{"id":"https://openalex.org/W4413051263","doi":"https://doi.org/10.3233/shti250948","title":"The Best of All Worlds: A Hybrid Approach to Cohort Identification with Rules, Small and Large Language Models","display_name":"The Best of All Worlds: A Hybrid Approach to Cohort Identification with Rules, Small and Large Language Models","publication_year":2025,"publication_date":"2025-08-07","ids":{"openalex":"https://openalex.org/W4413051263","doi":"https://doi.org/10.3233/shti250948","pmid":"https://pubmed.ncbi.nlm.nih.gov/40775966"},"language":"en","primary_location":{"id":"doi:10.3233/shti250948","is_oa":true,"landing_page_url":"https://doi.org/10.3233/shti250948","pdf_url":null,"source":{"id":"https://openalex.org/S4210179765","display_name":"Studies in health technology and informatics","issn_l":"0926-9630","issn":["0926-9630","1879-8365"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"book series"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Studies in Health Technology and Informatics","raw_type":"book-chapter"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.3233/shti250948","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5061308443","display_name":"Qiwei Gan","orcid":"https://orcid.org/0000-0002-6830-9544"},"institutions":[{"id":"https://openalex.org/I223532165","display_name":"University of Utah","ror":"https://ror.org/03r0ha626","country_code":"US","type":"education","lineage":["https://openalex.org/I223532165"]},{"id":"https://openalex.org/I4210089864","display_name":"VA Salt Lake City Healthcare System","ror":"https://ror.org/007fyq698","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1322918889","https://openalex.org/I2799886695","https://openalex.org/I4210089864","https://openalex.org/I4210113540"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Qiwei Gan","raw_affiliation_strings":["Department of Internal Medicine, University of Utah Medical School, Salt Lake","VA Salt Lake City Health Care System, Salt Lake City, UT, USA"],"raw_orcid":"https://orcid.org/0000-0002-6830-9544","affiliations":[{"raw_affiliation_string":"Department of Internal Medicine, University of Utah Medical School, Salt Lake","institution_ids":["https://openalex.org/I223532165"]},{"raw_affiliation_string":"VA Salt Lake City Health Care System, Salt Lake City, UT, USA","institution_ids":["https://openalex.org/I4210089864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101778639","display_name":"Jianlin Shi","orcid":"https://orcid.org/0000-0003-2950-8038"},"institutions":[{"id":"https://openalex.org/I223532165","display_name":"University of Utah","ror":"https://ror.org/03r0ha626","country_code":"US","type":"education","lineage":["https://openalex.org/I223532165"]},{"id":"https://openalex.org/I4210089864","display_name":"VA Salt Lake City Healthcare System","ror":"https://ror.org/007fyq698","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1322918889","https://openalex.org/I2799886695","https://openalex.org/I4210089864","https://openalex.org/I4210113540"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jianlin Shi","raw_affiliation_strings":["Department of Internal Medicine, University of Utah Medical School, Salt Lake","VA Salt Lake City Health Care System, Salt Lake City, UT, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Internal Medicine, University of Utah Medical School, Salt Lake","institution_ids":["https://openalex.org/I223532165"]},{"raw_affiliation_string":"VA Salt Lake City Health Care System, Salt Lake City, UT, USA","institution_ids":["https://openalex.org/I4210089864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112438356","display_name":"Annie C. Bowles","orcid":"https://orcid.org/0009-0002-1670-1023"},"institutions":[{"id":"https://openalex.org/I223532165","display_name":"University of Utah","ror":"https://ror.org/03r0ha626","country_code":"US","type":"education","lineage":["https://openalex.org/I223532165"]},{"id":"https://openalex.org/I4210089864","display_name":"VA Salt Lake City Healthcare System","ror":"https://ror.org/007fyq698","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1322918889","https://openalex.org/I2799886695","https://openalex.org/I4210089864","https://openalex.org/I4210113540"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Annie Bowles","raw_affiliation_strings":["Department of Internal Medicine, University of Utah Medical School, Salt Lake","VA Salt Lake City Health Care System, Salt Lake City, UT, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Internal Medicine, University of Utah Medical School, Salt Lake","institution_ids":["https://openalex.org/I223532165"]},{"raw_affiliation_string":"VA Salt Lake City Health Care System, Salt Lake City, UT, USA","institution_ids":["https://openalex.org/I4210089864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036033113","display_name":"Elizabeth Hanchrow","orcid":null},"institutions":[{"id":"https://openalex.org/I4210089864","display_name":"VA Salt Lake City Healthcare System","ror":"https://ror.org/007fyq698","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1322918889","https://openalex.org/I2799886695","https://openalex.org/I4210089864","https://openalex.org/I4210113540"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Elizabeth Hanchrow","raw_affiliation_strings":["VA Salt Lake City Health Care System, Salt Lake City, UT, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"VA Salt Lake City Health Care System, Salt Lake City, UT, USA","institution_ids":["https://openalex.org/I4210089864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109802950","display_name":"John Stanley","orcid":null},"institutions":[{"id":"https://openalex.org/I4210089864","display_name":"VA Salt Lake City Healthcare