{"id":"https://openalex.org/W4290944545","doi":"https://doi.org/10.1145/3534678.3542675","title":"Automatic Phenotyping by a Seed-guided Topic Model","display_name":"Automatic Phenotyping by a Seed-guided Topic Model","publication_year":2022,"publication_date":"2022-08-12","ids":{"openalex":"https://openalex.org/W4290944545","doi":"https://doi.org/10.1145/3534678.3542675"},"language":"en","primary_location":{"id":"doi:10.1145/3534678.3542675","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3534678.3542675","pdf_url":null,"source":{"id":"https://openalex.org/S4363608767","display_name":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5076263241","display_name":"Ziyang Song","orcid":"https://orcid.org/0009-0009-6348-8713"},"institutions":[{"id":"https://openalex.org/I5023651","display_name":"McGill University","ror":"https://ror.org/01pxwe438","country_code":"CA","type":"education","lineage":["https://openalex.org/I5023651"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Ziyang Song","raw_affiliation_strings":["McGill University, Montreal, PQ, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"McGill University, Montreal, PQ, Canada","institution_ids":["https://openalex.org/I5023651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101104766","display_name":"Yuanyi Hu","orcid":null},"institutions":[{"id":"https://openalex.org/I5023651","display_name":"McGill University","ror":"https://ror.org/01pxwe438","country_code":"CA","type":"education","lineage":["https://openalex.org/I5023651"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Yuanyi Hu","raw_affiliation_strings":["McGill University, Montreal, PQ, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"McGill University, Montreal, PQ, Canada","institution_ids":["https://openalex.org/I5023651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049629789","display_name":"Aman Verma","orcid":"https://orcid.org/0000-0001-7436-1325"},"institutions":[{"id":"https://openalex.org/I5023651","display_name":"McGill University","ror":"https://ror.org/01pxwe438","country_code":"CA","type":"education","lineage":["https://openalex.org/I5023651"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Aman Verma","raw_affiliation_strings":["McGill University, Montreal, PQ, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"McGill University, Montreal, PQ, Canada","institution_ids":["https://openalex.org/I5023651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027694435","display_name":"David L. Buckeridge","orcid":"https://orcid.org/0000-0003-1817-5047"},"institutions":[{"id":"https://openalex.org/I5023651","display_name":"McGill University","ror":"https://ror.org/01pxwe438","country_code":"CA","type":"education","lineage":["https://openalex.org/I5023651"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"David L. Buckeridge","raw_affiliation_strings":["McGill University, Montreal, PQ, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"McGill University, Montreal, PQ, Canada","institution_ids":["https://openalex.org/I5023651"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100387861","display_name":"Yue Li","orcid":"https://orcid.org/0000-0003-3844-4865"},"institutions":[{"id":"https://openalex.org/I5023651","display_name":"McGill University","ror":"https://ror.org/01pxwe438","country_code":"CA","type":"education","lineage":["https://openalex.org/I5023651"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Yue Li","raw_affiliation_strings":["McGill University, Montreal, PQ, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"McGill University, Montreal, PQ, Canada","institution_ids":["https://openalex.org/I5023651"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I5023651"],"apc_list":null,"apc_paid":null,"fwci":2.0243,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.88863983,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"4713","last_page":"4723"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13702","display_name":"Machine Learning in Healthcare","score":0.9998000264167786,"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":0.9998000264167786,"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/T10028","display_name":"Topic Modeling","score":0.9943000078201294,"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":0.9534000158309937,"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/inference","display_name":"Inference","score":0.7763763666152954},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6646642684936523},{"id":"https://openalex.org/keywords/topic-model","display_name":"Topic model","score":0.6602016687393188},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5978947281837463},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5465050935745239},{"id":"https://openalex.org/keywords/bayesian-inference","display_name":"Bayesian