{"id":"https://openalex.org/W7166741332","doi":"https://doi.org/10.48550/arxiv.2606.28960","title":"Expert Evaluation of Clinical AI Tools on Real Point-of-Care Clinical Queries","display_name":"Expert Evaluation of Clinical AI Tools on Real Point-of-Care Clinical Queries","publication_year":2026,"publication_date":"2026-06-27","ids":{"openalex":"https://openalex.org/W7166741332","doi":"https://doi.org/10.48550/arxiv.2606.28960"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2606.28960","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2606.28960","pdf_url":"https://arxiv.org/pdf/2606.28960","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2606.28960","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5051492770","display_name":"Jean Feng","orcid":"https://orcid.org/0000-0003-2041-3104","observed_orcids":["https://orcid.org/0000-0003-2041-3104"]},"institutions":[{"id":"https://openalex.org/I180670191","display_name":"University of California, San Francisco","ror":"https://ror.org/043mz5j54","country_code":"US","type":"education","lineage":["https://openalex.org/I180670191"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Feng, Jean","raw_affiliation_strings":["Department of Epidemiology and Biostatistics , University of California , San Francisco , San Francisco , California , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Epidemiology and Biostatistics , University of California , San Francisco , San Francisco , California , USA","institution_ids":["https://openalex.org/I180670191"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5159743107","display_name":"Vishal Patel","orcid":null,"observed_orcids":[]},"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/I121934306","https://openalex.org/I1283280774","https://openalex.org/I48633490"]},{"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":"Patel, Vishal","raw_affiliation_strings":["Brigham and Women's Hospital , Boston , Massachusetts , USA","Harvard Medical School , Boston , Massachusetts , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Brigham and Women's Hospital , Boston , Massachusetts , USA","institution_ids":["https://openalex.org/I1283280774"]},{"raw_affiliation_string":"Harvard Medical School , Boston , Massachusetts , USA","institution_ids":["https://openalex.org/I136199984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045447914","display_name":"PJ Heagerty","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Heagerty, Patrick","raw_affiliation_strings":["Department of Biostatistics , University of Washington , Seattle , Washington , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Biostatistics , University of Washington , Seattle , Washington , USA","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006623234","display_name":"Yifan Mai","orcid":"https://orcid.org/0000-0002-4807-037X","observed_orcids":["https://orcid.org/0000-0002-4807-037X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mai, Yifan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010866431","display_name":"Venkatesh Sivaraman","orcid":"https://orcid.org/0000-0002-6965-3961","observed_orcids":["https://orcid.org/0000-0002-6965-3961"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sivaraman, Venkatesh","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123145892","display_name":"Patrick Vossler","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vossler, Patrick","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024515289","display_name":"Jialin Ouyang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ouyang, Jialin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5053124245","display_name":"Anupam Bapu Jena","orcid":"https://orcid.org/0000-0002-9734-5122","observed_orcids":["https://orcid.org/0000-0002-9734-5122"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jena, Anupam B.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":13,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"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":0.9994999766349792,"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":0.9994999766349792,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.00019999999494757503,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T13702","display_name":"Machine Learning in Healthcare","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"}}],"keywords":[{"id":"https://openalex.org/keywords/expert-evaluation","display_name":"expert evaluation","score":0.48399999737739563},{"id":"https://openalex.org/keywords/openevidence","display_name":"OpenEvidence","score":0.5210000276565552},{"id":"https://openalex.org/keywords/clinical-decision-support","display_name":"clinical decision support","score":0.6359999775886536},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.734000027179718},{"id":"https://openalex.org/keywords/benchmark-dataset","display_name":"benchmark dataset","score":0.42899999022483826},{"id":"https://openalex.org/keywords/llm-as-a-judge","display_name":"LLM-as-a-judge","score":0.4830000102519989},{"id":"https://openalex.org/keywords/claude-opus","display_name":"Claude Opus","score":0.5419999957084656},{"id":"https://openalex.org/keywords/gemini","display_name":"Gemini","score":0.7850000262260437},{"id":"https://openalex.org/keywords/gpt-5-5","display_name":"GPT-5.5","score":0.8970000147819519},{"id":"https://openalex.org/keywords/source-quality","display_name":"source quality","score":0.47200000286102295},{"id":"https://openalex.org/keywords/clinical-utility","display_name":"clinical utility","score":0.4429999887943268}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5209000110626221},{"id":"https://openalex.org/C183003079","wikidata":"https://www.wikidata.org/wiki/Q1000371","display_name":"Personalization","level":2,"score":0.47839999198913574},{"id":"https://openalex.org/C2778805511","wikidata":"https://www.wikidata.org/wiki/Q1713","display_name":"Citation","level":2,"score":0.41769999265670776},{"id":"https://openalex.org/C17231256","wikidata":"https://www.wikidata.org/wiki/Q5156540","display_name":"Completeness (order