{"id":"https://openalex.org/W7118167914","doi":"https://doi.org/10.1109/aiccsa66935.2025.11315481","title":"Information Reasoning and Question Answering in Healthcare: A PubMedQA Benchmark Study","display_name":"Information Reasoning and Question Answering in Healthcare: A PubMedQA Benchmark Study","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W7118167914","doi":"https://doi.org/10.1109/aiccsa66935.2025.11315481"},"language":null,"primary_location":{"id":"doi:10.1109/aiccsa66935.2025.11315481","is_oa":false,"landing_page_url":"https://doi.org/10.1109/aiccsa66935.2025.11315481","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/ACS 22nd International Conference on Computer Systems and Applications (AICCSA)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5058607205","display_name":"Dina Sayed","orcid":null},"institutions":[{"id":"https://openalex.org/I1850255","display_name":"University of Basel","ror":"https://ror.org/02s6k3f65","country_code":"CH","type":"education","lineage":["https://openalex.org/I1850255"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Dina Sayed","raw_affiliation_strings":["University of Basel,Databases and Information Systems Research Group,Basel,Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Basel,Databases and Information Systems Research Group,Basel,Switzerland","institution_ids":["https://openalex.org/I1850255"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034703920","display_name":"Heiko Schuldt","orcid":"https://orcid.org/0000-0001-9865-6371"},"institutions":[{"id":"https://openalex.org/I1850255","display_name":"University of Basel","ror":"https://ror.org/02s6k3f65","country_code":"CH","type":"education","lineage":["https://openalex.org/I1850255"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Heiko Schuldt","raw_affiliation_strings":["University of Basel,Databases and Information Systems Research Group,Basel,Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Basel,Databases and Information Systems Research Group,Basel,Switzerland","institution_ids":["https://openalex.org/I1850255"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1850255"],"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":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.4505999982357025,"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/T10028","display_name":"Topic Modeling","score":0.4505999982357025,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.21160000562667847,"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/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.121799997985363,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7943000197410583},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.6003000140190125},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4814999997615814},{"id":"https://openalex.org/keywords/health-care","display_name":"Health care","score":0.43389999866485596},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.4219000041484833},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.3991999924182892},{"id":"https://openalex.org/keywords/unstructured-data","display_name":"Unstructured data","score":0.34470000863075256}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7943000197410583},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7383000254631042},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.6003000140190125},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5188000202178955},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.5073999762535095},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4814999997615814},{"id":"https://openalex.org/C160735492","wikidata":"https://www.wikidata.org/wiki/Q31207","display_name":"Health care","level":2,"score":0.43389999866485596},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.4219000041484833},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.3991999924182892},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3605000078678131},{"id":"https://openalex.org/C2781252014","wikidata":"https://www.wikidata.org/wiki/Q1141900","display_name":"Unstructured data","level":3,"score":0.34470000863075256},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3310000002384186},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.33090001344680786},{"id":"https://openalex.org/C3019150057","wikidata":"https://www.wikidata.org/wiki/Q92779279","display_name":"Medical