{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,29]],"date-time":"2026-10-29T18:56:57Z","timestamp":1793300217254,"version":"4.5.0"},"reference-count":42,"publisher":"Elsevier BV","issue":"2","license":[{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2025,11,20]],"date-time":"2025-11-20T00:00:00Z","timestamp":1763596800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["82388101"],"award-info":[{"award-number":["82388101"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004826","name":"Natural Science Foundation of Beijing Municipality","doi-asserted-by":"publisher","award":["12171270"],"award-info":[{"award-number":["12171270"]}],"id":[{"id":"10.13039\/501100004826","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["clinicalkey.com","clinicalkey.com.au","clinicalkey.es","clinicalkey.fr","clinicalkey.jp","thelancet.com","elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["The Lancet Digital Health"],"published-print":{"date-parts":[[2026,2]]},"DOI":"10.1016\/j.landig.2025.100953","type":"journal-article","created":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T03:55:08Z","timestamp":1772078108000},"page":"100953","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":4,"title":["RareArena: a comprehensive benchmark dataset unveiling the potential of large language models in rare disease diagnosis"],"prefix":"10.1016","volume":"8","author":[{"given":"Haichao","family":"Chen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9425-7752","authenticated-orcid":false,"given":"Zhengyun","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Songchi","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shikai","family":"Hu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8378-1249","authenticated-orcid":false,"given":"Jinyuan","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ye","family":"Jin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xianghong","family":"Jin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yih Chung","family":"Tham","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3175-0344","authenticated-orcid":false,"given":"Xiaofei","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weizhi","family":"Ma","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Honghan","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8510-2556","authenticated-orcid":false,"given":"Bin","family":"Sheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuyang","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sheng","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8448-1264","authenticated-orcid":false,"given":"Tien Yin","family":"Wong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.landig.2025.100953_bib1","doi-asserted-by":"crossref","first-page":"165","DOI":"10.1038\/s41431-019-0508-0","article-title":"Estimating cumulative point prevalence of rare diseases: analysis of the Orphanet database","volume":"28","author":"Nguengang Wakap","year":"2020","journal-title":"Eur J Hum Genet"},{"key":"10.1016\/j.landig.2025.100953_bib2","series-title":"Rare diseases: individually rare, collectively common","first-page":"139","volume":"11","year":"2023"},{"key":"10.1016\/j.landig.2025.100953_bib3","author":"Andreu"},{"key":"10.1016\/j.landig.2025.100953_bib4","first-page":"2000","article-title":"The cost of rare diseases","volume":"326","author":"Rubin","year":"2021","journal-title":"JAMA"},{"key":"10.1016\/j.landig.2025.100953_bib5","doi-asserted-by":"crossref","first-page":"77","DOI":"10.1038\/d41573-019-00180-y","article-title":"How many rare diseases are there?","volume":"19","author":"Haendel","year":"2020","journal-title":"Nat Rev Drug Discov"},{"key":"10.1016\/j.landig.2025.100953_bib6","doi-asserted-by":"crossref","first-page":"171","DOI":"10.1186\/s13023-021-01788-3","article-title":"Rare disease awareness and perspectives of physicians in China: a questionnaire-based study","volume":"16","author":"Li","year":"2021","journal-title":"Orphanet J Rare Dis"},{"key":"10.1016\/j.landig.2025.100953_bib7","doi-asserted-by":"crossref","first-page":"99","DOI":"10.1186\/s13023-019-1075-8","article-title":"Information needs of physicians regarding the diagnosis of rare diseases: a questionnaire-based study in Belgium","volume":"14","author":"Vandeborne","year":"2019","journal-title":"Orphanet J Rare Dis"},{"key":"10.1016\/j.landig.2025.100953_bib8","doi-asserted-by":"crossref","first-page":"418","DOI":"10.1186\/s13023-022-02530-3","article-title":"Diagnostic delay in rare diseases: data from the Spanish rare diseases patient registry","volume":"17","author":"Benito-Lozano","year":"2022","journal-title":"Orphanet J Rare Dis"},{"key":"10.1016\/j.landig.2025.100953_bib9","doi-asserted-by":"crossref","unstructured":"The Lancet Global Health. The landscape for rare diseases in 2024. 