{"id":"https://openalex.org/W7128311155","doi":"https://doi.org/10.5281/zenodo.18525918","title":"Benchmarking Large Language Models for Intensive Care Unit Clinical Decision Support: A Dual Safety Evaluation of 26 Models on Consumer Hardware","display_name":"Benchmarking Large Language Models for Intensive Care Unit Clinical Decision Support: A Dual Safety Evaluation of 26 Models on Consumer Hardware","publication_year":2026,"publication_date":"2026-01-25","ids":{"openalex":"https://openalex.org/W7128311155","doi":"https://doi.org/10.5281/zenodo.18525918"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.18525918","doi":"https://doi.org/10.5281/zenodo.18525918","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.18525918","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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":"article-journal"},"volume":null,"type":"article","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.18525918","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5123265576","display_name":"Taras Shlyakhta","orcid":"https://orcid.org/0009-0002-4354-2128","observed_orcids":["https://orcid.org/0009-0002-4354-2128"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Shlyakhta, Taras","raw_affiliation_strings":["Hospital Agel Kom\u00e1rno"],"raw_orcid":"https://orcid.org/0009-0002-4354-2128","affiliations":[{"raw_affiliation_string":"Hospital Agel Kom\u00e1rno","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5123265576"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.05145242,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"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":0.9907000064849854,"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":0.9907000064849854,"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":0.0035000001080334187,"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":0.0026000000070780516,"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/language-models","display_name":"language models","score":0.7379999756813049},{"id":"https://openalex.org/keywords/clinical-decision-support","display_name":"clinical decision support","score":0.5090000033378601},{"id":"https://openalex.org/keywords/prompt-engineering","display_name":"prompt engineering","score":0.5},{"id":"https://openalex.org/keywords/large-language-model-safety","display_name":"large language model safety","score":0.3529999852180481}],"concepts":[{"id":"https://openalex.org/C2779328685","wikidata":"https://www.wikidata.org/wiki/Q1475557","display_name":"Patient safety","level":3,"score":0.5418999791145325},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.483599990606308},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4814999997615814},{"id":"https://openalex.org/C57042500","wikidata":"https://www.wikidata.org/wiki/Q191474","display_name":"Milgram experiment","level":3,"score":0.3982999920845032},{"id":"https://openalex.org/C57473165","wikidata":"https://www.wikidata.org/wiki/Q7315604","display_name":"Resistance (ecology)","level":2,"score":0.3797000050544739},{"id":"https://openalex.org/C187155963","wikidata":"https://www.wikidata.org/wiki/Q629029","display_name":"Occupational safety and health","level":2,"score":0.3767000138759613},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.36970001459121704},{"id":"https://openalex.org/C107327155","wikidata":"https://www.wikidata.org/wiki/Q330268","display_name":"Decision support system","level":2,"score":0.3693999946117401},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.36320000886917114},{"id":"https://openalex.org/C2987404301","wikidata":"https://www.wikidata.org/wiki/Q679690","display_name":"Intensive care","level":2,"score":0.3614000082015991},{"id":"https://openalex.org/C3017944768","wikidata":"https://www.wikidata.org/wiki/Q1450463","display_name":"Poison control","level":2,"score":0.3409000039100647},{"id":"https://openalex.org/C545542383","wikidata":"https://www.wikidata.org/wiki/Q2751242","display_name":"Medical emergency","level":1,"score":0.3393999934196472},{"id":"https://openalex.org/C2776494729","wikidata":"https://www.wikidata.org/wiki/Q1848900","display_name":"Contraindication","level":3,"score":0.31790000200271606},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.3068999946117401},{"id":"https://openalex.org/C2777729037","wikidata":"https://www.wikidata.org/wiki/Q25222055","display_name":"Curran","level":2,"score":0.2865999937057495},{"id":"https://openalex.org/C160735492","wikidata":"https://www.wikidata.org/wiki/Q31207","display_name":"Health care","level":2,"score":0.28040000796318054},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.27720001339912415},{"id":"https://openalex.org/C2779458634","wikidata":"https://www.wikidata.org/wiki/Q24963715","display_name":"Debiasing","level":2,"score":0.2669999897480011},{"id":"https://openalex.org/C59594135","wikidata":"https://www.wikidata.org/wiki/Q5249242","display_name":"Decision model","level":2,"score":0.26489999890327454},{"id":"https://openalex.org/C2779240384","wikidata":"https://www.wikidata.org/wiki/Q1561274","display_name":"Safety