information","level":2,"score":0.32010000944137573},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.31929999589920044},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2840999960899353},{"id":"https://openalex.org/C120567893","wikidata":"https://www.wikidata.org/wiki/Q1582085","display_name":"Knowledge extraction","level":2,"score":0.28209999203681946},{"id":"https://openalex.org/C145642194","wikidata":"https://www.wikidata.org/wiki/Q870895","display_name":"Health informatics","level":3,"score":0.271699994802475},{"id":"https://openalex.org/C180198813","wikidata":"https://www.wikidata.org/wiki/Q121182","display_name":"Information system","level":2,"score":0.2687000036239624},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2648000121116638},{"id":"https://openalex.org/C45983554","wikidata":"https://www.wikidata.org/wiki/Q3412851","display_name":"Information quality","level":3,"score":0.2612999975681305},{"id":"https://openalex.org/C37335422","wikidata":"https://www.wikidata.org/wiki/Q6888134","display_name":"Model-based reasoning","level":3,"score":0.2524000108242035}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/aiccsa66935.2025.11315481","is_oa":false,"landing_page_url":"https://doi.org/10.1109/aiccsa66935.2025.11315481","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/ACS 22nd International Conference on Computer Systems and Applications (AICCSA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.4933192729949951}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1981208470","https://openalex.org/W2032090856","https://openalex.org/W2101105183","https://openalex.org/W2123442489","https://openalex.org/W2291662195","https://openalex.org/W2560647685","https://openalex.org/W2970482702","https://openalex.org/W3046375318","https://openalex.org/W3155040665","https://openalex.org/W3162922479","https://openalex.org/W3166508187","https://openalex.org/W4287889346","https://openalex.org/W4386120650","https://openalex.org/W4394782456","https://openalex.org/W4400111803","https://openalex.org/W4401042843"],"related_works":[],"abstract_inverted_index":{"Information":[0],"extraction":[1],"and":[2,14,32,36,39,58,115,136,142,149,158,185],"analysis":[3,128],"in":[4,11,17,74,77,180,201],"healthcare":[5,68],"have":[6],"benefited":[7],"significantly":[8,91],"from":[9],"advances":[10],"the":[12,51,59,71,82,99,110,133,162],"AI":[13],"NLP":[15],"community":[16],"recent":[18,72],"years,":[19],"often":[20],"directly":[21],"impacting":[22],"human":[23],"lives":[24],"or":[25],"at":[26],"least":[27],"their":[28],"well-being.":[29],"However,":[30],"processing":[31],"analyzing":[33],"mostly":[34],"unstructured":[35],"semi-structured":[37],"health":[38,157],"biomedical":[40,159],"information":[41,113,160],"presents":[42],"substantial":[43],"challenges":[44],"to":[45,155,191],"researchers.":[46],"The":[47],"inherent":[48],"complexity":[49],"of":[50,62,84,86,112,129,132,164,182,206],"domain,":[52],"limited":[53],"data":[54,56,88],"availability,":[55],"ambiguity,":[57],"high":[60],"cost":[61],"involving":[63],"medical":[64,103],"experts":[65],"make":[66],"supporting":[67,165],"difficult.":[69],"With":[70],"revolution":[73],"AI,":[75],"particularly":[76],"Large":[78],"Language":[79],"Models":[80],"(LLMs),":[81],"quality":[83,184],"analyses":[85],"these":[87],"has":[89,95],"increased":[90],"-":[92],"though":[93],"it":[94],"not":[96],"yet":[97],"reached":[98],"level":[100],"required":[101],"by":[102,147],"practitioners.":[104],"In":[105],"this":[106],"work,":[107],"we":[108],"address":[109],"challenge":[111],"reasoning":[114],"question":[116],"answering,":[117],"with":[118,161],"a":[119,126,151],"particular":[120],"focus":[121],"on":[122],"healthcare.":[123],"We":[124,139],"conduct":[125],"detailed":[127],"PubMedQA,":[130],"one":[131],"most":[134,176],"challenging":[135],"prominent":[137],"benchmarks.":[138],"design,":[140],"implement,":[141],"evaluate":[143],"Med-RCQ":[144],"(Medical":[145],"Reasoning":[146],"Concluding":[148],"Questioning),":[150],"novel":[152],"LLM-based":[153],"method":[154],"analyze":[156],"objective":[163],"informed":[166],"decisions.":[167],"Our":[168],"PubMedQA":[169],"benchmark":[170,199],"results":[171,189,200],"show":[172],"that":[173],"MedRCQ":[174],"outperforms":[175],"competing":[177],"open":[178],"approaches":[179],"terms":[181],"result":[183],"even":[186],"provides":[187],"similar":[188],"compared":[190],"large":[192],"commercial":[193],"models,":[194],"while":[195],"outperforming":[196],"all":[197],"other":[198],"an":[202],"\u2018accuracy":[203],"per":[204],"number":[205],"model":[207],"parameters\u2019":[208],"metric.":[209]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-01-05T00:00:00"}