inference","score":0.5099793672561646},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.45829424262046814},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.4452958405017853},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.4105132520198822},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.38265475630760193},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.3671402037143707},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.33338475227355957}],"concepts":[{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7763763666152954},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6646642684936523},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.6602016687393188},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5978947281837463},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5465050935745239},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.5099793672561646},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.45829424262046814},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.4452958405017853},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.4105132520198822},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.38265475630760193},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.3671402037143707},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.33338475227355957},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3534678.3542675","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3534678.3542675","pdf_url":null,"source":{"id":"https://openalex.org/S4363608767","display_name":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/3","display_name":"Good health and well-being","score":0.5899999737739563}],"awards":[{"id":"https://openalex.org/G6822511564","display_name":null,"funder_award_id":"G249591","funder_id":"https://openalex.org/F4320326644","funder_display_name":"Canada First Research Excellence Fund"}],"funders":[{"id":"https://openalex.org/F4320326644","display_name":"Canada First Research Excellence Fund","ror":null},{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1880262756","https://openalex.org/W1902526473","https://openalex.org/W1969208427","https://openalex.org/W1974660612","https://openalex.org/W2072644219","https://openalex.org/W2113105800","https://openalex.org/W2121382432","https://openalex.org/W2138162199","https://openalex.org/W2166851633","https://openalex.org/W2534494754","https://openalex.org/W2779019473","https://openalex.org/W2914304175","https://openalex.org/W2962899141","https://openalex.org/W2996824246","https://openalex.org/W3027889410","https://openalex.org/W3186929568","https://openalex.org/W4200297453","https://openalex.org/W4288400169"],"related_works":["https://openalex.org/W2793406240","https://openalex.org/W2735336991","https://openalex.org/W2964127409","https://openalex.org/W2106867672","https://openalex.org/W2753218748","https://openalex.org/W2774409638","https://openalex.org/W2949366006","https://openalex.org/W2104594922","https://openalex.org/W2147201983","https://openalex.org/W1621301074"],"abstract_inverted_index":{"Electronic":[0],"health":[1],"records":[2,159],"(EHRs)":[3],"provide":[4],"rich":[5],"clinical":[6],"information":[7],"and":[8,17,92,162,166],"the":[9,98,177],"opportunities":[10],"to":[11,15,49,54,153],"extract":[12],"epidemiological":[13],"patterns":[14],"understand":[16],"predict":[18],"patient":[19],"disease":[20,106,184,189],"risks":[21],"with":[22,67,156],"suitable":[23],"machine":[24],"learning":[25],"methods":[26],"such":[27],"as":[28,108],"topic":[29,33,56,63,79,95,111],"models.":[30],"However,":[31],"existing":[32],"models":[34],"do":[35],"not":[36],"generate":[37],"identifiable":[38],"topics":[39,118,139],"each":[40,72],"predicting":[41],"a":[42,60,76,81,85,93,128],"unique":[43,164],"phenotype.":[44],"One":[45],"promising":[46],"direction":[47],"is":[48,193],"use":[50],"known":[51],"phenotype":[52,138,174],"concepts":[53],"guide":[55],"inference.":[57],"We":[58,170],"present":[59],"seed-guided":[61,116],"Bayesian":[62],"model":[64,104],"called":[65],"MixEHR-Seed":[66],"3":[68],"contributions:":[69],"(1)":[70,172],"for":[71,151,160],"phenotype,":[73],"we":[74,103,114,126,134],"infer":[75,115],"dual-form":[77],"of":[78,88],"distribution:":[80],"seed-topic":[82],"distribution":[83,96],"over":[84,97,119],"small":[86],"set":[87],"key":[89],"EHR":[90,100,121,142],"codes":[91],"regular":[94],"entire":[99],"vocabulary;":[101],"(2)":[102,180],"age-dependent":[105,188],"progression":[107],"Markovian":[109],"dynamic":[110],"priors;":[112],"(3)":[113,186],"multi-modal":[117],"distinct":[120],"data":[122],"types.":[123],"For":[124],"inference,":[125],"developed":[127],"variational":[129],"inference":[130],"algorithm.":[131],"Using":[132],"MixEHR-Seed,":[133],"inferred":[135],"1569":[136],"PheCode-guided":[137,183],"from":[140],"an":[141],"database":[143],"in":[144],"Quebec,":[145],"Canada":[146],"covering":[147],"1.3":[148],"million":[149,158],"patients":[150],"up":[152],"20-year":[154],"follow-up":[155],"122":[157],"8539":[161],"1126":[163],"diagnostic":[165],"drug":[167],"codes,":[168],"respectively.":[169],"observed":[171],"accurate":[173],"prediction":[175],"by":[176],"guided":[178],"topics,":[179,185],"clinically":[181],"relevant":[182],"meaningful":[187],"prevalence.":[190],"Source":[191],"code":[192],"available":[194],"at":[195],"GitHub:":[196],"https://github.com/li-lab-mcgill/MixEHR-Seed.":[197]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}