{"id":"https://openalex.org/W7224467135","doi":"https://doi.org/10.2196/106199","title":"Construct Validity of Frontier Large Language Models on 4 Spanish Health Professions Specialty-Access Examinations (MIR, EIR, PIR, and FIR): Cross-Sectional Benchmarking and Psychometric Study","display_name":"Construct Validity of Frontier Large Language Models on 4 Spanish Health Professions Specialty-Access Examinations (MIR, EIR, PIR, and FIR): Cross-Sectional Benchmarking and Psychometric Study","publication_year":2026,"publication_date":"2026-10-29","ids":{"openalex":"https://openalex.org/W7224467135","doi":"https://doi.org/10.2196/106199","pmid":"https://pubmed.ncbi.nlm.nih.gov/42954916","pmcid":"https://www.ncbi.nlm.nih.gov/pmc/articles/13718280"},"language":"en","primary_location":{"id":"doi:10.2196/106199","doi":"https://doi.org/10.2196/106199","is_oa":true,"landing_page_url":"https://doi.org/10.2196/106199","pdf_url":null,"source":{"id":"https://openalex.org/S4210212741","display_name":"JMIR Medical Education","issn_l":"2369-3762","issn":["2369-3762"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","doyens","jufo-1","ki-jl-1","medline","norway-1","poland-20","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310320608","host_organization_name":"JMIR Publications","host_organization_lineage":["https://openalex.org/P4310320608"],"host_organization_lineage_names":["JMIR Publications"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"JMIR Medical Education","raw_type":"journal-article"},"volume":null,"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.2196/106199","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101938625","display_name":"Clemente Garc\u00eda-Hidalgo","orcid":"https://orcid.org/0009-0001-6672-2714","observed_orcids":["https://orcid.org/0009-0001-6672-2714"]},"institutions":[{"id":"https://openalex.org/I4210091031","display_name":"Hospital General Universitario Morales Meseguer","ror":"https://ror.org/00cfm3y81","country_code":"ES","type":"healthcare","lineage":["https://openalex.org/I4210091031"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"Clemente Garc\u00eda-Hidalgo","raw_affiliation_strings":["Radiology Department, Hospital General Universitario Morales Meseguer, Av Marqu\u00e9s de los V\u00e9lez S/N, Murcia\u00ba, Murcia, 30008, Spain, 34 666817007"],"raw_orcid":"https://orcid.org/0009-0001-6672-2714","affiliations":[{"raw_affiliation_string":"Radiology Department, Hospital General Universitario Morales Meseguer, Av Marqu\u00e9s de los V\u00e9lez S/N, Murcia\u00ba, Murcia, 30008, Spain, 34 666817007","institution_ids":["https://openalex.org/I4210091031"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031057738","display_name":"Manuel Carpio Salmer\u00f3n","orcid":"https://orcid.org/0009-0009-8772-4565","observed_orcids":["https://orcid.org/0009-0009-8772-4565"]},"institutions":[{"id":"https://openalex.org/I4210146010","display_name":"Santa Luc\u00eda University General Hospital","ror":"https://ror.org/051fvq837","country_code":"ES","type":"healthcare","lineage":["https://openalex.org/I4210146010"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Manuel Carpio-Salmer\u00f3n","raw_affiliation_strings":["Endocrinology Department, Santa Luc\u00eda University General Hospital, Cartagena, Murcia, Spain"],"raw_orcid":"https://orcid.org/0009-0009-8772-4565","affiliations":[{"raw_affiliation_string":"Endocrinology Department, Santa Luc\u00eda University General Hospital, Cartagena, Murcia, Spain","institution_ids":["https://openalex.org/I4210146010"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122857568","display_name":"Pau Benito","orcid":"https://orcid.org/0000-0002-2480-9133","observed_orcids":["https://orcid.org/0000-0002-2480-9133"]},"institutions":[{"id":"https://openalex.org/I4210115097","display_name":"Hospital Cl\u00ednic de