theory)","level":2,"score":0.414000004529953},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3968000113964081},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.38179999589920044},{"id":"https://openalex.org/C2779473830","wikidata":"https://www.wikidata.org/wiki/Q1540899","display_name":"MEDLINE","level":2,"score":0.3598000109195709},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33079999685287476},{"id":"https://openalex.org/C2989179672","wikidata":"https://www.wikidata.org/wiki/Q6806500","display_name":"Clinical decision making","level":2,"score":0.31869998574256897},{"id":"https://openalex.org/C148220186","wikidata":"https://www.wikidata.org/wiki/Q7111912","display_name":"Outcome (game theory)","level":2,"score":0.303600013256073},{"id":"https://openalex.org/C58328972","wikidata":"https://www.wikidata.org/wiki/Q184609","display_name":"Expert system","level":2,"score":0.3000999987125397},{"id":"https://openalex.org/C2779974597","wikidata":"https://www.wikidata.org/wiki/Q28448986","display_name":"Clinical Practice","level":2,"score":0.2992999851703644},{"id":"https://openalex.org/C509550671","wikidata":"https://www.wikidata.org/wiki/Q126945","display_name":"Medical education","level":1,"score":0.29760000109672546},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.2973000109195709},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.28349998593330383},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.2793999910354614},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.27469998598098755},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.26989999413490295},{"id":"https://openalex.org/C138816342","wikidata":"https://www.wikidata.org/wiki/Q189603","display_name":"Public health","level":2,"score":0.25619998574256897},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.25609999895095825}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2606.28960","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2606.28960","pdf_url":"https://arxiv.org/pdf/2606.28960","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},{"id":"doi:10.48550/arxiv.2606.28960","doi":"https://doi.org/10.48550/arxiv.2606.28960","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.28960","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2606.28960","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2606.28960","pdf_url":"https://arxiv.org/pdf/2606.28960","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},"sustainable_development_goals":[{"score":0.8048999905586243,"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/W7166741332.pdf","grobid_xml":"https://content.openalex.org/works/W7166741332.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7164566809","https://openalex.org/W7165001305","https://openalex.org/W4416959427","https://openalex.org/W7221095347","https://openalex.org/W7221167256","https://openalex.org/W7207630722","https://openalex.org/W7208772530","https://openalex.org/W7159640047","https://openalex.org/W7214351212","https://openalex.org/W7167267914"],"abstract_inverted_index":{"Physicians":[0],"now":[1],"pose":[2],"millions":[3],"of":[4,216,266],"clinical":[5,86,104,109],"questions":[6,56],"to":[7,42,92,103,143,172],"AI":[8,192],"tools":[9,14],"each":[10,93],"week,":[11],"yet":[12],"these":[13],"are":[15],"evaluated":[16],"largely":[17],"on":[18,35,123,130,182],"hypothetical":[19],"or":[20],"exam-style":[21],"questions,":[22],"not":[23,224],"those":[24],"actually":[25],"asked":[26],"in":[27,126,151,244],"practice.":[28],"We":[29,249],"report":[30],"a":[31,84,253],"blinded":[32],"evaluation":[33],"built":[34],"620":[36],"Real-world":[37],"Point-Of-Care":[38],"Queries":[39],"(Real-POCQi)":[40],"submitted":[41],"the":[43,119,127,183,206,213,217,228,259],"OpenEvidence":[44],"(OE)":[45],"platform":[46],"by":[47,155],"physicians":[48,61,117],"spanning":[49],"30":[50],"specialties,":[51],"as":[52,54,252,256,258],"well":[53,257],"187":[55],"from":[57,70,141,175],"HealthBench.":[58,165],"149":[59],"practicing":[60],"across":[62],"36":[63],"states":[64],"made":[65],"head-to-head":[66],"comparisons":[67],"between":[68,135],"answers":[69,98],"three":[71],"frontier":[72],"general-purpose":[73,221],"models":[74,222],"(Claude":[75],"Opus":[76],"4.8,":[77],"Gemini":[78],"3.1":[79],"Pro,":[80],"and":[81,83,137,162,200,211,238],"GPT-5.5)":[82],"specialized":[85,120,218],"tool":[87,121,193,219],"(OE),":[88],"with":[89],"graders":[90],"matched":[91],"question's":[94],"specialty.":[95],"When":[96],"comparing":[97],"along":[99],"five":[100],"dimensions":[101],"relevant":[102],"decision":[105],"support":[106],"--":[107,116],"accuracy,":[108],"utility,":[110],"source":[111],"quality,":[112],"verifiability,":[113],"&":[114],"completeness":[115],"scored":[118],"highest":[122],"all":[124],"axes;":[125],"primary":[128],"analysis":[129,262],"Real-POCQi,":[131],"win":[132,136],"differences":[133],"(margins":[134],"loss":[138],"rates)":[139],"ranged":[140],"25":[142],"39":[144],"percentage":[145],"points":[146],"(p<0.001).":[147],"Results":[148],"remained":[149],"consistent":[150,214],"sensitivity":[152],"analyses":[153],"stratifying":[154],"citation":[156],"display,":[157],"answer":[158],"length,":[159],"OE-user":[160],"status,":[161],"Real-POCQi":[163,251],"versus":[164],"In":[166],"parallel,":[167],"LLM":[168],"judges":[169,203],"were":[170],"found":[171],"systematically":[173],"differ":[174],"expert":[176,202],"judges,":[177],"though":[178],"both":[179],"generally":[180],"agreed":[181],"best":[184],"model.":[185],"These":[186],"findings":[187],"underscore":[188],"two":[189],"conclusions:":[190],"(i)":[191],"evaluations":[194],"should":[195],"reflect":[196],"real-world":[197],"query":[198],"distributions":[199],"use":[201],"that":[204,227,235],"mirror":[205],"specialization":[207],"defining":[208],"modern":[209],"medicine":[210],"(ii)":[212],"advantage":[215],"over":[220],"does":[223],"necessarily":[225],"mean":[226],"latter":[229],"cannot":[230],"serve":[231],"similar":[232],"purposes,":[233],"but":[234],"targeted":[236],"engineering":[237],"customization":[239],"can":[240],"yield":[241],"meaningful":[242],"gains":[243],"performance":[245],"for":[246,263],"its":[247],"users.":[248],"release":[250],"public":[254],"benchmark,":[255],"prespecified":[260],"statistical":[261],"reproducing":[264],"results":[265],"this":[267],"study.":[268]},"counts_by_year":[{"year":2026,"cited_by_count":13}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-07-01T00:00:00"}