openalex.org/keywords/observational-study","display_name":"Observational study","score":0.5351546406745911},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.531897783279419},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5068760514259338},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.5019118785858154},{"id":"https://openalex.org/keywords/health-records","display_name":"Health records","score":0.4836179316043854},{"id":"https://openalex.org/keywords/medical-record","display_name":"Medical record","score":0.48088887333869934},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4790003001689911},{"id":"https://openalex.org/keywords/cluster","display_name":"Cluster (spacecraft)","score":0.4786582887172699},{"id":"https://openalex.org/keywords/data-quality","display_name":"Data quality","score":0.47468969225883484},{"id":"https://openalex.org/keywords/general-partnership","display_name":"General partnership","score":0.4628118574619293},{"id":"https://openalex.org/keywords/aggregate-data","display_name":"Aggregate data","score":0.4324626922607422},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.42542338371276855},{"id":"https://openalex.org/keywords/health-care","display_name":"Health care","score":0.37561744451522827},{"id":"https://openalex.org/keywords/medicine","display_name":"Medicine","score":0.27979469299316406},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.2311837375164032},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.15310296416282654},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12117540836334229},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11226573586463928},{"id":"https://openalex.org/keywords/operations-management","display_name":"Operations management","score":0.10498008131980896},{"id":"https://openalex.org/keywords/business","display_name":"Business","score":0.10065528750419617}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6866819858551025},{"id":"https://openalex.org/C4679612","wikidata":"https://www.wikidata.org/wiki/Q866298","display_name":"Aggregate (composite)","level":2,"score":0.5985330939292908},{"id":"https://openalex.org/C534262118","wikidata":"https://www.wikidata.org/wiki/Q177719","display_name":"Medical diagnosis","level":2,"score":0.5594757199287415},{"id":"https://openalex.org/C23131810","wikidata":"https://www.wikidata.org/wiki/Q818574","display_name":"Observational study","level":2,"score":0.5351546406745911},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.531897783279419},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5068760514259338},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.5019118785858154},{"id":"https://openalex.org/C3019952477","wikidata":"https://www.wikidata.org/wiki/Q1324077","display_name":"Health records","level":3,"score":0.4836179316043854},{"id":"https://openalex.org/C195910791","wikidata":"https://www.wikidata.org/wiki/Q1324077","display_name":"Medical record","level":2,"score":0.48088887333869934},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4790003001689911},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.4786582887172699},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.47468969225883484},{"id":"https://openalex.org/C71750763","wikidata":"https://www.wikidata.org/wiki/Q646164","display_name":"General partnership","level":2,"score":0.4628118574619293},{"id":"https://openalex.org/C2778058735","wikidata":"https://www.wikidata.org/wiki/Q4692253","display_name":"Aggregate data","level":2,"score":0.4324626922607422},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.42542338371276855},{"id":"https://openalex.org/C160735492","wikidata":"https://www.wikidata.org/wiki/Q31207","display_name":"Health care","level":2,"score":0.37561744451522827},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.27979469299316406},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.2311837375164032},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.15310296416282654},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12117540836334229},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11226573586463928},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.10498008131980896},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.10065528750419617},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C126838900","wikidata":"https://www.wikidata.org/wiki/Q77604","display_name":"Radiology","level":1,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C142724271","wikidata":"https://www.wikidata.org/wiki/Q7208","display_name":"Pathology","level":1,"score":0.0},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.0}],"mesh":[{"descriptor_ui":"D000068598","descriptor_name":"Data Accuracy","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000068598","descriptor_name":"Data Accuracy","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000068598","descriptor_name":"Data