12: e341.","DOI":"10.1016\/S2214-109X(24)00056-1"},{"key":"10.1016\/j.landig.2025.100953_bib10","doi-asserted-by":"crossref","DOI":"10.1001\/jamanetworkopen.2024.8895","article-title":"Use of a large language model to assess clinical acuity of adults in the emergency department","volume":"7","author":"Williams","year":"2024","journal-title":"JAMA Netw Open"},{"key":"10.1016\/j.landig.2025.100953_bib11","doi-asserted-by":"crossref","DOI":"10.2196\/53297","article-title":"Triage performance across large language models, ChatGPT, and untrained doctors in emergency medicine: comparative study","volume":"26","author":"Masanneck","year":"2024","journal-title":"J Med Internet Res"},{"key":"10.1016\/j.landig.2025.100953_bib12","doi-asserted-by":"crossref","first-page":"e555","DOI":"10.1016\/S2589-7500(24)00097-9","article-title":"The diagnostic and triage accuracy of the GPT-3 artificial intelligence model: an observational study","volume":"6","author":"Levine","year":"2024","journal-title":"Lancet Digit Health"},{"key":"10.1016\/j.landig.2025.100953_bib13","doi-asserted-by":"crossref","first-page":"1574","DOI":"10.1038\/s41591-024-02933-8","article-title":"Large language models for preventing medication direction errors in online pharmacies","volume":"30","author":"Pais","year":"2024","journal-title":"Nat Med"},{"key":"10.1016\/j.landig.2025.100953_bib14","doi-asserted-by":"crossref","first-page":"78","DOI":"10.1001\/jama.2023.8288","article-title":"Accuracy of a generative artificial intelligence model in a complex diagnostic challenge","volume":"330","author":"Kanjee","year":"2023","journal-title":"JAMA"},{"key":"10.1016\/j.landig.2025.100953_bib15","doi-asserted-by":"crossref","DOI":"10.1001\/jamanetworkopen.2023.25000","article-title":"Use of GPT-4 to analyze medical records of patients with extensive investigations and delayed diagnosis","volume":"6","author":"Shea","year":"2023","journal-title":"JAMA Netw Open"},{"key":"10.1016\/j.landig.2025.100953_bib16","article-title":"Assessing and enhancing large language models in rare disease question-answering","author":"Wang","year":"2024","journal-title":"arXiv"},{"key":"10.1016\/j.landig.2025.100953_bib17","article-title":"ChatGPT as a medical doctor? A diagnostic accuracy study on common and rare diseases","author":"Mehnen","year":"2023","journal-title":"medRxiv"},{"key":"10.1016\/j.landig.2025.100953_bib18","article-title":"Assessing DxGPT: diagnosing rare diseases with various large language models","author":"do Olmo","year":"2024","journal-title":"medRxiv"},{"key":"10.1016\/j.landig.2025.100953_bib19","series-title":"RareBench: Can LLMs serve as rare diseases specialists?","first-page":"4850","author":"Chen","year":"2024"},{"key":"10.1016\/j.landig.2025.100953_bib20","article-title":"Systematic benchmarking demonstrates large language models have not reached the diagnostic accuracy of traditional rare-disease decision support tools","author":"Reese","year":"2025","journal-title":"medRxiv"},{"key":"10.1016\/j.landig.2025.100953_bib21","doi-asserted-by":"crossref","first-page":"1097","DOI":"10.1038\/s41591-021-01356-z","article-title":"Phenotypic signatures in clinical data enable systematic identification of patients for genetic testing","volume":"27","author":"Morley","year":"2021","journal-title":"Nat Med"},{"key":"10.1016\/j.landig.2025.100953_bib22","article-title":"MSDiagnosis: a benchmark for evaluating large language models in multi-step clinical diagnosis","author":"Hou","year":"2024","journal-title":"arXiv"},{"key":"10.1016\/j.landig.2025.100953_bib23","article-title":"ClinicalLab: aligning agents for multi-departmental clinical diagnostics in the real world","author":"Yan","year":"2024","journal-title":"arXiv"},{"key":"10.1016\/j.landig.2025.100953_bib24","doi-asserted-by":"crossref","first-page":"172","DOI":"10.1038\/s41586-023-06291-2","article-title":"Large language models encode clinical knowledge","volume":"620","author":"Singhal","year":"2023","journal-title":"Nature"},{"key":"10.1016\/j.landig.2025.100953_bib25","doi-asserted-by":"crossref","first-page":"909","DOI":"10.1038\/s41597-023-02814-8","article-title":"A large-scale dataset of patient summaries for retrieval-based clinical decision support systems","volume":"10","author":"Zhao","year":"2023","journal-title":"Sci Data"},{"key":"10.1016\/j.landig.2025.100953_bib26","first-page":"518","article-title":"Orphanet: a European database for rare diseases","volume":"152","author":"Weinreich","year":"2008","journal-title":"Ned Tijdschr Geneeskd"},{"key":"10.1016\/j.landig.2025.100953_bib27","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0170365","article-title":"Clinical practice guidelines for rare diseases: the Orphanet database","volume":"12","author":"Pavan","year":"2017","journal-title":"PLoS