{"id":"https://openalex.org/W4411219914","doi":"https://doi.org/10.1186/s13040-025-00454-9","title":"A probabilistic approach for building disease phenotypes across electronic health records","display_name":"A probabilistic approach for building disease phenotypes across electronic health records","publication_year":2025,"publication_date":"2025-06-11","ids":{"openalex":"https://openalex.org/W4411219914","doi":"https://doi.org/10.1186/s13040-025-00454-9","pmid":"https://pubmed.ncbi.nlm.nih.gov/40500747"},"language":"en","primary_location":{"id":"doi:10.1186/s13040-025-00454-9","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13040-025-00454-9","pdf_url":"https://biodatamining.biomedcentral.com/counter/pdf/10.1186/s13040-025-00454-9","source":{"id":"https://openalex.org/S84409260","display_name":"BioData Mining","issn_l":"1756-0381","issn":["1756-0381"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BioData Mining","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://biodatamining.biomedcentral.com/counter/pdf/10.1186/s13040-025-00454-9","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5001397941","display_name":"David Vidmar","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"David Vidmar","raw_affiliation_strings":["Tempus AI, 600 West Chicago Avenue, Suite 510, Chicago, IL, 60654, USA. david.vidmar@tempus.com"],"affiliations":[{"raw_affiliation_string":"Tempus AI, 600 West Chicago Avenue, Suite 510, Chicago, IL, 60654, USA. david.vidmar@tempus.com","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068000164","display_name":"Jessica De Freitas","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114883","display_name":"Tempus Labs (United States)","ror":"https://ror.org/01gbymr57","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114883"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jessica De Freitas","raw_affiliation_strings":["Tempus AI, 600 West Chicago Avenue, Suite 510, Chicago, IL, 60654, USA"],"affiliations":[{"raw_affiliation_string":"Tempus AI, 600 West Chicago Avenue, Suite 510, Chicago, IL, 60654, USA","institution_ids":["https://openalex.org/I4210114883"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044008294","display_name":"Will Thompson","orcid":"https://orcid.org/0000-0002-1353-2562"},"institutions":[{"id":"https://openalex.org/I4210114883","display_name":"Tempus Labs (United States)","ror":"https://ror.org/01gbymr57","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114883"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Will Thompson","raw_affiliation_strings":["Tempus AI, 600 West Chicago Avenue, Suite 510, Chicago, IL, 60654, USA"],"affiliations":[{"raw_affiliation_string":"Tempus AI, 600 West Chicago Avenue, Suite 510, Chicago, IL, 60654, USA","institution_ids":["https://openalex.org/I4210114883"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047051899","display_name":"Jochen Pfeifer","orcid":"https://orcid.org/0000-0003-1673-6285"},"institutions":[{"id":"https://openalex.org/I4210114883","display_name":"Tempus Labs (United States)","ror":"https://ror.org/01gbymr57","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114883"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John M. Pfeifer","raw_affiliation_strings":["Tempus AI, 600 West Chicago Avenue, Suite 510, Chicago, IL, 60654, USA"],"affiliations":[{"raw_affiliation_string":"Tempus AI, 600 West Chicago Avenue, Suite 510, Chicago, IL, 60654, USA","institution_ids":["https://openalex.org/I4210114883"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066640136","display_name":"Brandon K. Fornwalt","orcid":"https://orcid.org/0000-0002-6231-9442"},"institutions":[{"id":"https://openalex.org/I4210114883","display_name":"Tempus Labs (United States)","ror":"https://ror.org/01gbymr57","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114883"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Brandon K. Fornwalt","raw_affiliation_strings":["Tempus AI, 600 West Chicago Avenue, Suite 510, Chicago, IL, 60654, USA"],"affiliations":[{"raw_affiliation_string":"Tempus AI, 600 West Chicago Avenue, Suite 510, Chicago, IL, 60654, USA","institution_ids":["https://openalex.org/I4210114883"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081302033","display_name":"Noah Zimmerman","orcid":"https://orcid.org/0000-0003-3391-2623"},"institutions":[{"id":"https://openalex.org/I4210114883","display_name":"Tempus Labs (United States)","ror":"https://ror.org/01gbymr57","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114883"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Noah Zimmerman","raw_affiliation_strings":["Tempus AI, 600 West Chicago Avenue, Suite 510, Chicago, IL, 60654, USA"],"affiliations":[{"raw_affiliation_string":"Tempus AI, 600 West Chicago Avenue, Suite 510, Chicago, IL, 60654, USA","institution_ids":["https://openalex.org/I4210114883"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001694059","display_name":"Riccardo Miotto","orcid":"https://orcid.org/0000-0002-7815-6000"},"institutions":[{"id":"https://openalex.org/I4210114883","display_name":"Tempus Labs (United States)","ror":"https://ror.org/01gbymr57","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114883"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Riccardo