Accuracy","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D003695","descriptor_name":"Delivery of Health Care","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003695","descriptor_name":"Delivery of Health Care","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003695","descriptor_name":"Delivery of Health Care","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","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":"D016208","descriptor_name":"Databases, Factual","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},{"descriptor_ui":"D057286","descriptor_name":"Electronic Health Records","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D057286","descriptor_name":"Electronic Health Records","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":3,"locations":[{"id":"doi:10.3233/shti190248","is_oa":true,"landing_page_url":"https://doi.org/10.3233/shti190248","pdf_url":null,"source":{"id":"https://openalex.org/S4210179765","display_name":"Studies in health technology and informatics","issn_l":"0926-9630","issn":["0926-9630","1879-8365"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"book series"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Studies in Health Technology and Informatics","raw_type":"book-chapter"},{"id":"pmid:31437950","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/31437950","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":"Studies in health technology and informatics","raw_type":null},{"id":"pmh:oai:europepmc.org:5816255","is_oa":false,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/6857180","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Text"}],"best_oa_location":{"id":"doi:10.3233/shti190248","is_oa":true,"landing_page_url":"https://doi.org/10.3233/shti190248","pdf_url":null,"source":{"id":"https://openalex.org/S4210179765","display_name":"Studies in health technology and informatics","issn_l":"0926-9630","issn":["0926-9630","1879-8365"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"book series"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Studies in Health Technology and Informatics","raw_type":"book-chapter"},"sustainable_development_goals":[{"score":0.5799999833106995,"display_name":"Partnerships for the goals","id":"https://metadata.un.org/sdg/17"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W115293911","https://openalex.org/W1126991912","https://openalex.org/W2065268028","https://openalex.org/W2089037908","https://openalex.org/W2121382432","https://openalex.org/W2124994452","https://openalex.org/W2291655442","https://openalex.org/W2305956589","https://openalex.org/W2487407743","https://openalex.org/W2518786827","https://openalex.org/W2623074472","https://openalex.org/W2885743523"],"related_works":["https://openalex.org/W591343008","https://openalex.org/W2013343313","https://openalex.org/W1539684430","https://openalex.org/W1853327011","https://openalex.org/W2371295515","https://openalex.org/W2121409501","https://openalex.org/W3202928283","https://openalex.org/W2463566895","https://openalex.org/W4294956381","https://openalex.org/W2117054901"],"abstract_inverted_index":{"Secondary":[0],"analysis":[1],"of":[2,63,109],"electronic":[3],"health":[4,19],"records":[5],"for":[6,23,41],"clinical":[7,24,64],"research":[8],"faces":[9],"significant":[10],"challenges":[11],"due":[12],"to":[13,88],"known":[14],"data":[15,20,28,42,133],"quality":[16,43,134],"issues":[17,135],"in":[18,71,116],"observationally":[21],"collected":[22],"care":[25],"and":[26,51,55,76,103,120],"the":[27,89,113,117,122],"biases":[29],"caused":[30],"by":[31,45,74,137],"standard":[32],"healthcare":[33],"processes.":[34],"In":[35],"this":[36],"manuscript,":[37],"we":[38],"contribute":[39],"methodology":[40],"assessment":[44],"plotting":[46],"domain-level":[47],"(conditions":[48],"(diagnoses),":[49],"drugs,":[50],"procedures)":[52],"aggregate":[53],"statistics":[54],"concept-level":[56],"temporal":[57,69],"frequencies":[58,73,80],"(i.e.,":[59],"annual":[60,78],"prevalence":[61],"rates":[62],"concepts).":[65],"We":[66,84,111,127],"detect":[67],"common":[68],"patterns":[70,114,131],"concept":[72,79,143],"normalizing":[75],"clustering":[77],"using":[81],"K-means":[82],"clustering.":[83],"apply":[85],"these":[86,130],"methods":[87],"Columbia":[90],"University":[91],"Irving":[92],"Medical":[93,96],"Center":[94],"Observational":[95],"Outcomes":[97],"Partnership":[98],"database.":[99],"The":[100],"resulting":[101],"domain-aggregate":[102],"cluster":[104],"plots":[105],"show":[106],"a":[107],"variety":[108],"patterns.":[110],"review":[112],"found":[115],"condition":[118],"domain":[119],"investigate":[121],"processes":[123],"that":[124,129,140],"shape":[125],"them.":[126],"find":[128],"suggest":[132],"influenced":[136],"system-wide":[138],"factors":[139],"affect":[141],"individual":[142],"frequencies.":[144]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":3}],"updated_date":"2026-04-16T08:26:57.006410","created_date":"2025-10-10T00:00:00"}