Barcelona","ror":"https://ror.org/02a2kzf50","country_code":"ES","type":"healthcare","lineage":["https://openalex.org/I4210115097"]},{"id":"https://openalex.org/I4210148332","display_name":"Barcelona Institute for Global Health","ror":"https://ror.org/03hjgt059","country_code":"ES","type":"healthcare","lineage":["https://openalex.org/I4210148332","https://openalex.org/I4387153040"]},{"id":"https://openalex.org/I71999127","display_name":"Universitat de Barcelona","ror":"https://ror.org/021018s57","country_code":"ES","type":"education","lineage":["https://openalex.org/I71999127"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Pau Benito","raw_affiliation_strings":["Barcelona Institute for Global Health (ISGlobal), Universitat de Barcelona, Hospital Cl\u00ednic de Barcelona, Barcelona, Catalonia, Spain","Department of Preventive Medicine and Epidemiology, Clinical Institute of Medicine and Dermatology (ICMiD), Hospital Cl\u00ednic de Barcelona, Barcelona, Catalonia, Spain"],"raw_orcid":"https://orcid.org/0000-0002-2480-9133","affiliations":[{"raw_affiliation_string":"Barcelona Institute for Global Health (ISGlobal), Universitat de Barcelona, Hospital Cl\u00ednic de Barcelona, Barcelona, Catalonia, Spain","institution_ids":["https://openalex.org/I4210115097","https://openalex.org/I4210148332","https://openalex.org/I71999127"]},{"raw_affiliation_string":"Department of Preventive Medicine and Epidemiology, Clinical Institute of Medicine and Dermatology (ICMiD), Hospital Cl\u00ednic de Barcelona, Barcelona, Catalonia, Spain","institution_ids":["https://openalex.org/I4210115097"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000675028","display_name":"Carlos Carazo-Casas","orcid":"https://orcid.org/0000-0001-7568-7140","observed_orcids":["https://orcid.org/0000-0001-7568-7140"]},"institutions":[{"id":"https://openalex.org/I4210161852","display_name":"Hospital Universitario Ram\u00f3n y Cajal","ror":"https://ror.org/050eq1942","country_code":"ES","type":"healthcare","lineage":["https://openalex.org/I4210139293","https://openalex.org/I4210161852"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Carlos Carazo-Casas","raw_affiliation_strings":["Department of Otolaryngology, Hospital Universitario Ram\u00f3n y Cajal, Madrid, Madrid, Spain"],"raw_orcid":"https://orcid.org/0000-0001-7568-7140","affiliations":[{"raw_affiliation_string":"Department of Otolaryngology, Hospital Universitario Ram\u00f3n y Cajal, Madrid, Madrid, Spain","institution_ids":["https://openalex.org/I4210161852"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122869408","display_name":"Beatriz Carratal\u00e1","orcid":"https://orcid.org/0009-0000-1751-0048","observed_orcids":["https://orcid.org/0009-0000-1751-0048"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Beatriz Carratal\u00e1","raw_affiliation_strings":["Innovation and Digital Projects Academic Department, Healthcademia, Madrid, Madrid, Spain"],"raw_orcid":"https://orcid.org/0009-0000-1751-0048","affiliations":[{"raw_affiliation_string":"Innovation and Digital Projects Academic Department, Healthcademia, Madrid, Madrid, Spain","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070783444","display_name":"Jaime Campos Pav\u00f3n","orcid":"https://orcid.org/0000-0001-7852-2675","observed_orcids":["https://orcid.org/0000-0001-7852-2675"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jaime Campos Pav\u00f3n","raw_affiliation_strings":["Academia AMIR, Madrid, Madrid, Spain","Department of Ophthalmology, Hospital Universitario, Madrid, Spain"],"raw_orcid":"https://orcid.org/0000-0001-7852-2675","affiliations":[{"raw_affiliation_string":"Academia AMIR, Madrid, Madrid, Spain","institution_ids":[]},{"raw_affiliation_string":"Department of Ophthalmology, Hospital