System","ror":"https://ror.org/007fyq698","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1322918889","https://openalex.org/I2799886695","https://openalex.org/I4210089864","https://openalex.org/I4210113540"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John Stanley","raw_affiliation_strings":["VA Salt Lake City Health Care System, Salt Lake City, UT, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"VA Salt Lake City Health Care System, Salt Lake City, UT, USA","institution_ids":["https://openalex.org/I4210089864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039458635","display_name":"Mengke Hu","orcid":"https://orcid.org/0000-0001-9421-6432"},"institutions":[{"id":"https://openalex.org/I223532165","display_name":"University of Utah","ror":"https://ror.org/03r0ha626","country_code":"US","type":"education","lineage":["https://openalex.org/I223532165"]},{"id":"https://openalex.org/I4210089864","display_name":"VA Salt Lake City Healthcare System","ror":"https://ror.org/007fyq698","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1322918889","https://openalex.org/I2799886695","https://openalex.org/I4210089864","https://openalex.org/I4210113540"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mengke Hu","raw_affiliation_strings":["Department of Internal Medicine, University of Utah Medical School, Salt Lake","VA Salt Lake City Health Care System, Salt Lake City, UT, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Internal Medicine, University of Utah Medical School, Salt Lake","institution_ids":["https://openalex.org/I223532165"]},{"raw_affiliation_string":"VA Salt Lake City Health Care System, Salt Lake City, UT, USA","institution_ids":["https://openalex.org/I4210089864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037435182","display_name":"Scott L. DuVall","orcid":"https://orcid.org/0000-0002-4898-3865"},"institutions":[{"id":"https://openalex.org/I223532165","display_name":"University of Utah","ror":"https://ror.org/03r0ha626","country_code":"US","type":"education","lineage":["https://openalex.org/I223532165"]},{"id":"https://openalex.org/I4210089864","display_name":"VA Salt Lake City Healthcare System","ror":"https://ror.org/007fyq698","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1322918889","https://openalex.org/I2799886695","https://openalex.org/I4210089864","https://openalex.org/I4210113540"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Scott L. Duvall","raw_affiliation_strings":["Department of Internal Medicine, University of Utah Medical School, Salt Lake","VA Salt Lake City Health Care System, Salt Lake City, UT, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Internal Medicine, University of Utah Medical School, Salt Lake","institution_ids":["https://openalex.org/I223532165"]},{"raw_affiliation_string":"VA Salt Lake City Health Care System, Salt Lake City, UT, USA","institution_ids":["https://openalex.org/I4210089864"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080489523","display_name":"Patrick R. Alba","orcid":"https://orcid.org/0000-0002-5176-5447"},"institutions":[{"id":"https://openalex.org/I223532165","display_name":"University of Utah","ror":"https://ror.org/03r0ha626","country_code":"US","type":"education","lineage":["https://openalex.org/I223532165"]},{"id":"https://openalex.org/I4210089864","display_name":"VA Salt Lake City Healthcare System","ror":"https://ror.org/007fyq698","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1322918889","https://openalex.org/I2799886695","https://openalex.org/I4210089864","https://openalex.org/I4210113540"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Patrick R. Alba","raw_affiliation_strings":["Department of Internal Medicine, University of Utah Medical School, Salt Lake","VA Salt Lake City Health Care System, Salt Lake City, UT, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Internal Medicine, University of Utah Medical School, Salt Lake","institution_ids":["https://openalex.org/I223532165"]},{"raw_affiliation_string":"VA Salt Lake City Health Care System, Salt Lake City, UT, USA","institution_ids":["https://openalex.org/I4210089864"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5061308443"],"corresponding_institution_ids":["https://openalex.org/I223532165","https://openalex.org/I4210089864"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.33525235,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"329","issue":null,"first_page":"789","last_page":"793"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13702","display_name":"Machine Learning in Healthcare","score":0.9858999848365784,"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":0.9858999848365784,"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":0.9785000085830688,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7656744718551636},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.7158305644989014},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5325549840927124},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5258315801620483},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4957474172115326},{"id":"https://openalex.org/keywords/cohort","display_name":"Cohort","score":0.49444055557250977},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.46436095237731934},{"id":"https://openalex.org/keywords/language-identification","display_name":"Language identification","score":0.4423624277114868},{"id":"https://openalex.org/keywords/healthcare-system","display_name":"Healthcare system","score":0.41631221771240234},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.37856632471084595},{"id":"https://openalex.org/keywords/health-care","display_name":"Health