{"id":"https://openalex.org/W4385564272","doi":null,"title":"Few-Shot Learning with Semi-Supervised Transformers for Electronic Health Records.","display_name":"Few-Shot Learning with Semi-Supervised Transformers for Electronic Health Records.","publication_year":2022,"publication_date":"2022-08-01","ids":{"openalex":"https://openalex.org/W4385564272","pmid":"https://pubmed.ncbi.nlm.nih.gov/37538125","pmcid":"https://www.ncbi.nlm.nih.gov/pmc/articles/10399128"},"language":"en","primary_location":{"id":"pmid:37538125","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/37538125","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,"listed_in":[],"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":"Proceedings of machine learning research","raw_type":"Journal Article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC10399128/pdf/nihms-1865430.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5080077033","display_name":"Raphael Poulain","orcid":"https://orcid.org/0000-0001-9893-5469","observed_orcids":["https://orcid.org/0000-0001-9893-5469","https://orcid.org/0000-0003-0053-5112"]},"institutions":[{"id":"https://openalex.org/I86501945","display_name":"University of Delaware","ror":"https://ror.org/01sbq1a82","country_code":"US","type":"education","lineage":["https://openalex.org/I86501945"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Raphael Poulain","raw_affiliation_strings":["University of Delaware"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Delaware","institution_ids":["https://openalex.org/I86501945"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038349196","display_name":"Mehak Gupta","orcid":"https://orcid.org/0000-0001-8036-2025","observed_orcids":["https://orcid.org/0000-0001-8036-2025"]},"institutions":[{"id":"https://openalex.org/I86501945","display_name":"University of Delaware","ror":"https://ror.org/01sbq1a82","country_code":"US","type":"education","lineage":["https://openalex.org/I86501945"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mehak Gupta","raw_affiliation_strings":["University of Delaware"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Delaware","institution_ids":["https://openalex.org/I86501945"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044208559","display_name":"Rahmatollah Beheshti","orcid":"https://orcid.org/0000-0001-8912-3063","observed_orcids":["https://orcid.org/0000-0001-8912-3063","https://orcid.org/0000-0001-9893-5469"]},"institutions":[{"id":"https://openalex.org/I86501945","display_name":"University of Delaware","ror":"https://ror.org/01sbq1a82","country_code":"US","type":"education","lineage":["https://openalex.org/I86501945"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rahmatollah Beheshti","raw_affiliation_strings":["University of Delaware"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Delaware","institution_ids":["https://openalex.org/I86501945"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I86501945"],"apc_list":null,"apc_paid":null,"fwci":0.5975,"has_fulltext":true,"cited_by_count":9,"citation_normalized_percentile":{"value":0.63853135,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":97},"biblio":{"volume":"182","issue":null,"first_page":"853","last_page":"873"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13702","display_name":"Machine Learning in Healthcare","score":1.0,"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":1.0,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":9.999999747378752e-05,"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/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.0,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"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/few-shot-learning","display_name":"few-shot learning","score":0.9890000224113464},{"id":"https://openalex.org/keywords/semi-supervised-learning","display_name":"semi-supervised learning","score":0.9729999899864197},{"id":"https://openalex.org/keywords/transformer","display_name":"transformer models","score":0.7910000085830688},{"id":"https://openalex.org/keywords/electronic-health-records","display_name":"electronic health records","score":0.9940000176429749},{"id":"https://openalex.org/keywords/gan-based-data-augmentation","display_name":"GAN-based data augmentation","score":0.5839999914169312},{"id":"https://openalex.org/keywords/patient-representation-learning","display_name":"patient representation learning","score":0.8050000071525574},{"id":"https://openalex.org/keywords/small-medical-datasets","display_name":"small medical datasets","score":0.675000011920929},{"id":"https://openalex.org/keywords/rare-diseases","display_name":"rare diseases","score":0.734000027179718},{"id":"https://openalex.org/keywords/healthcare-prediction","display_name":"medical prediction","score":0.765999972820282}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7773858308792114},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7207244634628296},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6975807547569275},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6692839860916138},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6125509738922119},{"id":"https://openalex.org/C3019952477","wikidata":"https://www.wikidata.org/wiki/Q1324077","display_name":"Health records","level":3,"score":0.5682162046432495},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.46146729588508606},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.4506804645061493},{"id":"https://openalex.org/C148524875","wikidata":"https://www.wikidata.org/wiki/Q6975395","display_name":"F1 score","level":2,"score":0.4266740679740906},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.425035297870636},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3418438136577606},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.1472175419330597},{"id":"https://openalex.org/C160735492","wikidata":"https://www.wikidata.org/wiki/Q31207","display_name":"Health