{"id":"https://openalex.org/W4416779554","doi":"https://doi.org/10.7490/f1000research.1120392.1","title":"Asking the right questions: Benchmarking large language models in the development of clinical consultation templates","display_name":"Asking the right questions: Benchmarking large language models in the development of clinical consultation templates","publication_year":2025,"publication_date":"2025-11-13","ids":{"openalex":"https://openalex.org/W4416779554","doi":"https://doi.org/10.7490/f1000research.1120392.1"},"language":"en","primary_location":{"id":"doi:10.7490/f1000research.1120392.1","doi":"https://doi.org/10.7490/f1000research.1120392.1","is_oa":true,"landing_page_url":"https://doi.org/10.7490/f1000research.1120392.1","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"},"volume":null,"type":"other","is_traditional":false,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.7490/f1000research.1120392.1","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5082108649","display_name":"Liam G. McCoy","orcid":"https://orcid.org/0000-0002-4468-2256","observed_orcids":["https://orcid.org/0000-0002-4468-2256"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liam G. McCoy","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056466429","display_name":"Fateme Nateghi Haredasht","orcid":"https://orcid.org/0000-0002-8874-8835","observed_orcids":["https://orcid.org/0000-0002-8874-8835"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fateme Nateghi Haredasht","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101630248","display_name":"David W.\u2013L. Wu","orcid":"https://orcid.org/0000-0002-6924-6047","observed_orcids":["https://orcid.org/0000-0002-6924-6047"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"David Wu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034182517","display_name":"David Wu","orcid":"https://orcid.org/0000-0003-1965-025X","observed_orcids":["https://orcid.org/0000-0003-1965-025X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"David JH Wu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120540633","display_name":"Sarita Khemani","orcid":"https://orcid.org/0000-0002-5836-0688","observed_orcids":["https://orcid.org/0000-0002-5836-0688"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sarita Khemani","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077342977","display_name":"Vishnu Ravi","orcid":"https://orcid.org/0000-0003-0359-1275","observed_orcids":["https://orcid.org/0000-0003-0359-1275"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vishnu Ravi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043882260","display_name":"Saloni Kumar Maharaj","orcid":"https://orcid.org/0009-0006-1498-9755","observed_orcids":["https://orcid.org/0009-0006-1498-9755"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Saloni Kumar Maharaj","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056996128","display_name":"Kelvin Zhenghao Li","orcid":"https://orcid.org/0000-0002-9993-5118","observed_orcids":["https://orcid.org/0000-0002-9993-5118"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kelvin Zhenghao Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086769682","display_name":"Abass M. Conteh","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Abass Conteh","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063376595","display_name":"Yingjie Weng","orcid":"https://orcid.org/0000-0003-3015-7036","observed_orcids":["https://orcid.org/0000-0003-3015-7036"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yingjie Weng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Kanav Chopra","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kanav Chopra","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079305230","display_name":"Daniel Shirvani","orcid":"https://orcid.org/0000-0002-1050-6158","observed_orcids":["https://orcid.org/0000-0002-1050-6158"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Daniel Shirvani","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070936825","display_name":"Leah Rosengaus","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Leah Rosengaus","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Arth Pahwa","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Arth Pahwa","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111956821","display_name":"Lena M. Giang","orcid":"https://orcid.org/0000-0001-6678-3544","observed_orcids":["https://orcid.org/0000-0001-6678-3544"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lena Giang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030674015","display_name":"Olivia Jee","orcid":"https://orcid.org/0000-0002-1255-7055","observed_orcids":["https://orcid.org/0000-0002-1255-7055"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Olivia Jee","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103153068","display_name":"Ethan Goh","orcid":"https://orcid.org/0009-0001-7491-4257","observed_orcids":["https://orcid.org/0009-0001-7491-4257"]},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ethan Goh","raw_affiliation_strings":["Stanford University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046725885","display_name":"Jonathan H. Chen","orcid":"https://orcid.org/0000-0002-4387-8740","observed_orcids":["https://orcid.org/0000-0002-4387-8740"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jonathan H. Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5103153068"],"corresponding_institution_ids":["https://openalex.org/I97018004"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"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":0.9731000065803528,"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":0.9731000065803528,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.009800000116229057,"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":0.0034000000450760126,"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/large-language-models","display_name":"large language models","score":0.996999979019165},{"id":"https://openalex.org/keywords/e-consultation","display_name":"e-consultation","score":0.7820000052452087},{"id":"https://openalex.org/keywords/benchmarking","display_name":"benchmarking","score":0.7149999737739563},{"id":"https://openalex.org/keywords/prompt-optimization","display_name":"prompt optimization","score":0.7630000114440918},{"id":"https://openalex.org/keywords/multi-agent-pipeline","display_name":"multi-agent pipeline","score":0.8309999704360962},{"id":"https://openalex.org/keywords/specialty-variation","display_name":"specialty