Universitario, Madrid, Spain","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5101938625"],"corresponding_institution_ids":["https://openalex.org/I4210091031"],"apc_list":{"value":1873,"currency":"USD","value_usd":1873},"apc_paid":{"value":1873,"currency":"USD","value_usd":1873},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.76306872,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"12","issue":null,"first_page":"e106199","last_page":"e106199"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.5429999828338623,"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"}},"topics":[{"id":"https://openalex.org/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.5429999828338623,"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"}},{"id":"https://openalex.org/T10254","display_name":"Innovations in Medical Education","score":0.17149999737739563,"subfield":{"id":"https://openalex.org/subfields/2739","display_name":"Public Health, Environmental and Occupational Health"},"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/T12602","display_name":"Medical Education and Admissions","score":0.15610000491142273,"subfield":{"id":"https://openalex.org/subfields/2739","display_name":"Public Health, Environmental and Occupational Health"},"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/large-language-models","display_name":"large language models","score":0.9430000185966492},{"id":"https://openalex.org/keywords/construct-validity","display_name":"construct validity","score":0.746999979019165},{"id":"https://openalex.org/keywords/distractor-selection","display_name":"distractor selection","score":0.7609999775886536},{"id":"https://openalex.org/keywords/surface-features","display_name":"surface features","score":0.5789999961853027},{"id":"https://openalex.org/keywords/llm-generated-explanations","display_name":"LLM-generated explanations","score":0.6039999723434448},{"id":"https://openalex.org/keywords/health-professions-education","display_name":"health professions education","score":0.48399999737739563},{"id":"https://openalex.org/keywords/llm-benchmarking","display_name":"LLM benchmarking","score":0.42800000309944153},{"id":"https://openalex.org/keywords/gpt-5","display_name":"GPT-5","score":0.46000000834465027},{"id":"https://openalex.org/keywords/claude","display_name":"Claude","score":0.5210000276565552}],"concepts":[{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.5924999713897705},{"id":"https://openalex.org/C19875794","wikidata":"https://www.wikidata.org/wiki/Q1207340","display_name":"Item response theory","level":3,"score":0.461899995803833},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.4584999978542328},{"id":"https://openalex.org/C75630572","wikidata":"https://www.wikidata.org/wiki/Q538904","display_name":"Applied psychology","level":1,"score":0.43470001220703125},{"id":"https://openalex.org/C2778880076","wikidata":"https://www.wikidata.org/wiki/Q750553","display_name":"Brazilian Portuguese","level":3,"score":0.41999998688697815},{"id":"https://openalex.org/C509550671","wikidata":"https://www.wikidata.org/wiki/Q126945","display_name":"Medical education","level":1,"score":0.39480000734329224},{"id":"https://openalex.org/C35219183","wikidata":"https://www.wikidata.org/wiki/Q5146","display_name":"Portuguese","level":2,"score":0.3700000047683716},{"id":"https://openalex.org/C49453240","wikidata":"https://www.wikidata.org/wiki/Q1592163","display_name":"Construct validity","level":3,"score":0.3675000071525574},{"id":"https://openalex.org/C199521495","wikidata":"https://www.wikidata.org/wiki/Q181487","display_name":"Audit","level":2,"score":0.3301999866962433},{"id":"https://openalex.org/C171606756","wikidata":"https://www.wikidata.org/wiki/Q506132","display_name":"Psychometrics","level":2,"score":0.30660000443458557},{"id":"https://openalex.org/C20387591","wikidata":"https://www.wikidata.org/wiki/Q930752","display_name":"Specialty","level":2,"score":0.30630001425743103},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.29829999804496765},{"id":"https://openalex.org/C70410870","wikidata":"https://www.wikidata.org/wiki/Q199906","display_name":"Clinical