{"id":"https://openalex.org/W4316174755","doi":"https://doi.org/10.1177/14604582221115667","title":"Using ICD-9 diagnostic codes for external validation of topic models derived from primary care electronic medical record clinical text data","display_name":"Using ICD-9 diagnostic codes for external validation of topic models derived from primary care electronic medical record clinical text data","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4316174755","doi":"https://doi.org/10.1177/14604582221115667","pmid":"https://pubmed.ncbi.nlm.nih.gov/36639910"},"language":"en","primary_location":{"id":"doi:10.1177/14604582221115667","is_oa":true,"landing_page_url":"https://doi.org/10.1177/14604582221115667","pdf_url":"https://journals.sagepub.com/doi/pdf/10.1177/14604582221115667","source":{"id":"https://openalex.org/S201800618","display_name":"Health Informatics Journal","issn_l":"1460-4582","issn":["1460-4582","1741-2811"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Health Informatics Journal","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://journals.sagepub.com/doi/pdf/10.1177/14604582221115667","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5088217018","display_name":"Christopher Meaney","orcid":"https://orcid.org/0000-0002-5429-5233"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Christopher Meaney","raw_affiliation_strings":["University of Toronto, Toronto, ON, Canada"],"raw_orcid":"https://orcid.org/0000-0002-5429-5233","affiliations":[{"raw_affiliation_string":"University of Toronto, Toronto, ON, Canada","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061181406","display_name":"Michael Escobar","orcid":"https://orcid.org/0000-0001-9055-4709"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Michael Escobar","raw_affiliation_strings":["University of Toronto, Toronto, ON, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Toronto, Toronto, ON, Canada","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107443857","display_name":"Th\u00e9r\u00e8se A. Stukel","orcid":"https://orcid.org/0000-0001-9283-8764"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Therese A Stukel","raw_affiliation_strings":["ICES, Toronto, ON, Canada; University of Toronto, Toronto, ON, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ICES, Toronto, ON, Canada; University of Toronto, Toronto, ON, Canada","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030080832","display_name":"Peter C. Austin","orcid":"https://orcid.org/0000-0003-3337-233X"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Peter C Austin","raw_affiliation_strings":["ICES, Toronto, ON, Canada; University of Toronto, Toronto, ON, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ICES, Toronto, ON, Canada; University of Toronto, Toronto, ON, Canada","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088612935","display_name":"Sumeet Kalia","orcid":"https://orcid.org/0000-0002-8165-4959"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Sumeet Kalia","raw_affiliation_strings":["University of Toronto, Toronto, ON, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Toronto, Toronto, ON, Canada","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060769041","display_name":"Babak Aliarzadeh","orcid":"https://orcid.org/0000-0002-3185-9307"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Babak Aliarzadeh","raw_affiliation_strings":["University of Toronto, Toronto, ON, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Toronto, Toronto, ON, Canada","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081830188","display_name":"Rahim Moineddin","orcid":"https://orcid.org/0000-0002-5506-084X"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Rahim Moineddin","raw_affiliation_strings":["University of Toronto, Toronto, ON, Canada"],"raw_orcid":"https://orcid.org/0000-0002-5506-084X","affiliations":[{"raw_affiliation_string":"University of Toronto, Toronto, ON, Canada","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077044149","display_name":"Michelle Greiver","orcid":"https://orcid.org/0000-0001-8957-0285"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]},{"id":"https://openalex.org/I2800061829","display_name":"North York General Hospital","ror":"https://ror.org/05b3hqn14","country_code":"CA","type":"healthcare","lineage":["https://openalex.org/I2800061829"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Michelle Greiver","raw_affiliation_strings":["University of Toronto, Toronto, ON, Canada; North York General Hospital, Toronto, ON, Canada"],"raw_orcid":"https://orcid.org/0000-0001-8957-0285","affiliations":[{"raw_affiliation_string":"University of Toronto, Toronto, ON, Canada; North York General Hospital, Toronto, ON, Canada","institution_ids":["https://openalex.org/I2800061829","https://openalex.org/I185261750"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1500,"currency":"USD","value_usd":1500},"apc_paid":{"value":1500,"currency":"USD","value_usd":1500},"fwci":1.0917,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.81210748,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"29","issue":"1","first_page":"14604582221115667","last_page":"14604582221115667"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13910","display_name":"Computational