{"id":"https://openalex.org/W4415299179","doi":"https://doi.org/10.3390/make7040121","title":"Small or Large? Zero-Shot or Finetuned? Guiding Language Model Choice for Specialized Applications in Healthcare","display_name":"Small or Large? Zero-Shot or Finetuned? Guiding Language Model Choice for Specialized Applications in Healthcare","publication_year":2025,"publication_date":"2025-10-17","ids":{"openalex":"https://openalex.org/W4415299179","doi":"https://doi.org/10.3390/make7040121"},"language":"en","primary_location":{"id":"doi:10.3390/make7040121","is_oa":true,"landing_page_url":"https://doi.org/10.3390/make7040121","pdf_url":null,"source":{"id":"https://openalex.org/S4210213891","display_name":"Machine Learning and Knowledge Extraction","issn_l":"2504-4990","issn":["2504-4990"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning and Knowledge Extraction","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.3390/make7040121","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5004441174","display_name":"Lovedeep Gondara","orcid":"https://orcid.org/0000-0003-0287-9672"},"institutions":[{"id":"https://openalex.org/I141945490","display_name":"University of British Columbia","ror":"https://ror.org/03rmrcq20","country_code":"CA","type":"education","lineage":["https://openalex.org/I141945490"]},{"id":"https://openalex.org/I156965999","display_name":"Provincial Health Services Authority","ror":"https://ror.org/01jvd8304","country_code":"CA","type":"government","lineage":["https://openalex.org/I1308729876","https://openalex.org/I156965999"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Lovedeep Gondara","raw_affiliation_strings":["British Columbia Cancer Registry, Provincial Health Services Authority, Vancouver, BC V6H 4C1, Canada","School of Population and Public Health, University of British Columbia, Vancouver, BC V5Z 4E8, Canada"],"affiliations":[{"raw_affiliation_string":"British Columbia Cancer Registry, Provincial Health Services Authority, Vancouver, BC V6H 4C1, Canada","institution_ids":["https://openalex.org/I156965999"]},{"raw_affiliation_string":"School of Population and Public Health, University of British Columbia, Vancouver, BC V5Z 4E8, Canada","institution_ids":["https://openalex.org/I141945490"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004478607","display_name":"Jonathan Simkin","orcid":"https://orcid.org/0000-0001-6184-6024"},"institutions":[{"id":"https://openalex.org/I156965999","display_name":"Provincial Health Services Authority","ror":"https://ror.org/01jvd8304","country_code":"CA","type":"government","lineage":["https://openalex.org/I1308729876","https://openalex.org/I156965999"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Jonathan Simkin","raw_affiliation_strings":["British Columbia Cancer Registry, Provincial Health Services Authority, Vancouver, BC V6H 4C1, Canada"],"affiliations":[{"raw_affiliation_string":"British Columbia Cancer Registry, Provincial Health Services Authority, Vancouver, BC V6H 4C1, Canada","institution_ids":["https://openalex.org/I156965999"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120042112","display_name":"Graham Sayle","orcid":null},"institutions":[{"id":"https://openalex.org/I141945490","display_name":"University of British Columbia","ror":"https://ror.org/03rmrcq20","country_code":"CA","type":"education","lineage":["https://openalex.org/I141945490"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Graham Sayle","raw_affiliation_strings":["The Data Science Institute, University of British Columbia, Vancouver, BC V5Z 4E8, Canada"],"affiliations":[{"raw_affiliation_string":"The Data Science Institute, University of British Columbia, Vancouver, BC V5Z 4E8, Canada","institution_ids":["https://openalex.org/I141945490"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015725130","display_name":"Shebnum Devji","orcid":null},"institutions":[{"id":"https://openalex.org/I156965999","display_name":"Provincial Health Services Authority","ror":"https://ror.org/01jvd8304","country_code":"CA","type":"government","lineage":["https://openalex.org/I1308729876","https://openalex.org/I156965999"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Shebnum Devji","raw_affiliation_strings":["British Columbia Cancer Registry, Provincial Health Services Authority, Vancouver, BC V6H 4C1, Canada"],"affiliations":[{"raw_affiliation_string":"British Columbia