psychology","level":1,"score":0.29409998655319214},{"id":"https://openalex.org/C2779473830","wikidata":"https://www.wikidata.org/wiki/Q1540899","display_name":"MEDLINE","level":2,"score":0.2833999991416931},{"id":"https://openalex.org/C117220453","wikidata":"https://www.wikidata.org/wiki/Q5172842","display_name":"Correlation","level":2,"score":0.2685000002384186},{"id":"https://openalex.org/C40722632","wikidata":"https://www.wikidata.org/wiki/Q5160137","display_name":"Confirmatory factor analysis","level":3,"score":0.26100000739097595},{"id":"https://openalex.org/C2778263599","wikidata":"https://www.wikidata.org/wiki/Q1669245","display_name":"Item analysis","level":3,"score":0.2590000033378601},{"id":"https://openalex.org/C198999979","wikidata":"https://www.wikidata.org/wiki/Q5159115","display_name":"Concurrent validity","level":4,"score":0.25690001249313354},{"id":"https://openalex.org/C101266164","wikidata":"https://www.wikidata.org/wiki/Q2131821","display_name":"Rasch model","level":2,"score":0.2565000057220459}],"mesh":[{"descriptor_ui":"D000098342","descriptor_name":"Large Language Models","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D003430","descriptor_name":"Cross-Sectional Studies","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D004521","descriptor_name":"Educational Measurement","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D004521","descriptor_name":"Educational Measurement","qualifier_ui":"Q000592","qualifier_name":"standards","is_major_topic":true},{"descriptor_ui":"D004521","descriptor_name":"Educational Measurement","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":true},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011594","descriptor_name":"Psychometrics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D011594","descriptor_name":"Psychometrics","qualifier_ui":"Q000592","qualifier_name":"standards","is_major_topic":true},{"descriptor_ui":"D013030","descriptor_name":"Spain","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015203","descriptor_name":"Reproducibility of Results","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019985","descriptor_name":"Benchmarking","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D019985","descriptor_name":"Benchmarking","qualifier_ui":"Q000592","qualifier_name":"standards","is_major_topic":true},{"descriptor_ui":"D019985","descriptor_name":"Benchmarking","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":true}],"locations_count":3,"locations":[{"id":"doi:10.2196/106199","doi":"https://doi.org/10.2196/106199","is_oa":true,"landing_page_url":"https://doi.org/10.2196/106199","pdf_url":null,"source":{"id":"https://openalex.org/S4210212741","display_name":"JMIR Medical Education","issn_l":"2369-3762","issn":["2369-3762"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","doyens","jufo-1","ki-jl-1","medline","norway-1","poland-20","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310320608","host_organization_name":"JMIR Publications","host_organization_lineage":["https://openalex.org/P4310320608"],"host_organization_lineage_names":["JMIR Publications"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"JMIR Medical Education","raw_type":"journal-article"},{"id":"pmh:oai:pubmedcentral.nih.gov:13718280","doi":null,"is_oa":true,"landing_page_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC13718280/","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC13718280/pdf/mededu-v12-e106199.