{"id":"https://openalex.org/W7163039087","doi":"https://doi.org/10.48550/arxiv.2605.30637","title":"EHRBench: An Automated and Reliable EHR-based Benchmark for Clinical Decision Making with LLMs","display_name":"EHRBench: An Automated and Reliable EHR-based Benchmark for Clinical Decision Making with LLMs","publication_year":2026,"publication_date":"2026-05-28","ids":{"openalex":"https://openalex.org/W7163039087","doi":"https://doi.org/10.48550/arxiv.2605.30637"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.30637","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.30637","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.30637","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5137604466","display_name":"Yuzhang Xie","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xie, Yuzhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137571991","display_name":"Keqi Han","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Han, Keqi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137546458","display_name":"Yunpeng Xiao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiao, Yunpeng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033157677","display_name":"Hejie Cui","orcid":"https://orcid.org/0000-0001-6388-2619"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cui, Hejie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067651547","display_name":"Guanchen Wu","orcid":"https://orcid.org/0000-0002-5579-1052"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Guanchen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137586041","display_name":"Ziyang Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Ziyang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137590268","display_name":"Kai Shu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shu, Kai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137527702","display_name":"Jiaying Lu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lu, Jiaying","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137559574","display_name":"Xiao Hu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hu, Xiao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5137560365","display_name":"Carl Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Carl","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"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/T13702","display_name":"Machine Learning in Healthcare","score":0.8061000108718872,"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":0.8061000108718872,"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":0.04740000143647194,"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/T10350","display_name":"Electronic Health Records Systems","score":0.032099999487400055,"subfield":{"id":"https://openalex.org/subfields/3605","display_name":"Health Information Management"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.8079000115394592},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.5960000157356262},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5378999710083008},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.5285999774932861},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5227000117301941},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.4821000099182129},{"id":"https://openalex.org/keywords/decision-support-system","display_name":"Decision support system","score":0.4620000123977661},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.44359999895095825}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.8079000115394592},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6236000061035156},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.5960000157356262},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5378999710083008},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5285999774932861},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5227000117301941},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.4821000099182129},{"id":"https://openalex.org/C107327155","wikidata":"https://www.wikidata.org/wiki/Q330268","display_name":"Decision support system","level":2,"score":0.4620000123977661},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.44359999895095825},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.4374000132083893},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.42410001158714294},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.4034000039100647},{"id":"https://openalex.org/C63527458","wikidata":"https://www.wikidata.org/wiki/Q5133829","display_name":"Clinical decision support system","level":3,"score":0.4007999897003174},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3402999937534332},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33329999446868896},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.32429999113082886},{"id":"https://openalex.org/C12174686","wikidata":"https://www.wikidata.org/wiki/Q1058438","display_name":"Risk assessment","level":2,"score":0.3037000000476837},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.2994999885559082},{"id":"https://openalex.org/C2989179672","wikidata":"https://www.wikidata.org/wiki/Q6806500","display_name":"Clinical decision making","level":2,"score":0.29910001158714294},{"id":"https://openalex.org/C2776035091","wikidata":"https://www.wikidata.org/wiki/Q7928819","display_name":"Viewpoints","level":2,"score":0.2802000045776367},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.26510000228881836},{"id":"https://openalex.org/C32896092","wikidata":"https://www.wikidata.org/wiki/Q189447","display_name":"Risk management","level":2,"score":0.2637999951839447},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.25029999017715454},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.25}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.30637","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.30637","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.30637","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.30637","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.7619714736938477,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Clinical":[0],"decision-making":[1,127],"(CDM)":[2],"is":[3,136],"central":[4],"to":[5,27,32,77,150,176,183],"real-world":[6,47],"clinical":[7,48,108,126,200],"workflows,":[8],"where":[9],"clinicians":[10],"infer":[11],"diagnoses,":[12],"select":[13],"treatments,":[14],"or":[15,179],"anticipate":[16],"future":[17],"health":[18],"outcomes":[19],"under":[20],"incomplete":[21],"evidence.":[22],"LLMs":[23,45,213],"are":[24],"increasingly":[25],"used":[26],"support":[28,96],"these":[29],"decisions":[30],"due":[31],"strong":[33],"language":[34],"capabilities,":[35],"broad":[36],"biomedical":[37,105],"knowledge,":[38],"and":[39,63,81,107,119,133,159,174,182,205,216,222,238],"efficiency,":[40,144],"yet":[41,74],"the":[42,84,112,162,234],"reliability":[43,235],"of":[44,86,220,236],"on":[46,98,214],"decision":[49,66,201],"tasks":[50,101],"remains":[51],"insufficiently":[52],"understood.":[53],"To":[54,110,130],"evaluate":[55],"CDM":[56,88,100],"models,":[57,60],"especially":[58],"LLM-based":[59,125],"an":[61,72,117,139],"ideal":[62],"practical":[64,99],"medical":[65],"benchmark":[67,89,122,208],"should":[68],"be":[69],"constructed":[70,137],"via":[71],"automated":[73,118],"reliable":[75,120,244],"pipeline":[76],"ensure":[78,131],"both":[79],"scale":[80],"quality.":[82],"Moreover,":[83],"grounding":[85],"a":[87,147],"in":[90],"real":[91],"patient":[92],"EHRs":[93],"can":[94],"better":[95],"evaluation":[97],"that":[102],"require":[103],"substantive":[104],"knowledge":[106],"inference.":[109],"fill":[111],"gaps,":[113],"we":[114,145,169,189],"introduce":[115],"EHRBench,":[116],"EHR-grounded":[121],"for":[123],"evaluating":[124],"at":[128],"scale.":[129],"scalability":[132],"reliability,":[134],"EHRBench":[135,215,237],"through":[138],"EHR-LLM-KB(knowledge-base)":[140],"interaction":[141],"pipeline.":[142],"For":[143],"use":[146],"specialized":[148],"LLM":[149,245],"automatically":[151],"convert":[152],"encounter-level":[153],"EHR":[154],"trajectories":[155],"into":[156,164],"structured":[157],"templates":[158,163],"deterministically":[160],"instantiate":[161],"QA":[165,194],"items.":[166],"In":[167],"parallel,":[168],"apply":[170],"systematic":[171],"KB-based":[172],"verification":[173],"enrichment":[175],"filter":[177],"hallucinated":[178],"ambiguous":[180],"relations":[181],"improve":[184],"reliability.":[185],"Using":[186],"this":[187],"pipeline,":[188],"construct":[190],"nearly":[191],"1M":[192],"(960,067)":[193],"items":[195],"spanning":[196],"three":[197],"core":[198],"inference-required":[199],"tasks:":[202],"diagnosis,":[203],"treatment,":[204],"prognosis.":[206],"We":[207],"more":[209],"than":[210],"30":[211],"representative":[212],"provide":[217],"detailed":[218],"analyses":[219],"performance":[221],"robustness.":[223],"The":[224],"results":[225],"show":[226],"consistent":[227],"capability":[228],"trends":[229],"across":[230],"settings,":[231],"further":[232],"validating":[233],"highlighting":[239],"actionable":[240],"gaps":[241],"toward":[242],"clinically":[243],"systems.":[246]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-06-02T00:00:00"}