Cancer Registry, Provincial Health Services Authority, Vancouver, BC V6H 4C1, Canada","institution_ids":["https://openalex.org/I156965999"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010728835","display_name":"Gregory Arbour","orcid":"https://orcid.org/0009-0008-7323-4701"},"institutions":[{"id":"https://openalex.org/I141945490","display_name":"University of British Columbia","ror":"https://ror.org/03rmrcq20","country_code":"CA","type":"education","lineage":["https://openalex.org/I141945490"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Gregory Arbour","raw_affiliation_strings":["The Data Science Institute, University of British Columbia, Vancouver, BC V5Z 4E8, Canada"],"affiliations":[{"raw_affiliation_string":"The Data Science Institute, University of British Columbia, Vancouver, BC V5Z 4E8, Canada","institution_ids":["https://openalex.org/I141945490"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113567130","display_name":"Raymond T. Ng","orcid":"https://orcid.org/0000-0003-3692-8524"},"institutions":[{"id":"https://openalex.org/I141945490","display_name":"University of British Columbia","ror":"https://ror.org/03rmrcq20","country_code":"CA","type":"education","lineage":["https://openalex.org/I141945490"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Raymond Ng","raw_affiliation_strings":["The Data Science Institute, University of British Columbia, Vancouver, BC V5Z 4E8, Canada"],"affiliations":[{"raw_affiliation_string":"The Data Science Institute, University of British Columbia, Vancouver, BC V5Z 4E8, Canada","institution_ids":["https://openalex.org/I141945490"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5004441174"],"corresponding_institution_ids":["https://openalex.org/I141945490","https://openalex.org/I156965999"],"apc_list":{"value":1400,"currency":"CHF","value_usd":1515},"apc_paid":{"value":1400,"currency":"CHF","value_usd":1515},"fwci":8.4993,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.97469721,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":100},"biblio":{"volume":"7","issue":"4","first_page":"121","last_page":"121"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9954000115394592,"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/T10028","display_name":"Topic Modeling","score":0.9954000115394592,"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":0.9872000217437744,"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"}},{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9710999727249146,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.654699981212616},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6204000115394592},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.555899977684021},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.4081999957561493},{"id":"https://openalex.org/keywords/health-care","display_name":"Health care","score":0.34380000829696655},{"id":"https://openalex.org/keywords/language-understanding","display_name":"Language understanding","score":0.30709999799728394},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.3027999997138977}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8543999791145325},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.654699981212616},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6204000115394592},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.555899977684021},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5315999984741211},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4327000081539154},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.4081999957561493},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.34929999709129333},{"id":"https://openalex.org/C160735492","wikidata":"https://www.wikidata.org/wiki/Q31207","display_name":"Health care","level":2,"score":0.34380000829696655},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.30790001153945923},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.30709999799728394},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3027999997138977},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.2930999994277954},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.27079999446868896},{"id":"https://openalex.org/C94922259","wikidata":"https://www.wikidata.org/wiki/Q33215","display_name":"Constructed language","level":2,"score":0.26910001039505005},{"id":"https://openalex.org/C2779974597","wikidata":"https://www.wikidata.org/wiki/Q28448986","display_name":"Clinical