{"id":"https://openalex.org/W4415016554","doi":"https://doi.org/10.48550/arxiv.2505.11733","title":"MedCaseReasoning: Evaluating and learning diagnostic reasoning from clinical case reports","display_name":"MedCaseReasoning: Evaluating and learning diagnostic reasoning from clinical case reports","publication_year":2025,"publication_date":"2025-05-16","ids":{"openalex":"https://openalex.org/W4415016554","doi":"https://doi.org/10.48550/arxiv.2505.11733"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2505.11733","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.11733","pdf_url":"https://arxiv.org/pdf/2505.11733","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2505.11733","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5002340225","display_name":"Kevin Wu","orcid":"https://orcid.org/0000-0002-4786-9796","observed_orcids":["https://orcid.org/0000-0002-4786-9796","https://orcid.org/0000-0001-7112-1190"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Kevin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Wu, Eric","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Eric","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026274141","display_name":"Rahul Thapa","orcid":"https://orcid.org/0000-0002-1137-955X","observed_orcids":["https://orcid.org/0000-0002-1137-955X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Thapa, Rahul","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102886709","display_name":"Kevin Wei","orcid":"https://orcid.org/0009-0004-8522-4333","observed_orcids":["https://orcid.org/0009-0004-8522-4333"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei, Kevin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076640237","display_name":"Angela Zhang","orcid":"https://orcid.org/0000-0003-0906-6770","observed_orcids":["https://orcid.org/0000-0003-0906-6770"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Angela","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Suresh, Arvind","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Suresh, Arvind","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024754722","display_name":"Jacqueline J. Tao","orcid":"https://orcid.org/0000-0003-1806-1269","observed_orcids":["https://orcid.org/0000-0003-1806-1269"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tao, Jacqueline J.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089070900","display_name":"Min Sun","orcid":"https://orcid.org/0000-0003-1049-1854","observed_orcids":["https://orcid.org/0000-0003-1049-1854"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sun, Min Woo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034257892","display_name":"Alejandro Lozano","orcid":"https://orcid.org/0000-0002-6952-289X","observed_orcids":["https://orcid.org/0000-0002-6952-289X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lozano, Alejandro","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5005779176","display_name":"James Zou","orcid":"https://orcid.org/0000-0001-8880-4764","observed_orcids":["https://orcid.org/0000-0001-8880-4764"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zou, James","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":5,"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":0.9307000041007996,"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":0.9307000041007996,"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":0.027499999850988388,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.014700000174343586,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/diagnostic-reasoning","display_name":"diagnostic reasoning","score":0.6679999828338623},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.8960000276565552},{"id":"https://openalex.org/keywords/llm-evaluation","display_name":"LLM evaluation","score":0.5759999752044678},{"id":"https://openalex.org/keywords/reasoning-traces","display_name":"reasoning traces","score":0.6380000114440918},{"id":"https://openalex.org/keywords/llm-fine-tuning","display_name":"LLM fine-tuning","score":0.7509999871253967},{"id":"https://openalex.org/keywords/diagnosis","display_name":"diagnosis","score":0.5419999957084656},{"id":"https://openalex.org/keywords/deepseek-r1","display_name":"DeepSeek-R1","score":0.878000020980835}],"concepts":[{"id":"https://openalex.org/C534262118","wikidata":"https://www.wikidata.org/wiki/Q177719","display_name":"Medical diagnosis","level":2,"score":0.751800000667572},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.574400007724762},{"id":"https://openalex.org/C20162079","wikidata":"https://www.wikidata.org/wiki/Q1151406","display_name":"Case-based reasoning","level":2,"score":0.5568000078201294},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.49709999561309814},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4593000113964081},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4404999911785126},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.41830000281333923},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.41290000081062317},{"id":"https://openalex.org/C37335422","wikidata":"https://www.wikidata.org/wiki/Q6888134","display_name":"Model-based reasoning","level":3,"score":0.41110000014305115},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3926999866962433},{"id":"https://openalex.org/C103057564","wikidata":"https://www.wikidata.org/wiki/Q4751139","display_name":"Analytic reasoning","level":3,"score":0.3734999895095825},{"id":"https://openalex.org/C2779473830","wikidata":"https://www.wikidata.org/wiki/Q1540899","display_name":"MEDLINE","level":2,"score":0.3698999881744385},{"id":"https://openalex.org/C3020452639","wikidata":"https://www.wikidata.org/wiki/Q454812","display_name":"Clinical