variation","score":0.3659999966621399},{"id":"https://openalex.org/keywords/pain-medicine","display_name":"pain medicine","score":0.9900000095367432},{"id":"https://openalex.org/keywords/clinical-information-exchange","display_name":"clinical information exchange","score":0.5640000104904175},{"id":"https://openalex.org/keywords/llm-evaluation","display_name":"LLM evaluation","score":0.5389999747276306}],"concepts":[{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.6028000116348267},{"id":"https://openalex.org/C82714645","wikidata":"https://www.wikidata.org/wiki/Q438331","display_name":"Template","level":2,"score":0.5989999771118164},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5842000246047974},{"id":"https://openalex.org/C2777615720","wikidata":"https://www.wikidata.org/wiki/Q11888847","display_name":"Prioritization","level":2,"score":0.5666000247001648},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5486999750137329},{"id":"https://openalex.org/C197947376","wikidata":"https://www.wikidata.org/wiki/Q5155608","display_name":"Comparability","level":2,"score":0.47369998693466187},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.38839998841285706},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.3862999975681305},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.38339999318122864},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.3513000011444092},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3434999883174896},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3276999890804291},{"id":"https://openalex.org/C195094911","wikidata":"https://www.wikidata.org/wiki/Q14167904","display_name":"Process management","level":1,"score":0.31200000643730164},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3077000081539154},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.30550000071525574},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3001999855041504},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.29420000314712524},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.29159998893737793},{"id":"https://openalex.org/C189693848","wikidata":"https://www.wikidata.org/wiki/Q6031064","display_name":"Information exchange","level":2,"score":0.28679999709129333},{"id":"https://openalex.org/C145642194","wikidata":"https://www.wikidata.org/wiki/Q870895","display_name":"Health informatics","level":3,"score":0.28279998898506165},{"id":"https://openalex.org/C2779974597","wikidata":"https://www.wikidata.org/wiki/Q28448986","display_name":"Clinical Practice","level":2,"score":0.27549999952316284},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.27219998836517334},{"id":"https://openalex.org/C2779473830","wikidata":"https://www.wikidata.org/wiki/Q1540899","display_name":"MEDLINE","level":2,"score":0.2694999873638153},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.26660001277923584},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.25600001215934753},{"id":"https://openalex.org/C184356942","wikidata":"https://www.wikidata.org/wiki/Q830382","display_name":"Best practice","level":2,"score":0.2529999911785126}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.7490/f1000research.1120392.1","doi":"https://doi.org/10.7490/f1000research.1120392.1","is_oa":true,"landing_page_url":"https://doi.org/10.7490/f1000research.1120392.1","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.7490/f1000research.1120392.1","doi":"https://doi.org/10.7490/f1000research.1120392.1","is_oa":true,"landing_page_url":"https://doi.org/10.7490/f1000research.1120392.1","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/3","display_name":"Good health and well-being","score":0.5683000087738037}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7164998437","https://openalex.org/W7203752643","https://openalex.org/W7220852171","https://openalex.org/W4386557455","https://openalex.org/W7222684247","https://openalex.org/W7151865890","https://openalex.org/W4417399510","https://openalex.org/W7219155282","https://openalex.org/W4399994866","https://openalex.org/W4413868110"],"abstract_inverted_index":{"This":[0],"study":[1],"evaluates":[2],"the":[3,97,136,154,180],"capacity":[4],"of":[5,157],"large":[6],"language":[7],"models":[8,77],"(LLMs)":[9],"to":[10,51,84,94,148],"generate":[11,88],"structured":[12,128],"clinical":[13,58,129],"consultation":[14],"templates":[15,22,91,166],"for":[16,138,179],"electronic":[17],"consultation.":[18],"Using":[19],"145":[20],"expert-crafted":[21],"developed":[23],"and":[24,45,56,70,92,118,167],"routinely":[25],"used":[26],"by":[27],"Stanford\u2019s":[28],"eConsult":[29],"team,":[30],"we":[31,73],"assess":[32],"frontier":[33],"models\u2014including":[34],"o3,":[35],"GPT-4o,":[36],"Kimi":[37],"K2,":[38],"Claude":[39],"4":[40],"Sonnet,":[41],"Llama":[42],"3":[43],"70B,":[44],"Gemini":[46],"2.5":[47],"Pro\u2014for":[48],"their":[49],"ability":[50,147],"produce":[52],"clinically":[53,99,150,175],"coherent,":[54],"concise,":[55],"prioritized":[57],"question":[59],"schemas.":[60],"Through":[61],"a":[62,145],"multi-agent":[63],"pipeline":[64],"combining":[65],"prompt":[66],"optimization,":[67],"semantic":[68],"autograding,":[69],"prioritization":[71],"analysis,":[72],"show":[74],"that":[75,124,143],"while":[76,134],"like":[78],"o3":[79],"achieve":[80],"high":[81],"comprehensiveness":[82],"(up":[83],"92.2%),":[85],"they":[86],"consistently":[87],"excessively":[89],"long":[90],"fail":[93],"correctly":[95],"prioritize":[96,149],"most":[98],"important":[100],"questions":[101],"under":[102],"length":[103],"constraints.":[104],"Performance":[105],"varies":[106],"across":[107],"specialties,":[108],"with":[109],"significant":[110],"degradation":[111],"in":[112],"narrative-driven":[113],"fields":[114],"such":[115],"as":[116],"psychiatry":[117],"pain":[119],"medicine.":[120],"Our":[121],"findings":[122],"demonstrate":[123],"LLMs":[125],"can":[126],"enhance":[127],"information":[130,152],"exchange":[131],"between":[132],"physicians,":[133],"highlighting":[135],"need":[137],"more":[139],"robust":[140],"evaluation":[141],"methods":[142],"capture":[144,173],"model\u2019s":[146],"salient":[151],"within":[153],"time":[155],"constraints":[156],"real-world":[158],"physician":[159],"communication.":[160],"Limitations":[161],"include":[162],"reliance":[163],"on":[164,183],"Stanford-specific":[165],"concordance-based":[168],"grading,":[169],"which":[170],"may":[171],"not":[172],"all":[174],"reasonable":[176],"outputs.":[177],"Poster":[178],"Pacific":[181],"Symposium":[182],"Biocomputing":[184],"2026":[185]},"counts_by_year":[],"updated_date":"2026-11-01T11:40:01.658920","created_date":"2025-11-28T00:00:00"}