and Text Analysis Methods","score":0.998199999332428,"subfield":{"id":"https://openalex.org/subfields/3300","display_name":"General Social Sciences"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T13910","display_name":"Computational and Text Analysis Methods","score":0.998199999332428,"subfield":{"id":"https://openalex.org/subfields/3300","display_name":"General Social Sciences"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9950000047683716,"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9824000000953674,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"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/computer-science","display_name":"Computer science","score":0.5233725309371948},{"id":"https://openalex.org/keywords/diagnosis-code","display_name":"Diagnosis code","score":0.5057239532470703},{"id":"https://openalex.org/keywords/topic-model","display_name":"Topic model","score":0.4566847085952759},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4441814422607422},{"id":"https://openalex.org/keywords/face-validity","display_name":"Face validity","score":0.4367888569831848},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.41165611147880554},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3782179653644562},{"id":"https://openalex.org/keywords/medicine","display_name":"Medicine","score":0.3526684641838074},{"id":"https://openalex.org/keywords/population","display_name":"Population","score":0.14665967226028442}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5233725309371948},{"id":"https://openalex.org/C45827449","wikidata":"https://www.wikidata.org/wiki/Q5270338","display_name":"Diagnosis code","level":3,"score":0.5057239532470703},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.4566847085952759},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4441814422607422},{"id":"https://openalex.org/C33191230","wikidata":"https://www.wikidata.org/wiki/Q3737383","display_name":"Face validity","level":3,"score":0.4367888569831848},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.41165611147880554},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3782179653644562},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.3526684641838074},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.14665967226028442},{"id":"https://openalex.org/C99454951","wikidata":"https://www.wikidata.org/wiki/Q932068","display_name":"Environmental health","level":1,"score":0.0},{"id":"https://openalex.org/C171606756","wikidata":"https://www.wikidata.org/wiki/Q506132","display_name":"Psychometrics","level":2,"score":0.0},{"id":"https://openalex.org/C70410870","wikidata":"https://www.wikidata.org/wiki/Q199906","display_name":"Clinical psychology","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D005260","descriptor_name":"Female","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D005260","descriptor_name":"Female","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D005260","descriptor_name":"Female","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":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007858","descriptor_name":"Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007858","descriptor_name":"Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007858","descriptor_name":"Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011320","descriptor_name":"Primary Health Care","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011320","descriptor_name":"Primary Health Care","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011320","descriptor_name":"Primary Health Care","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012189","descriptor_name":"Retrospective Studies","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012189","descriptor_name":"Retrospective Studies","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012189","descriptor_name":"Retrospective Studies","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D038801","descriptor_name":"International Classification of Diseases","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D038801","descriptor_name":"International Classification of Diseases","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D038801","descriptor_name":"International Classification of Diseases","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},{"descriptor_ui":"D057286","descriptor_name":"Electronic Health Records","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":3,"locations":[{"id":"doi:10.1177/14604582221115667","is_oa":true,"landing_page_url":"https://doi.org/10.1177/14604582221115667","pdf_url":"https://journals.sagepub.com/doi/pdf/10.1177/14604582221115667","source":{"id":"https://openalex.org/S201800618","display_name":"Health Informatics Journal","issn_l":"1460-4582","issn":["1460-4582","1741-2811"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Health