care","level":2,"score":0.12205365300178528},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09095177054405212},{"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/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmid:37538125","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/37538125","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,"listed_in":[],"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":"Proceedings of machine learning research","raw_type":"Journal Article"},{"id":"pmh:oai:pubmedcentral.nih.gov:10399128","doi":null,"is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/10399128","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC10399128/pdf/nihms-1865430.pdf","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,"listed_in":[],"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":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"Proc Mach Learn Res","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:pubmedcentral.nih.gov:10399128","doi":null,"is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/10399128","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC10399128/pdf/nihms-1865430.pdf","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,"listed_in":[],"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":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"Proc Mach Learn Res","raw_type":"Text"},"sustainable_development_goals":[{"display_name":"Good health and well-being","id":"https://metadata.un.org/sdg/3","score":0.504800021648407}],"study_designs":[],"awards":[{"id":"https://openalex.org/G9000872601","display_name":"Delaware INBRE","funder_award_id":"P20GM103446","funder_id":"https://openalex.org/F4320337354","funder_display_name":"National Institute of General Medical Sciences"},{"id":"https://openalex.org/G9000893663","display_name":"Center of Biomedical Research Excellence in Cardiovascular Health","funder_award_id":"P20GM113125","funder_id":"https://openalex.org/F4320337354","funder_display_name":"National Institute of General Medical Sciences"}],"funders":[{"id":"https://openalex.org/F4320337354","display_name":"National Institute of General Medical Sciences","ror":"https://ror.org/04q48ey07"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4385564272.pdf","grobid_xml":"https://content.openalex.org/works/W4385564272.grobid-xml"},"referenced_works_count":16,"referenced_works":["https://openalex.org/W2518582440","https://openalex.org/W2751687090","https://openalex.org/W2950813464","https://openalex.org/W2965373594","https://openalex.org/W2973113902","https://openalex.org/W2996035354","https://openalex.org/W3017637887","https://openalex.org/W3089168780","https://openalex.org/W3160137267","https://openalex.org/W3160457727","https://openalex.org/W3192221070","https://openalex.org/W4205170775","https://openalex.org/W4206457381","https://openalex.org/W4283810220","https://openalex.org/W4288758404","https://openalex.org/W4310645210"],"related_works":["https://openalex.org/W4388341236","https://openalex.org/W3160137267","https://openalex.org/W4313417929","https://openalex.org/W3112116031","https://openalex.org/W4389132345","https://openalex.org/W2965570621","https://openalex.org/W4411027404","https://openalex.org/W4390822127","https://openalex.org/W4311431862","https://openalex.org/W4287017985"],"abstract_inverted_index":{"With":[0],"the":[1,43,67,71,76,82,140,174,195,205],"growing":[2],"availability":[3],"of":[4,84,142,176,183],"Electronic":[5],"Health":[6],"Records":[7],"(EHRs),":[8],"many":[9],"deep":[10],"learning":[11,150],"methods":[12],"have":[13,27,98],"been":[14],"developed":[15],"to":[16,29,50,60,96,100,134,179],"leverage":[17],"such":[18],"datasets":[19,49,53,69,172],"in":[20,41,139],"medical":[21],"prediction":[22,167],"tasks.":[23],"Notably,":[24],"transformer-based":[25,125],"architectures":[26,36],"proven":[28],"be":[30],"highly":[31],"effective":[32,40],"for":[33,70,103],"EHRs.":[34],"Transformer-based":[35],"are":[37,158],"generally":[38],"very":[39,47],"\"transferring\"":[42],"acquired":[44],"knowledge":[45],"from":[46],"large":[48],"smaller":[51],"target":[52,68,77],"through":[54],"their":[55],"comprehensive":[56],"\"pre-training\"":[57],"process.":[58,207],"However,":[59],"work":[61],"efficiently,":[62],"they":[63],"still":[64],"rely":[65],"on":[66,165,185,194],"downstream":[72,85],"tasks,":[73],"and":[74,131,169,191],"if":[75],"dataset":[78],"is":[79,94],"(very)":[80],"small,":[81],"performance":[83,187],"models":[86],"can":[87],"degrade":[88],"rapidly.":[89],"In":[90,117],"biomedical":[91],"applications,":[92],"it":[93],"common":[95],"only":[97,153],"access":[99],"small":[101],"datasets,":[102],"instance,":[104],"when":[105],"studying":[106],"rare":[107],"diseases,":[108],"invasive":[109],"procedures,":[110],"or":[111],"using":[112],"restrictive":[113],"cohort":[114],"selection":[115],"processes.":[116],"this":[118],"study,":[119],"we":[120],"present":[121],"CEHR-GAN-BERT,":[122],"a":[123,154],"semi-supervised":[124],"architecture":[126],"that":[127,197],"leverages":[128],"both":[129],"in-":[130],"out-of-cohort":[132],"patients":[133,203],"learn":[135],"better":[136],"patient":[137],"representations":[138],"context":[141],"few-shot":[143],"learning.":[144],"The":[145],"proposed":[146],"method":[147,164],"opens":[148],"new":[149],"opportunities":[151],"where":[152],"few":[155],"hundred":[156],"samples":[157],"available.":[159],"We":[160],"extensively":[161],"evaluate":[162],"our":[163,177],"four":[166],"tasks":[168,196],"three":[170],"public":[171],"showing":[173],"ability":[175],"model":[178],"achieve":[180],"improvements":[181],"upwards":[182],"5%":[184],"all":[186],"metrics":[188],"(including":[189],"AUROC":[190],"F1":[192],"Score)":[193],"use":[198],"less":[199],"than":[200],"200":[201],"annotated":[202],"during":[204],"training":[206]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1}],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2023-08-05T00:00:00"}