{"id":"https://openalex.org/W7128036334","doi":"https://doi.org/10.1038/s41746-026-02406-x","title":"A weakly supervised transformer for rare disease diagnosis and subphenotyping from EHRs with pulmonary case studies","display_name":"A weakly supervised transformer for rare disease diagnosis and subphenotyping from EHRs with pulmonary case studies","publication_year":2026,"publication_date":"2026-02-06","ids":{"openalex":"https://openalex.org/W7128036334","doi":"https://doi.org/10.1038/s41746-026-02406-x","pmid":"https://pubmed.ncbi.nlm.nih.gov/41652033"},"language":"en","primary_location":{"id":"doi:10.1038/s41746-026-02406-x","is_oa":true,"landing_page_url":"https://doi.org/10.1038/s41746-026-02406-x","pdf_url":"https://www.nature.com/articles/s41746-026-02406-x_reference.pdf","source":{"id":"https://openalex.org/S4210195431","display_name":"npj Digital Medicine","issn_l":"2398-6352","issn":["2398-6352"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319908","host_organization_name":"Nature Portfolio","host_organization_lineage":["https://openalex.org/P4310319908","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Nature Portfolio","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":"npj Digital Medicine","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.nature.com/articles/s41746-026-02406-x_reference.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5044941932","display_name":"Kimberly F. Greco","orcid":"https://orcid.org/0000-0003-1790-0737"},"institutions":[{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kimberly F. Greco","raw_affiliation_strings":["Department of Biostatistics, Harvard T.H. Chan School of Public Health, Boston, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Biostatistics, Harvard T.H. Chan School of Public Health, Boston, MA, USA","institution_ids":["https://openalex.org/I136199984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125186982","display_name":"Zongxin Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zongxin Yang","raw_affiliation_strings":["Department of Biomedical Informatics, Harvard Medical School, Boston, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Biomedical Informatics, Harvard Medical School, Boston, MA, USA","institution_ids":["https://openalex.org/I136199984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125246215","display_name":"Mengyan Li","orcid":null},"institutions":[{"id":"https://openalex.org/I139924743","display_name":"Bentley University","ror":"https://ror.org/01px48m89","country_code":"US","type":"education","lineage":["https://openalex.org/I139924743"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mengyan Li","raw_affiliation_strings":["Department of Mathematical Sciences, Bentley University, Waltham, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mathematical Sciences, Bentley University, Waltham, MA, USA","institution_ids":["https://openalex.org/I139924743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125132750","display_name":"Han Tong","orcid":null},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Han Tong","raw_affiliation_strings":["Department of Statistics, Columbia University, New York, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Statistics, Columbia University, New York, NY, USA","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104229524","display_name":"Sara Morini Sweet","orcid":null},"institutions":[{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sara Morini Sweet","raw_affiliation_strings":["Department of Biomedical Informatics, Harvard Medical School, Boston, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Biomedical Informatics, Harvard Medical School, Boston, MA, USA","institution_ids":["https://openalex.org/I136199984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060000892","display_name":"Alon Geva","orcid":"https://orcid.org/0000-0002-8574-0133"},"institutions":[{"id":"https://openalex.org/I1288882113","display_name":"Boston Children's Hospital","ror":"https://ror.org/00dvg7y05","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1288882113"]},{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alon Geva","raw_affiliation_strings":["Computational Health Informatics Program, Boston Children's Hospital, Boston, MA, USA","Department of Anesthesia, Harvard Medical School, Boston, MA, USA","Department of Anesthesiology, Critical Care, and Pain Medicine, Boston Children's Hospital, Boston, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computational Health Informatics Program, Boston Children's Hospital, Boston, MA, USA","institution_ids":["https://openalex.org/I1288882113"]},{"raw_affiliation_string":"Department of Anesthesia, Harvard Medical School, Boston, MA, USA","institution_ids":["https://openalex.org/I136199984"]},{"raw_affiliation_string":"Department of Anesthesiology, Critical Care, and Pain Medicine, Boston Children's Hospital, Boston, MA, USA","institution_ids":["https://openalex.org/I1288882113"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125157975","display_name":"Kenneth D. Mandl","orcid":null},"institutions":[{"id":"https://openalex.org/I1288882113","display_name":"Boston Children's Hospital","ror":"https://ror.org/00dvg7y05","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1288882113"]},{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kenneth