Informatics Journal","raw_type":"journal-article"},{"id":"pmid:36639910","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/36639910","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":"Health informatics journal","raw_type":null},{"id":"pmh:oai:doaj.org/article:9c5341b55b394160b9837cb02b074530","is_oa":true,"landing_page_url":"https://doaj.org/article/9c5341b55b394160b9837cb02b074530","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":"Health Informatics Journal, Vol 29 (2023)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1177/14604582221115667","is_oa":true,"landing_page_url":"https://doi.org/10.1177/14604582221115667","pdf_url":"https://journals.sagepub.com/doi/pdf/10.1177/14604582221115667","source":{"id":"https://openalex.org/S201800618","display_name":"Health Informatics Journal","issn_l":"1460-4582","issn":["1460-4582","1741-2811"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Health Informatics Journal","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.4399999976158142,"display_name":"Reduced inequalities"}],"awards":[{"id":"https://openalex.org/G7151687979","display_name":null,"funder_award_id":"143303","funder_id":"https://openalex.org/F4320334506","funder_display_name":"Canadian Institutes of Health Research"}],"funders":[{"id":"https://openalex.org/F4320334506","display_name":"Canadian Institutes of Health Research","ror":"https://ror.org/01gavpb45"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4316174755.pdf"},"referenced_works_count":11,"referenced_works":["https://openalex.org/W1902027874","https://openalex.org/W1978527081","https://openalex.org/W2005051528","https://openalex.org/W2017288758","https://openalex.org/W2059745395","https://openalex.org/W2174706414","https://openalex.org/W2946254251","https://openalex.org/W4206519735","https://openalex.org/W4221142221","https://openalex.org/W4245318117","https://openalex.org/W4287687124"],"related_works":["https://openalex.org/W3200230513","https://openalex.org/W2787993192","https://openalex.org/W2769501189","https://openalex.org/W2226452791","https://openalex.org/W2158269427","https://openalex.org/W4381280689","https://openalex.org/W3033859939","https://openalex.org/W2847365777","https://openalex.org/W2962686197","https://openalex.org/W2132052677"],"abstract_inverted_index":{"Background/Objectives:":[0],"Unsupervised":[1],"topic":[2,42,71,132,194],"models":[3,195],"are":[4],"often":[5],"used":[6,33,125],"to":[7,34,79,196,209],"facilitate":[8],"improved":[9],"understanding":[10],"of":[11,40,90,129,138,162,167,171,183,214],"large":[12],"unstructured":[13],"clinical":[14,28,197],"text":[15,29,198],"datasets.":[16],"In":[17],"this":[18],"study":[19],"we":[20],"investigated":[21],"how":[22,120],"ICD-9":[23,95,106,148],"diagnostic":[24,96,107,149],"codes,":[25],"collected":[26,51,204],"alongside":[27],"data,":[30],"could":[31,123],"be":[32,124],"establish":[35],"concurrent-,":[36],"convergent-":[37],"and":[38,98,117,141,155,187],"discriminant-validity":[39],"learned":[41,131,152],"models.":[43,218],"Design/Setting:":[44],"Retrospective":[45],"open":[46],"cohort":[47],"design.":[48],"Data":[49],"were":[50],"from":[52],"primary":[53],"care":[54],"clinics":[55],"located":[56],"in":[57],"Toronto,":[58],"Canada":[59],"between":[60,92],"01/01/2017":[61],"through":[62],"12/31/2020.":[63],"Methods:":[64],"We":[65,86,104,144],"fit":[66],"a":[67,160],"non-negative":[68],"matrix":[69,84],"factorization":[70],"model,":[72],"with":[73,112,151],"K":[74],"=":[75],"50":[76],"latent":[77,101,114,163,216],"topics/themes,":[78],"our":[80],"input":[81],"document":[82],"term":[83],"(DTM).":[85],"estimated":[87],"the":[88,130,168,172,184,211],"magnitude":[89],"association":[91],"each":[93,99,113],"Boolean-valued":[94],"code":[97],"continuous":[100],"topical":[102,115,153],"vector.":[103],"identified":[105],"codes":[108,122,150],"most":[109],"strongly":[110],"associated":[111],"vector;":[116],"qualitatively":[118],"interpreted":[119],"these":[121],"for":[126,159],"external":[127,212],"validation":[128],"model.":[133],"Results:":[134],"The":[135],"DTM":[136],"consisted":[137],"382,666":[139],"documents":[140],"2210":[142],"words/tokens.":[143],"correlated":[145],"concurrently":[146],"assigned":[147],"vectors,":[154],"observed":[156],"semantic":[157],"agreement":[158],"subset":[161],"constructs":[164],"(e.g.":[165],"conditions":[166,182],"breast,":[169],"disorders":[170],"female":[173],"genital":[174],"tract,":[175],"respiratory":[176],"disease,":[177],"viral":[178],"infection,":[179],"eye/ear/nose/throat":[180],"conditions,":[181,189],"urinary":[185],"system,":[186],"dermatological":[188],"etc.).":[190],"Conclusions:":[191],"When":[192],"fitting":[193],"corpora,":[199],"researchers":[200],"can":[201],"leverage":[202],"contemporaneously":[203],"electronic":[205],"medical":[206],"record":[207],"data":[208],"investigate":[210],"validity":[213],"fitted":[215],"variable":[217]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