judgment","level":2,"score":0.36149999499320984},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.35040000081062317},{"id":"https://openalex.org/C97364631","wikidata":"https://www.wikidata.org/wiki/Q484284","display_name":"Deductive reasoning","level":2,"score":0.33869999647140503},{"id":"https://openalex.org/C148220186","wikidata":"https://www.wikidata.org/wiki/Q7111912","display_name":"Outcome (game theory)","level":2,"score":0.334199994802475},{"id":"https://openalex.org/C3020132585","wikidata":"https://www.wikidata.org/wiki/Q2671652","display_name":"Diagnostic accuracy","level":2,"score":0.31349998712539673},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2946000099182129},{"id":"https://openalex.org/C206179267","wikidata":"https://www.wikidata.org/wiki/Q188952","display_name":"Medical history","level":2,"score":0.2912999987602234},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.290800005197525},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.2888999879360199},{"id":"https://openalex.org/C2983449737","wikidata":"https://www.wikidata.org/wiki/Q177719","display_name":"Clinical diagnosis","level":2,"score":0.28870001435279846},{"id":"https://openalex.org/C183521366","wikidata":"https://www.wikidata.org/wiki/Q7256422","display_name":"Psychology of reasoning","level":4,"score":0.2874999940395355},{"id":"https://openalex.org/C36964233","wikidata":"https://www.wikidata.org/wiki/Q7920942","display_name":"Verbal reasoning","level":3,"score":0.2840000092983246},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.2833000123500824},{"id":"https://openalex.org/C2779231881","wikidata":"https://www.wikidata.org/wiki/Q5977147","display_name":"Medical literature","level":2,"score":0.2736000120639801},{"id":"https://openalex.org/C195344581","wikidata":"https://www.wikidata.org/wiki/Q2555318","display_name":"Automated reasoning","level":2,"score":0.2632000148296356},{"id":"https://openalex.org/C2779974597","wikidata":"https://www.wikidata.org/wiki/Q28448986","display_name":"Clinical Practice","level":2,"score":0.2549000084400177},{"id":"https://openalex.org/C2989179672","wikidata":"https://www.wikidata.org/wiki/Q6806500","display_name":"Clinical decision making","level":2,"score":0.2533999979496002},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.250900000333786}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2505.11733","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.11733","pdf_url":"https://arxiv.org/pdf/2505.11733","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2505.11733","doi":"https://doi.org/10.48550/arxiv.2505.11733","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2505.11733","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2505.11733","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.11733","pdf_url":"https://arxiv.org/pdf/2505.11733","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"display_name":"Good health and well-being","score":0.8353999853134155,"id":"https://metadata.un.org/sdg/3"}],"sustainable_development_goals_aurora":[],"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":{"Doctors":[0],"and":[1,38,52,64,120,127,142,169,180,187],"patients":[2],"alike":[3],"increasingly":[4],"use":[5],"Large":[6],"Language":[7],"Models":[8],"(LLMs)":[9],"to":[10,42,88],"diagnose":[11],"clinical":[12,68,170],"cases.":[13],"However,":[14,152],"unlike":[15],"domains":[16],"such":[17],"as":[18],"math":[19],"or":[20],"coding,":[21],"where":[22],"correctness":[23],"can":[24],"be":[25,43],"objectively":[26],"defined":[27],"by":[28,173],"the":[29,36,39,58,62,67,78,131,147,159],"final":[30,59],"answer,":[31,60],"medical":[32,48,110],"diagnosis":[33],"requires":[34],"both":[35],"outcome":[37],"reasoning":[40,69,105,116,149,160,171],"process":[41],"accurate.":[44],"Currently,":[45],"widely":[46],"used":[47],"benchmarks":[49],"like":[50],"MedQA":[51],"MMLU":[53],"assess":[54],"only":[55,137,144],"accuracy":[56,141,168],"in":[57,124],"overlooking":[61],"quality":[63],"faithfulness":[65],"of":[66,146,178],"process.":[70],"To":[71],"address":[72],"this":[73],"limitation,":[74],"we":[75,153],"introduce":[76],"MedCaseReasoning,":[77],"first":[79],"open-access":[80,109],"dataset":[81,95],"for":[82,129],"evaluating":[83],"LLMs":[84,117,157],"on":[85,118,158],"their":[86,125],"ability":[87],"align":[89],"with":[90,103],"clinician-authored":[91],"diagnostic":[92,98,140,167],"reasoning.":[93],"The":[94,183],"includes":[96],"14,489":[97],"question-and-answer":[99],"cases,":[100],"each":[101],"paired":[102],"detailed":[104],"statements":[106,150],"derived":[107,162],"from":[108,163],"case":[111],"reports.":[112],"We":[113],"evaluate":[114],"state-of-the-art":[115],"MedCaseReasoning":[119,164],"find":[121],"significant":[122],"shortcomings":[123],"diagnoses":[126],"reasoning:":[128],"instance,":[130],"top-performing":[132],"open-source":[133,184],"model,":[134],"DeepSeek-R1,":[135],"achieves":[136],"48%":[138],"10-shot":[139],"mentions":[143],"64%":[145],"clinician":[148],"(recall).":[151],"demonstrate":[154],"that":[155],"fine-tuning":[156],"traces":[161],"significantly":[165],"improves":[166],"recall":[172],"an":[174],"average":[175],"relative":[176],"gain":[177],"29%":[179],"41%,":[181],"respectively.":[182],"dataset,":[185],"code,":[186],"models":[188],"are":[189],"available":[190],"at":[191],"https://github.com/kevinwu23/Stanford-MedCaseReasoning.":[192]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2025-10-10T00:00:00"}