D. Mandl","raw_affiliation_strings":["Computational Health Informatics Program, Boston Children's Hospital, Boston, MA, USA","Department of Pediatrics, Harvard Medical School, Boston, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computational Health Informatics Program, Boston Children's Hospital, Boston, MA, USA","institution_ids":["https://openalex.org/I1288882113"]},{"raw_affiliation_string":"Department of Pediatrics, Harvard Medical School, Boston, MA, USA","institution_ids":["https://openalex.org/I136199984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054459458","display_name":"Benjamin A. Raby","orcid":"https://orcid.org/0000-0003-2206-5748"},"institutions":[{"id":"https://openalex.org/I1283280774","display_name":"Brigham and Women's Hospital","ror":"https://ror.org/04b6nzv94","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1283280774","https://openalex.org/I48633490"]},{"id":"https://openalex.org/I1288882113","display_name":"Boston Children's Hospital","ror":"https://ror.org/00dvg7y05","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1288882113"]},{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Benjamin A. Raby","raw_affiliation_strings":["Channing Division of Network Medicine, Brigham and Women's Hospital, Harvard Medical School, Boston, MA, USA","Division of Pulmonary Medicine, Boston Children's Hospital, Harvard Medical School, Boston, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Channing Division of Network Medicine, Brigham and Women's Hospital, Harvard Medical School, Boston, MA, USA","institution_ids":["https://openalex.org/I1283280774","https://openalex.org/I136199984"]},{"raw_affiliation_string":"Division of Pulmonary Medicine, Boston Children's Hospital, Harvard Medical School, Boston, MA, USA","institution_ids":["https://openalex.org/I1288882113","https://openalex.org/I136199984"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5125161475","display_name":"Tianxi Cai","orcid":null},"institutions":[{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]},{"id":"https://openalex.org/I4210101190","display_name":"Cancer Research And Biostatistics","ror":"https://ror.org/01575p865","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210101190"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Tianxi Cai","raw_affiliation_strings":["Department of Biomedical Informatics, Harvard Medical School, Boston, MA, USA. tcai.hsph@gmail.com","Department of Biostatistics, Harvard T.H. Chan School of Public Health, Boston, MA, USA. tcai.hsph@gmail.com"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Biomedical Informatics, Harvard Medical School, Boston, MA, USA. tcai.hsph@gmail.com","institution_ids":["https://openalex.org/I136199984"]},{"raw_affiliation_string":"Department of Biostatistics, Harvard T.H. Chan School of Public Health, Boston, MA, USA. tcai.hsph@gmail.com","institution_ids":["https://openalex.org/I4210101190","https://openalex.org/I136199984"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5125161475"],"corresponding_institution_ids":["https://openalex.org/I136199984","https://openalex.org/I4210101190"],"apc_list":{"value":3060,"currency":"USD","value_usd":3060},"apc_paid":{"value":3060,"currency":"USD","value_usd":3060},"fwci":18.7632,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.97636663,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":"9","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11642","display_name":"Genomics and Rare Diseases","score":0.49079999327659607,"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"}},"topics":[{"id":"https://openalex.org/T11642","display_name":"Genomics and Rare Diseases","score":0.49079999327659607,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.3319000005722046,"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/T12246","display_name":"Chronic Disease Management Strategies","score":0.015300000086426735,"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/rare-disease","display_name":"Rare disease","score":0.5766000151634216},{"id":"https://openalex.org/keywords/disease","display_name":"Disease","score":0.47999998927116394},{"id":"https://openalex.org/keywords/health-records","display_name":"Health records","score":0.45829999446868896},{"id":"https://openalex.org/keywords/rare-events","display_name":"Rare events","score":0.45249998569488525},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.4253999888896942},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.4025999903678894},{"id":"https://openalex.org/keywords/medical-diagnosis","display_name":"Medical diagnosis","score":0.4000000059604645},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.35519999265670776}],"concepts":[{"id":"https://openalex.org/C2779701055","wikidata":"https://www.wikidata.org/wiki/Q929833","display_name":"Rare disease","level":3,"score":0.5766000151634216},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5658000111579895},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.5656999945640564},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4814999997615814},{"id":"https://openalex.org/C2779134260","wikidata":"https://www.wikidata.org/wiki/Q12136","display_name":"Disease","level":2,"score":0.47999998927116394},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.478300005197525},{"id":"https://openalex.org/C3019952477","wikidata":"https://www.wikidata.org/wiki/Q1324077","display_name":"Health