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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"JMIR Med Educ","raw_type":"Text"},{"id":"pmid:42954916","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/42954916","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":"JMIR medical education","raw_type":"Journal Article"}],"best_oa_location":{"id":"doi:10.2196/106199","doi":"https://doi.org/10.2196/106199","is_oa":true,"landing_page_url":"https://doi.org/10.2196/106199","pdf_url":null,"source":{"id":"https://openalex.org/S4210212741","display_name":"JMIR Medical Education","issn_l":"2369-3762","issn":["2369-3762"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","doyens","jufo-1","ki-jl-1","medline","norway-1","poland-20","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310320608","host_organization_name":"JMIR Publications","host_organization_lineage":["https://openalex.org/P4310320608"],"host_organization_lineage_names":["JMIR Publications"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"JMIR Medical Education","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.4000000059604645,"display_name":"Good health and well-being","id":"https://metadata.un.org/sdg/3"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7224467135.pdf","grobid_xml":"https://content.openalex.org/works/W7224467135.grobid-xml"},"referenced_works_count":40,"referenced_works":["https://openalex.org/W1704942559","https://openalex.org/W1970209023","https://openalex.org/W2028829385","https://openalex.org/W2130736456","https://openalex.org/W2156300785","https://openalex.org/W2171032518","https://openalex.org/W2326760832","https://openalex.org/W2811374795","https://openalex.org/W2921802966","https://openalex.org/W2949028947","https://openalex.org/W3016970897","https://openalex.org/W3036374590","https://openalex.org/W4235114045","https://openalex.org/W4319662928","https://openalex.org/W4360891289","https://openalex.org/W4366176207","https://openalex.org/W4383815588","https://openalex.org/W4388822338","https://openalex.org/W4389417677","https://openalex.org/W4392863142","https://openalex.org/W4393119065","https://openalex.org/W4393318738","https://openalex.org/W4394937526","https://openalex.org/W4399701665","https://openalex.org/W4402671701","https://openalex.org/W4405104931","https://openalex.org/W4406371336","https://openalex.org/W4407308237","https://openalex.org/W4407806804","https://openalex.org/W4411403091","https://openalex.org/W4412945366","https://openalex.org/W4415227752","https://openalex.org/W4416268504","https://openalex.org/W4416954175","https://openalex.org/W6947835970","https://openalex.org/W7117988202","https://openalex.org/W7123343764","https://openalex.org/W7133228402","https://openalex.org/W7140073993","https://openalex.org/W7204172788"],"related_works":["https://openalex.org/W7124991599","https://openalex.org/W7164763145","https://openalex.org/W4410952165","https://openalex.org/W6947835970","https://openalex.org/W7223323338","https://openalex.org/W7169623095","https://openalex.org/W7165480915","https://openalex.org/W7211869805","https://openalex.org/W7213241663","https://openalex.org/W4415071193"],"abstract_inverted_index":{"Abstract":[0],"Background":[1],"Large":[2],"language":[3],"models":[4],"(LLMs)":[5],"achieve":[6],"high":[7,359],"scores":[8,14,21,361,383],"on":[9,140],"health-professions":[10],"examinations.":[11],"Whether":[12],"these":[13],"support":[15],"the":[16,58,72,131,220,223,287,311,367,398],"same":[17],"interpretations":[18],"as":[19,384],"human":[20,75,136,374,388,401],"remains":[22],"uncertain.":[23],"Spain":[24],"uses":[25],"parallel":[26],"multiple-choice":[27],"examinations":[28,399],"for":[29,189,400],"entry":[30],"to":[31,70,81,148,240,274,297,309],"specialty":[32],"training":[33],"in":[34],"medicine":[35],"(M\u00e9dico":[36],"Interno":[37,42,47,53],"Residente":[38,43,48,54],"[MIR]),":[39],"nursing":[40],"(Enfermero":[41],"[EIR]),":[44],"psychology":[45],"(Psic\u00f3logo":[46],"[PIR]),":[49],"and":[50,64,76,80,87,108,112,119,137,153,165,227,245,345,370],"pharmacy":[51],"(Farmac\u00e9utico":[52],"[FIR]).":[55],"Objective":[56],"Using":[57],"January":[59],"2026":[60,357],"MIR,":[61],"EIR,":[62],"PIR,":[63],"FIR":[65],"examinations,":[66],"this":[67,355],"study":[68],"aimed":[69],"quantify":[71],"correspondence":[73,372],"between