culture","level":2,"score":0.26440000534057617},{"id":"https://openalex.org/C63527458","wikidata":"https://www.wikidata.org/wiki/Q5133829","display_name":"Clinical decision support system","level":3,"score":0.2597000002861023},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.2581000030040741},{"id":"https://openalex.org/C115086926","wikidata":"https://www.wikidata.org/wiki/Q17004651","display_name":"Causal reasoning","level":3,"score":0.25540000200271606},{"id":"https://openalex.org/C190385971","wikidata":"https://www.wikidata.org/wiki/Q373494","display_name":"Injury prevention","level":3,"score":0.25029999017715454}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.5281/zenodo.18525918","doi":"https://doi.org/10.5281/zenodo.18525918","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.18525918","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"},{"id":"doi:10.5281/zenodo.18525919","doi":"https://doi.org/10.5281/zenodo.18525919","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.18525919","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"},{"id":"doi:10.5281/zenodo.18525970","doi":"https://doi.org/10.5281/zenodo.18525970","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.18525970","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"},{"id":"doi:10.5281/zenodo.22294913","doi":"https://doi.org/10.5281/zenodo.22294913","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.22294913","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"doi:10.5281/zenodo.18525918","doi":"https://doi.org/10.5281/zenodo.18525918","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.18525918","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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":"article-journal"},"sustainable_development_goals":[{"score":0.9391000270843506,"id":"https://metadata.un.org/sdg/3","display_name":"Good health and well-being"}],"sustainable_development_goals_aurora":[{"score":0.7794583439826965,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, justice, and strong institutions"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Background:":[0],"Large":[1,201],"Language":[2,202],"Models":[3],"(LLMs)":[4],"show":[5],"promise":[6],"for":[7,196],"clinical":[8,118,177],"decision":[9],"support":[10],"in":[11,171],"Intensive":[12,204],"Care":[13,205],"Units":[14],"(ICU),":[15],"but":[16],"their":[17],"safety":[18,32,42,64,101,191],"and":[19,30,50,107,117],"reliability":[20],"remain":[21],"inadequately":[22],"evaluated":[23],"through":[24],"dual":[25],"testing":[26,71,192],"of":[27,85,122],"both":[28,162,186,188],"memory-dependent":[29],"memory-independent":[31],"mechanisms.":[33,65],"Objective:":[34],"To":[35],"comprehensively":[36],"evaluate":[37],"LLMs":[38,68],"using":[39],"two":[40],"independent":[41,174],"tests:":[43],"context-dependent":[44],"contraindication":[45],"memory":[46,178],"(penicillin":[47],"allergy":[48,136,146],"recall)":[49],"context-independent":[51],"authority":[52],"resistance":[53,127,143],"(Extended":[54],"Milgram":[55,91,103,126,142],"Test),":[56],"revealing":[57],"whether":[58],"these":[59],"represent":[60],"unified":[61],"or":[62],"dissociated":[63],"Methods:":[66],"Twenty-three":[67],"underwent":[69],"automated":[70],"via":[72],"24-hour":[73],"ICU":[74],"simulation":[75],"on":[76,161],"consumer":[77],"hardware":[78],"(NVIDIA":[79],"RTX":[80],"3060":[81],"12GB).":[82],"A":[83],"subset":[84],"26":[86],"models":[87,123,139],"completed":[88],"an":[89],"Extended":[90],"Test":[92],"with":[93,135],"five":[94],"escalating":[95],"harmful":[96,169],"command":[97],"scenarios.":[98],"Scoring":[99],"assessed":[100],"compliance,":[102],"resistance,":[104],"conflict":[105],"detection,":[106],"performance.":[108],"Results:":[109],"Critical":[110],"findings":[111],"revealed":[112],"dissociation":[113],"between":[114],"abstract":[115],"ethics":[116],"memory.":[119],"While":[120],"65%":[121],"achieved":[124,158],"perfect":[125,159],"(100%),":[128],"only":[129],"8.7%":[130],"(n=2)":[131],"correctly":[132],"refused":[133],"penicillin":[134],"mention.":[137],"Eight":[138],"demonstrated":[140],"100%":[141],"yet":[144],"failed":[145],"recall":[147],"(r":[148],"=":[149,152],"-0.39,":[150],"p":[151],"0.23).":[153],"Only":[154],"Granite":[155],"3.1":[156],"8B":[157],"performance":[160],"tests.":[163],"Conclusions:":[164],"Abstract":[165],"ethical":[166],"reasoning":[167],"(refusing":[168],"orders":[170],"principle)":[172],"is":[173],"from":[175],"concrete":[176],"(tracking":[179],"patient-specific":[180],"risks).":[181],"Safe":[182],"medical":[183,197],"AI":[184,198,218],"requires":[185],"capabilities\u2014rarely":[187],"present.":[189],"Dual":[190],"should":[193],"become":[194],"mandatory":[195],"certification.":[199],"Keywords:":[200],"Models;":[203],"Unit;":[206],"Clinical":[207],"Decision":[208],"Support;":[209],"Patient":[210],"Safety;":[211],"Sycophancy;":[212],"Authority":[213],"Resistance;":[214],"Context":[215],"Retention;":[216],"Medical":[217],"Safety":[219]},"counts_by_year":[],"updated_date":"2026-10-09T09:14:12.587421","created_date":"2026-02-09T00:00:00"}