records","level":3,"score":0.45829999446868896},{"id":"https://openalex.org/C2777317252","wikidata":"https://www.wikidata.org/wiki/Q18393516","display_name":"Rare events","level":2,"score":0.45249998569488525},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.4253999888896942},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4047999978065491},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.4025999903678894},{"id":"https://openalex.org/C534262118","wikidata":"https://www.wikidata.org/wiki/Q177719","display_name":"Medical diagnosis","level":2,"score":0.4000000059604645},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.35519999265670776},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.3400000035762787},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.33250001072883606},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.31949999928474426},{"id":"https://openalex.org/C206497026","wikidata":"https://www.wikidata.org/wiki/Q1753883","display_name":"SNOMED CT","level":3,"score":0.31310001015663147},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.30469998717308044},{"id":"https://openalex.org/C3020646490","wikidata":"https://www.wikidata.org/wiki/Q25203551","display_name":"Clinical phenotype","level":4,"score":0.27230000495910645},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.27129998803138733},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.26739999651908875},{"id":"https://openalex.org/C190812933","wikidata":"https://www.wikidata.org/wiki/Q28923","display_name":"Chart","level":2,"score":0.2639000117778778},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.2630000114440918},{"id":"https://openalex.org/C40993552","wikidata":"https://www.wikidata.org/wiki/Q514654","display_name":"Gold standard (test)","level":2,"score":0.25870001316070557},{"id":"https://openalex.org/C2779473830","wikidata":"https://www.wikidata.org/wiki/Q1540899","display_name":"MEDLINE","level":2,"score":0.2572999894618988}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1038/s41746-026-02406-x","is_oa":true,"landing_page_url":"https://doi.org/10.1038/s41746-026-02406-x","pdf_url":"https://www.nature.com/articles/s41746-026-02406-x_reference.pdf","source":{"id":"https://openalex.org/S4210195431","display_name":"npj Digital Medicine","issn_l":"2398-6352","issn":["2398-6352"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319908","host_organization_name":"Nature Portfolio","host_organization_lineage":["https://openalex.org/P4310319908","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Nature Portfolio","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":"npj Digital Medicine","raw_type":"journal-article"},{"id":"pmid:41652033","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41652033","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":"NPJ digital medicine","raw_type":null},{"id":"pmh:oai:doaj.org/article:2b98a6cc18104b3cb663066f120c3efe","is_oa":true,"landing_page_url":"https://doaj.org/article/2b98a6cc18104b3cb663066f120c3efe","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":"npj Digital Medicine, Vol 9, Iss 1 (2026)","raw_type":"article"},{"id":"pmh:oai:pubmedcentral.nih.gov:12987952","is_oa":true,"landing_page_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC12987952/","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"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":"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":"NPJ Digit Med","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1038/s41746-026-02406-x","is_oa":true,"landing_page_url":"https://doi.org/10.1038/s41746-026-02406-x","pdf_url":"https://www.nature.com/articles/s41746-026-02406-x_reference.pdf","source":{"id":"https://openalex.org/S4210195431","display_name":"npj Digital Medicine","issn_l":"2398-6352","issn":["2398-6352"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319908","host_organization_name":"Nature Portfolio","host_organization_lineage":["https://openalex.org/P4310319908","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Nature Portfolio","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":"npj Digital Medicine","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1478064418","display_name":null,"funder_award_id":"R01HL170151","funder_id":"https://openalex.org/F4320337338","funder_display_name":"National Heart, Lung, and Blood Institute"},{"id":"https://openalex.org/G1499194553","display_name":null,"funder_award_id":"U01TR002623","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G2984939352","display_name":null,"funder_award_id":"R01LM013614","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G3500112053","display_name":null,"funder_award_id":"U01TR002623","funder_id":"https://openalex.org/F4320337472","funder_display_name":"National Center for Advancing Translational Sciences"},{"id":"https://openalex.org/G977477354","display_name":null,"funder_award_id":"R01LM013614","funder_id":"https://openalex.org/F4320337372","funder_display_name":"U.S. National Library of Medicine"}],"funders":[{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320337338","display_name":"National Heart, Lung, and Blood