One"},{"key":"10.1016\/j.landig.2025.100953_bib28","doi-asserted-by":"crossref","DOI":"10.1016\/j.jbi.2021.103983","article-title":"CODER: knowledge-infused cross-lingual medical term embedding for term normalization","volume":"126","author":"Yuan","year":"2022","journal-title":"J Biomed Inform"},{"key":"10.1016\/j.landig.2025.100953_bib29","series-title":"Interpretation of diagnostic tests","author":"Wallach","year":"2007"},{"key":"10.1016\/j.landig.2025.100953_bib30","doi-asserted-by":"crossref","DOI":"10.1155\/2019\/1891569","article-title":"Medical diagnostic tests: a review of test anatomy, phases, and statistical treatment of data","volume":"2019","author":"Bolboac\u0103","year":"2019","journal-title":"Comput Math Methods Med"},{"key":"10.1016\/j.landig.2025.100953_bib31","article-title":"Qwen2.5-coder technical report","author":"Hui","year":"2024","journal-title":"arXiv"},{"key":"10.1016\/j.landig.2025.100953_bib32","article-title":"Phi-3 technical report: a highly capable language model locally on your phone","author":"Abdin","year":"2024","journal-title":"arXiv"},{"key":"10.1016\/j.landig.2025.100953_bib33","article-title":"Gemma 2: improving open language models at a practical size","author":"Team","year":"2024","journal-title":"arXiv"},{"key":"10.1016\/j.landig.2025.100953_bib34","first-page":"26045","article-title":"Ultramedical: building specialized generalists in biomedicine","volume":"37","author":"Zhang","year":"2024","journal-title":"Adv Neural Inf Process Syst"},{"key":"10.1016\/j.landig.2025.100953_bib35","doi-asserted-by":"crossref","first-page":"97","DOI":"10.1038\/s41746-025-01488-3","article-title":"Benchmarking the diagnostic performance of open source LLMs in 1933 Eurorad case reports","volume":"8","author":"Kim","year":"2025","journal-title":"NPJ Digit Med"},{"key":"10.1016\/j.landig.2025.100953_bib36","article-title":"A preliminary study of o1 in medicine: are we closer to an AI doctor?","author":"Xie","year":"2024","journal-title":"arXiv"},{"key":"10.1016\/j.landig.2025.100953_bib37","article-title":"Improving interactive diagnostic ability of a large language model agent through clinical experience learning","author":"Sun","year":"2025","journal-title":"arXiv"},{"key":"10.1016\/j.landig.2025.100953_bib38","article-title":"Scaling laws for neural language models","author":"Kaplan","year":"2020","journal-title":"arXiv"},{"key":"10.1016\/j.landig.2025.100953_bib39","first-page":"578","article-title":"Do we still need clinical language models?","volume":"290","author":"Lehman","year":"2023","journal-title":"Proc Mach Learn Res"},{"key":"10.1016\/j.landig.2025.100953_bib40","doi-asserted-by":"crossref","first-page":"528","DOI":"10.1016\/j.ijmedinf.2013.01.005","article-title":"FindZebra: a search engine for rare diseases","volume":"82","author":"Dragusin","year":"2013","journal-title":"Int J Med Inform"},{"key":"10.1016\/j.landig.2025.100953_bib41","doi-asserted-by":"crossref","first-page":"51","DOI":"10.1016\/j.jbi.2017.07.016","article-title":"Finding patients using similarity measures in a rare diseases-oriented clinical data warehouse: Dr. Warehouse and the needle in the needle stack","volume":"73","author":"Garcelon","year":"2017","journal-title":"J Biomed Inform"},{"key":"10.1016\/j.landig.2025.100953_bib42","doi-asserted-by":"crossref","first-page":"190","DOI":"10.1038\/s41746-024-01185-7","article-title":"Hidden flaws behind expert-level accuracy of multimodal GPT-4 vision in medicine","volume":"7","author":"Jin","year":"2024","journal-title":"NPJ Digit Med"}],"container-title":["The Lancet Digital Health"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S2589750025001359?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S2589750025001359?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T20:21:05Z","timestamp":1775247665000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S2589750025001359"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2]]},"references-count":42,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2026,2]]}},"alternative-id":["S2589750025001359"],"URL":"https:\/\/doi.org\/10.1016\/j.landig.2025.100953","relation":{},"ISSN":["2589-7500"],"issn-type":[{"value":"2589-7500","type":"print"}],"subject":[],"published":{"date-parts":[[2026,2]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"RareArena: a comprehensive benchmark dataset unveiling the potential of large language models in rare disease diagnosis","name":"articletitle","label":"Article Title"},{"value":"The Lancet Digital Health","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.landig.2025.100953","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2025 The Author(s). Published by Elsevier Ltd.","name":"copyright","label":"Copyright"}],"article-number":"100953"}}