Practice","level":2,"score":0.25540000200271606},{"id":"https://openalex.org/C2988170871","wikidata":"https://www.wikidata.org/wiki/Q11000047","display_name":"Healthcare system","level":3,"score":0.25440001487731934},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.2540000081062317},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.25369998812675476}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.3390/make7040121","is_oa":true,"landing_page_url":"https://doi.org/10.3390/make7040121","pdf_url":null,"source":{"id":"https://openalex.org/S4210213891","display_name":"Machine Learning and Knowledge Extraction","issn_l":"2504-4990","issn":["2504-4990"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning and Knowledge Extraction","raw_type":"journal-article"},{"id":"pmh:oai:circle.library.ubc.ca:2429/93354","is_oa":true,"landing_page_url":"http://hdl.handle.net/2429/93354","pdf_url":null,"source":{"id":"https://openalex.org/S4377196297","display_name":"cIRcle (University of British Columbia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I141945490","host_organization_name":"University of British Columbia","host_organization_lineage":["https://openalex.org/I141945490"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},{"id":"pmh:oai:doaj.org/article:a6c5f0d0415e4add9391269608612ef9","is_oa":true,"landing_page_url":"https://doaj.org/article/a6c5f0d0415e4add9391269608612ef9","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":"Machine Learning and Knowledge Extraction, Vol 7, Iss 4, p 121 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3390/make7040121","is_oa":true,"landing_page_url":"https://doi.org/10.3390/make7040121","pdf_url":null,"source":{"id":"https://openalex.org/S4210213891","display_name":"Machine Learning and Knowledge Extraction","issn_l":"2504-4990","issn":["2504-4990"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning and Knowledge Extraction","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W2963026768","https://openalex.org/W3034238904","https://openalex.org/W4292779060","https://openalex.org/W4394890393","https://openalex.org/W4402692877","https://openalex.org/W4404396281","https://openalex.org/W4404518252"],"related_works":[],"abstract_inverted_index":{"Objectives:":[0],"To":[1],"guide":[2],"language":[3,23],"model":[4],"(LM)":[5],"selection":[6],"by":[7,100],"comparing":[8],"finetuning":[9,126],"vs.":[10,15,17,29,68],"zero-shot":[11,67,71,85,88,91,94,132],"use,":[12],"generic":[13,107],"pretraining":[14,76,113,141],"domain-adjacent":[16],"further":[18,74],"domain-specific":[19,112,140],"pretraining,":[20],"and":[21,37,45,73,87],"bidirectional":[22],"models":[24,136],"(BiLMs)":[25],"such":[26],"as":[27],"BERT":[28],"unidirectional":[30],"LMs":[31],"(LLMs)":[32],"for":[33,147,157],"clinical":[34,159],"classification.":[35],"Materials":[36],"Methods:":[38],"We":[39,65],"evaluated":[40],"BiLMs":[41,83,86,95,104,108,127,150],"(RoBERTa,":[42],"PathologyBERT,":[43],"Gatortron)":[44],"LLM":[46,92],"(Mistral":[47],"nemo":[48],"instruct":[49],"12B)":[50],"on":[51],"three":[52],"British":[53],"Columbia":[54],"Cancer":[55],"Registry":[56],"(BCCR)":[57],"pathology":[58],"classification":[59],"tasks":[60],"varying":[61],"in":[62],"difficulty/data":[63],"size.":[64],"assessed":[66],"finetuned":[69,101],"BiLMs,":[70],"LLM,":[72],"BCCR-specific":[75],"using":[77],"macro-average":[78],"F1":[79],"scores.":[80],"Results:":[81],"Finetuned":[82],"outperformed":[84,93,99,106],"LLM.":[89],"The":[90],"but":[96],"was":[97],"consistently":[98],"BiLMs.":[102],"Domain-adjacent":[103,134],"generally":[105],"after":[109],"finetuning.":[110],"Further":[111,139],"boosted":[114],"complex/low-data":[115,148],"task":[116],"performance,":[117],"with":[118],"otherwise":[119],"modest":[120],"gains.":[121],"Conclusions:":[122],"For":[123],"specialized":[124],"classification,":[125],"is":[128],"crucial,":[129],"often":[130],"surpassing":[131],"LLMs.":[133],"pretrained":[135],"are":[137],"recommended.":[138],"provides":[142],"significant":[143],"performance":[144],"boosts,":[145],"especially":[146],"scenarios.":[149],"remain":[151],"relevant,":[152],"offering":[153],"strong":[154],"performance/resource":[155],"balance":[156],"targeted":[158],"tasks.":[160]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-18T00:00:00"}