Institute","ror":"https://ror.org/012pb6c26"},{"id":"https://openalex.org/F4320337372","display_name":"U.S. National Library of Medicine","ror":"https://ror.org/0060t0j89"},{"id":"https://openalex.org/F4320337472","display_name":"National Center for Advancing Translational Sciences","ror":"https://ror.org/04pw6fb54"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7128036334.pdf","grobid_xml":"https://content.openalex.org/works/W7128036334.grobid-xml"},"referenced_works_count":60,"referenced_works":["https://openalex.org/W1808652302","https://openalex.org/W2085457417","https://openalex.org/W2102630933","https://openalex.org/W2116721944","https://openalex.org/W2161370807","https://openalex.org/W2163922914","https://openalex.org/W2243399060","https://openalex.org/W2284851926","https://openalex.org/W2295598076","https://openalex.org/W2625154504","https://openalex.org/W2765693998","https://openalex.org/W2783464703","https://openalex.org/W2786134488","https://openalex.org/W2803290558","https://openalex.org/W2891706393","https://openalex.org/W2897742828","https://openalex.org/W2911671206","https://openalex.org/W2936827998","https://openalex.org/W2961573794","https://openalex.org/W2965414772","https://openalex.org/W2973767881","https://openalex.org/W2980626014","https://openalex.org/W2982546097","https://openalex.org/W2999840984","https://openalex.org/W3012641931","https://openalex.org/W3013917401","https://openalex.org/W3033581476","https://openalex.org/W3084643244","https://openalex.org/W3094258447","https://openalex.org/W3095448533","https://openalex.org/W3096403953","https://openalex.org/W3096986094","https://openalex.org/W3108074927","https://openalex.org/W3131411810","https://openalex.org/W3136253378","https://openalex.org/W3156423001","https://openalex.org/W3160137267","https://openalex.org/W3180983703","https://openalex.org/W3198262548","https://openalex.org/W4214613209","https://openalex.org/W4223504984","https://openalex.org/W4235216760","https://openalex.org/W4283077570","https://openalex.org/W4293217384","https://openalex.org/W4294647518","https://openalex.org/W4301581299","https://openalex.org/W4309650827","https://openalex.org/W4360874569","https://openalex.org/W4364321916","https://openalex.org/W4367319981","https://openalex.org/W4372294445","https://openalex.org/W4387267812","https://openalex.org/W4389445707","https://openalex.org/W4392866086","https://openalex.org/W4393021028","https://openalex.org/W4399621875","https://openalex.org/W4400976112","https://openalex.org/W4405783272","https://openalex.org/W4408312780","https://openalex.org/W4410737606"],"related_works":[],"abstract_inverted_index":{"Rare":[0],"diseases":[1],"affect":[2],"an":[3],"estimated":[4],"300-400":[5],"million":[6],"people":[7],"worldwide,":[8],"yet":[9],"individual":[10],"conditions":[11,141],"remain":[12],"underdiagnosed":[13],"and":[14,21,51,92,113,120,149,164,186],"poorly":[15],"characterized":[16],"due":[17],"to":[18,31,130],"low":[19],"prevalence":[20],"limited":[22,57,108],"clinician":[23],"familiarity.":[24],"Computational":[25],"phenotyping":[26],"offers":[27],"a":[28,101,107],"scalable":[29],"approach":[30],"improving":[32],"rare":[33,89,139,183],"disease":[34,90,167,184],"detection,":[35],"but":[36,56,71],"algorithm":[37],"development":[38],"is":[39],"constrained":[40],"by":[41],"scarce":[42],"high-quality":[43],"labeled":[44],"data.":[45,194],"Expert-labeled":[46],"datasets":[47],"from":[48,63,94,118,145,191],"chart":[49],"reviews":[50],"registries":[52],"are":[53,72,124],"highly":[54],"accurate":[55,182],"in":[58,156],"scope,":[59],"whereas":[60],"labels":[61,112],"derived":[62],"electronic":[64],"health":[65],"records":[66],"(EHRs)":[67],"provide":[68],"broader":[69],"coverage":[70],"often":[73],"noisy":[74],"or":[75],"incomplete.":[76],"To":[77],"efficiently":[78],"leverage":[79],"both":[80],"sources,":[81],"we":[82],"propose":[83],"WEST":[84,99,136,175],"(WEakly":[85],"Supervised":[86],"Transformer)":[87],"for":[88],"diagnosis":[91,185],"subphenotyping":[93],"EHRs.":[95],"At":[96],"its":[97],"core,":[98],"employs":[100],"weakly":[102],"supervised":[103],"transformer":[104],"trained":[105],"on":[106,137,172],"set":[109],"of":[110,160,166],"expert-validated":[111],"extensive":[114],"probabilistic":[115],"silver-standard":[116],"labels-derived":[117],"structured":[119],"unstructured":[121],"EHR":[122,143,193],"features-that":[123],"iteratively":[125],"refined":[126],"across":[127],"training":[128],"rounds":[129],"improve":[131],"model":[132],"calibration.":[133],"We":[134],"evaluate":[135],"two":[138],"pulmonary":[140],"using":[142],"data":[144],"Boston":[146],"Children's":[147],"Hospital":[148],"show":[150],"that":[151,180],"it":[152],"outperforms":[153],"existing":[154],"methods":[155],"phenotype":[157],"classification,":[158],"identification":[159],"clinically":[161],"relevant":[162],"subphenotypes,":[163],"prediction":[165],"progression.":[168],"By":[169],"reducing":[170],"reliance":[171],"manual":[173],"annotation,":[174],"enables":[176],"label-efficient":[177],"representation":[178],"learning":[179],"supports":[181],"reveals":[187],"deeper":[188],"clinical":[189],"insights":[190],"routine":[192]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-05-10T08:33:47.465468","created_date":"2026-02-07T00:00:00"}