":[74,135],"LLM":[77,360],"item":[78,375],"facility":[79,139,229],"describe":[82],"model":[83,268,280,320,382],"accuracy,":[84],"distractor":[85,157,190],"selection,":[86],"performance":[88,395],"associated":[89],"with":[90,122,159,236,265,300,319,363,373],"measured":[91],"surface":[92],"features.":[93],"Methods":[94],"We":[95,145],"evaluated":[96,166],"839":[97],"valid":[98],"items":[99,187,214],"using":[100],"12":[101,207],"configurations:":[102],"GPT-5.2":[103],"at":[104,231],"3":[105],"reasoning":[106],"efforts":[107],"Claude":[109],"Opus,":[110],"Sonnet,":[111],"Haiku":[113],"4.5":[114],"(Anthropic),":[115],"each":[116],"under":[117],"neutral":[118],"expert":[120],"prompts,":[121],"one":[123],"run":[124],"per":[125],"configuration.":[126],"The":[127,199,253,316],"primary":[128],"measure":[129],"was":[130,203,256,305,322,333],"Spearman":[132],"correlation":[133,255],"(\u03c1)":[134],"machine":[138,228],"828":[141,212],"complete":[142],"paired":[143,213],"items.":[144],"examined":[146],"sensitivity":[147],"panel":[149,243],"composition,":[150],"scoring,":[151],"pooling,":[152],"assumed":[154],"reliability;":[155],"compared":[156],"choices":[158],"a":[160,167,261,266],"post":[161],"hoc":[162],"plausibility-weighted":[163,288],"baseline;":[164],"surface-feature":[168],"classifier.":[169],"Image":[170],"analyses":[171],"distinguished":[172],"supplied":[173,339],"from":[174,286],"withheld":[175,347],"images.":[176],"An":[177],"exploratory":[178],"LLM-judge":[179],"audit":[180],"assessed":[181],"generated":[182],"explanations.":[183],"Bootstrap":[184],"CIs":[185],"resample":[186],"or,":[188],"concordance,":[191],"error":[192],"events;":[193],"they":[194],"exclude":[195],"run-to-run":[196],"uncertainty.":[197],"Results":[198],"highest":[200],"pooled":[201],"accuracy":[202,304,332],"94.8%":[204],"(795/839);":[205],"all":[206],"configurations":[208,369],"answered":[209],"668":[210],"of":[211,238,387],"correctly":[215],"(80.7%).":[216],"Scores":[217],"clustered":[218],"near":[219],"ceiling":[221],"among":[222,366],"strongest":[224,368],"configurations.":[225],"Human":[226],"correlated":[230],"0.40":[232,241],"(95%":[233,247,294],"CI":[234,248,295,329,343,351],"0.34-0.45),":[235],"estimates":[237],"0.31":[239],"across":[242],"definitions":[244],"0.39":[246],"0.33-0.45)":[249],"after":[250],"exam-stratified":[251],"pooling.":[252],"observed":[254],"lower":[257,334],"than":[258],"predicted":[259],"by":[260,290],"specified":[262],"one-axis":[263],"simulation":[264],"uniform":[267],"advantage":[269],"(0.63;":[270],"predictive":[271],"interval":[272],"0.59":[273],"0.66;":[275],"P":[276],"<.001).":[277],"Among":[278],"672":[279],"errors,":[281],"dominant":[282],"human-distractor":[283],"selection":[284],"differed":[285],"baseline":[289],"\u20131.25":[291],"percentage":[292],"points":[293],"\u20134.53":[296],"2.19),":[298],"compatible":[299],"no":[301],"difference.":[302],"Surface-feature":[303],"34.4%":[306],"(289/839),":[307],"similar":[308],"selecting":[310],"longest":[312],"option":[313],"(34.6%,":[314],"290/839).":[315],"adjusted":[317],"association":[318],"correctness":[321],"uncertain":[323],"(odds":[324],"ratio":[325],"[OR]":[326],"0.87,":[327],"95%":[328,342,350],"0.72-1.04).":[330],"Image-associated":[331],"both":[335],"when":[336,346],"images":[337],"were":[338],"(OR":[340,348],"0.33,":[341],"0.21-0.53)":[344],"0.11,":[349],"0.08-0.16).":[352],"Conclusions":[353],"In":[354],"single":[356],"cohort,":[358],"coexisted":[362],"limited":[364],"separation":[365],"moderate":[371],"difficulty.":[376],"These":[377],"findings":[378],"caution":[379],"against":[380],"interpreting":[381],"equivalent":[385],"evidence":[386],"competence.":[389],"They":[390],"do":[391],"not":[392],"establish":[393],"clinical":[394],"or":[396],"invalidate":[397],"candidates.":[402]},"counts_by_year":[],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2026-10-30T00:00:00"}