Miotto","raw_affiliation_strings":["Tempus AI, 600 West Chicago Avenue, Suite 510, Chicago, IL, 60654, USA"],"affiliations":[{"raw_affiliation_string":"Tempus AI, 600 West Chicago Avenue, Suite 510, Chicago, IL, 60654, USA","institution_ids":["https://openalex.org/I4210114883"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091530162","display_name":"Ruijun Chen","orcid":"https://orcid.org/0000-0001-5281-4143"},"institutions":[{"id":"https://openalex.org/I4210114883","display_name":"Tempus Labs (United States)","ror":"https://ror.org/01gbymr57","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114883"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ruijun Chen","raw_affiliation_strings":["Tempus AI, 600 West Chicago Avenue, Suite 510, Chicago, IL, 60654, USA"],"affiliations":[{"raw_affiliation_string":"Tempus AI, 600 West Chicago Avenue, Suite 510, Chicago, IL, 60654, USA","institution_ids":["https://openalex.org/I4210114883"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5001397941"],"corresponding_institution_ids":[],"apc_list":{"value":1690,"currency":"GBP","value_usd":2072},"apc_paid":{"value":1690,"currency":"GBP","value_usd":2072},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.19585912,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"18","issue":"1","first_page":"39","last_page":"39"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10654","display_name":"Pneumonia and Respiratory Infections","score":0.9914000034332275,"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"}},"topics":[{"id":"https://openalex.org/T10654","display_name":"Pneumonia and Respiratory Infections","score":0.9914000034332275,"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"}},{"id":"https://openalex.org/T11819","display_name":"Data-Driven Disease Surveillance","score":0.988099992275238,"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"}},{"id":"https://openalex.org/T11243","display_name":"Respiratory viral infections research","score":0.9602000117301941,"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/probabilistic-logic","display_name":"Probabilistic logic","score":0.6589815616607666},{"id":"https://openalex.org/keywords/health-records","display_name":"Health records","score":0.6268532276153564},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5524458885192871},{"id":"https://openalex.org/keywords/disease","display_name":"Disease","score":0.470353364944458},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.41257917881011963},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3728891611099243},{"id":"https://openalex.org/keywords/medicine","display_name":"Medicine","score":0.22706618905067444},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.191806823015213},{"id":"https://openalex.org/keywords/health-care","display_name":"Health care","score":0.17075294256210327},{"id":"https://openalex.org/keywords/political-science","display_name":"Political science","score":0.13257449865341187},{"id":"https://openalex.org/keywords/pathology","display_name":"Pathology","score":0.08300349116325378}],"concepts":[{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.6589815616607666},{"id":"https://openalex.org/C3019952477","wikidata":"https://www.wikidata.org/wiki/Q1324077","display_name":"Health records","level":3,"score":0.6268532276153564},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5524458885192871},{"id":"https://openalex.org/C2779134260","wikidata":"https://www.wikidata.org/wiki/Q12136","display_name":"Disease","level":2,"score":0.470353364944458},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.41257917881011963},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3728891611099243},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.22706618905067444},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.191806823015213},{"id":"https://openalex.org/C160735492","wikidata":"https://www.wikidata.org/wiki/Q31207","display_name":"Health care","level":2,"score":0.17075294256210327},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.13257449865341187},{"id":"https://openalex.org/C142724271","wikidata":"https://www.wikidata.org/wiki/Q7208","display_name":"Pathology","level":1,"score":0.08300349116325378},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1186/s13040-025-00454-9","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13040-025-00454-9","pdf_url":"https://biodatamining.biomedcentral.com/counter/pdf/10.1186/s13040-025-00454-9","source":{"id":"https://openalex.org/S84409260","display_name":"BioData Mining","issn_l":"1756-0381","issn":["1756-0381"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BioData Mining","raw_type":"journal-article"},{"id":"pmid:40500747","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40500747","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":"BioData mining","raw_type":null},{"id":"pmh:oai:doaj.org/article:ab9291f61c804e959921d5b161c25f32","is_oa":true,"landing_page_url":"https://doaj.org/article/ab9291f61c804e959921d5b161c25f32","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BioData Mining, Vol 18, Iss 1, Pp 1-13 (2025)","raw_type":"article"},{"id":"pmh:oai:pubmedcentral.nih.gov:12153169","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/12153169","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BioData Min","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1186/s13040-025-00454-9","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13040-025-00454-9","pdf_url":"https://biodatamining.biomedcentral.com/counter/pdf/10.1186/s13040-025-00454-9","source":{"id":"https://openalex.org/S84409260","display_name":"BioData Mining","issn_l":"1756-0381","issn":["1756-0381"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BioData Mining","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4411219914.pdf","grobid_xml":"https://content.openalex.org/works/W4411219914.grobid-xml"},"referenced_works_count":34,"referenced_works":["https://openalex.org/W284083829","https://openalex.org/W2025720061","https://openalex.org/W2032558547","https://openalex.org/W2096112399","https://openalex.org/W2113952938","https://openalex.org/W2226880313","https://openalex.org/W2317648909","https://openalex.org/W2337688125","https://openalex.org/W2432355112","https://openalex.org/W2613881683","https://openalex.org/W2762181533","https://openalex.org/W2769041395","https://openalex.org/W2784100015","https://openalex.org/W2788675884","https://openalex.org/W2803290558","https://openalex.org/W2895604144","https://openalex.org/W2959716049","https://openalex.org/W3014563232","https://openalex.org/W3015900446","https://openalex.org/W3032308670","https://openalex.org/W3035097673","https://openalex.org/W3129588459","https://openalex.org/W3133470659","https://openalex.org/W3137113787","https://openalex.org/W3169284847","https://openalex.org/W3177255321","https://openalex.org/W3196995059","https://openalex.org/W3205484571","https://openalex.org/W4313561913","https://openalex.org/W4323808485","https://openalex.org/W4366085127","https://openalex.org/W4391150982","https://openalex.org/W4399458041","https://openalex.org/W6739651123"],"related_works":["https://openalex.org/W2943623134","https://openalex.org/W2494523064","https://openalex.org/W2215759665","https://openalex.org/W2030292806","https://openalex.org/W2960358116","https://openalex.org/W2938171715","https://openalex.org/W4287727129","https://openalex.org/W3041172967","https://openalex.org/W2749065928","https://openalex.org/W2147155098"],"abstract_inverted_index":{"Identifying":[0],"the":[1,56,102,112,224],"set":[2],"of":[3,128,147,169,179,190],"patients":[4],"with":[5],"a":[6,18,45,83,88,125],"particular":[7],"disease":[8,196],"diagnosis":[9],"across":[10,74],"electronic":[11],"health":[12],"records":[13],"(EHRs),":[14],"referred":[15],"to":[16,48,105,155,207],"as":[17,114,116],"phenotype,":[19],"is":[20,32],"an":[21,117],"important":[22],"step":[23],"in":[24],"clinical":[25],"research":[26],"and":[27,54,78,94,183,209],"applications.":[28],"However,":[29],"this":[30,62],"task":[31],"often":[33],"challenging,":[34],"where":[35],"incomplete":[36],"data":[37,77],"can":[38,205],"render":[39],"definitive":[40],"classifications":[41],"impossible.":[42],"We":[43,100],"propose":[44],"probabilistic":[46,97,164],"approach":[47,86,91,98],"phenotyping":[49,198],"based":[50],"on":[51,142],"Bayesian":[52],"inference":[53],"without":[55,223],"need":[57,225],"for":[58,71,131,226,229],"gold-standard":[59],"labels.":[60],"In":[61],"paper,":[63],"we":[64],"develop":[65],"multiple":[66],"heuristic":[67],"\u201clabeling":[68],"functions\u2019\u2019":[69],"(LFs)":[70],"4":[72],"diseases":[73],"de-identified":[75],"EHR":[76],"aggregate":[79],"their":[80],"votes":[81],"through":[82],"majority":[84],"vote":[85],"(MV),":[87],"popular":[89],"open-source":[90],"(Snorkel":[92],"OSS),":[93],"our":[95],"proposed":[96],"(LEVI).":[99],"compare":[101],"resulting":[103],"phenotypes":[104,215],"those":[106],"built":[107,134,216],"using":[108,124,135,199,217],"expert-curated":[109],"logic":[110],"from":[111,158],"literature,":[113],"well":[115],"off-the-shelf":[118,140],"natural":[119],"language":[120],"processing":[121],"pipeline":[122],"(Medspacy),":[123],"curated":[126],"sample":[127],"physician-reviewed":[129],"labels":[130],"evaluation.":[132],"Phenotypes":[133],"LFs":[136],"perform":[137],"better":[138,163,230],"than":[139,202],"alternatives":[141],"classification":[143,204],"performance":[144,165],"(F1":[145],"scores":[146,157],"0.79\u20130.82":[148],"vs.":[149,171,181,192],"expert-logic:":[150],"0.68,":[151],"Medspacy:":[152],"0.55).":[153],"Compared":[154],"output":[156],"Snorkel":[159],"OSS,":[160],"LEVI":[161,218],"provides":[162],"(expected":[166],"calibration":[167,221],"error":[168,222],"0.04":[170],"0.12),":[172],"ROC":[173],"AUC":[174],"estimates":[175],"(interval":[176],"score":[177],"[loss]":[178],"0.03":[180],"0.10),":[182],"operating":[184],"point":[185],"selection":[186],"(equal-cost":[187],"net":[188],"benefit":[189],"0.18":[191],"0.15).":[193],"For":[194],"challenging":[195],"states,":[197],"probabilities":[200],"rather":[201],"binary":[203],"lead":[206],"improved":[208],"more":[210],"personalized":[211],"downstream":[212],"decision-making.":[213],"Probabilistic":[214],"exhibit":[219],"low":[220],"labels,":[227],"allowing":[228],"risk-benefit":[231],"tradeoffs.":[232]},"counts_by_year":[],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}