care","score":0.3313555121421814},{"id":"https://openalex.org/keywords/medicine","display_name":"Medicine","score":0.14138394594192505}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7656744718551636},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.7158305644989014},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5325549840927124},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5258315801620483},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4957474172115326},{"id":"https://openalex.org/C72563966","wikidata":"https://www.wikidata.org/wiki/Q1303415","display_name":"Cohort","level":2,"score":0.49444055557250977},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.46436095237731934},{"id":"https://openalex.org/C129792486","wikidata":"https://www.wikidata.org/wiki/Q1050419","display_name":"Language identification","level":3,"score":0.4423624277114868},{"id":"https://openalex.org/C2988170871","wikidata":"https://www.wikidata.org/wiki/Q11000047","display_name":"Healthcare system","level":3,"score":0.41631221771240234},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37856632471084595},{"id":"https://openalex.org/C160735492","wikidata":"https://www.wikidata.org/wiki/Q31207","display_name":"Health care","level":2,"score":0.3313555121421814},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.14138394594192505},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"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/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C126322002","wikidata":"https://www.wikidata.org/wiki/Q11180","display_name":"Internal medicine","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[{"descriptor_ui":"D000098342","descriptor_name":"Large Language Models","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000098342","descriptor_name":"Large Language Models","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":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D014481","descriptor_name":"United States","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D014481","descriptor_name":"United States","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015331","descriptor_name":"Cohort Studies","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015331","descriptor_name":"Cohort Studies","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D018875","descriptor_name":"Vocabulary, Controlled","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D018875","descriptor_name":"Vocabulary, Controlled","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D057286","descriptor_name":"Electronic Health Records","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":true},{"descriptor_ui":"D057286","descriptor_name":"Electronic Health Records","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":true},{"descriptor_ui":"D057286","descriptor_name":"Electronic Health Records","qualifier_ui":"Q000458","qualifier_name":"organization & administration","is_major_topic":true},{"descriptor_ui":"D057286","descriptor_name":"Electronic Health Records","qualifier_ui":"Q000458","qualifier_name":"organization & administration","is_major_topic":true}],"locations_count":2,"locations":[{"id":"doi:10.3233/shti250948","is_oa":true,"landing_page_url":"https://doi.org/10.3233/shti250948","pdf_url":null,"source":{"id":"https://openalex.org/S4210179765","display_name":"Studies in health technology and informatics","issn_l":"0926-9630","issn":["0926-9630","1879-8365"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"book series"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Studies in Health Technology and Informatics","raw_type":"book-chapter"},{"id":"pmid:40775966","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40775966","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":"Studies in health technology and informatics","raw_type":null}],"best_oa_location":{"id":"doi:10.3233/shti250948","is_oa":true,"landing_page_url":"https://doi.org/10.3233/shti250948","pdf_url":null,"source":{"id":"https://openalex.org/S4210179765","display_name":"Studies in health technology and informatics","issn_l":"0926-9630","issn":["0926-9630","1879-8365"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"book series"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Studies in Health Technology and Informatics","raw_type":"book-chapter"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7699999809265137}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W226586525","https://openalex.org/W1998541766","https://openalex.org/W2262900283","https://openalex.org/W1985349217","https://openalex.org/W2362145681","https://openalex.org/W2098508228","https://openalex.org/W2913520953","https://openalex.org/W1538826769","https://openalex.org/W2383292628","https://openalex.org/W2067569787"],"abstract_inverted_index":{"Balancing":[0],"operational":[1],"feasibility":[2],"with":[3],"the":[4,68],"performance":[5,44],"of":[6,47,64,71],"natural":[7],"language":[8,28,33],"processing":[9],"(NLP)":[10],"systems":[11],"is":[12],"a":[13,19],"significant":[14],"challenge.":[15],"This":[16,40],"study":[17],"presents":[18],"hybrid":[20],"strategy":[21],"to":[22],"integrate":[23],"manually":[24],"curated":[25],"rules,":[26],"small":[27],"model":[29,34],"(SLM),":[30],"and":[31,51],"large":[32,62],"(LLM)":[35],"for":[36],"cohort":[37],"identification":[38],"tasks.":[39],"approach":[41],"demonstrates":[42],"superior":[43],"in":[45,57],"terms":[46],"both":[48],"computational":[49],"efficiency":[50],"NLP":[52],"validity,":[53],"as":[54],"shown":[55],"here":[56],"two":[58],"separate":[59],"tasks":[60],"using":[61],"number":[63],"clinical":[65],"notes":[66],"from":[67],"US":[69],"Department":[70],"Veteran":[72],"Affairs":[73],"(VA)":[74],"Healthcare":[75],"system.":[76]},"counts_by_year":[],"updated_date":"2025-12-21T01:58:51.020947","created_date":"2025-10-10T00:00:00"}
