{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,16]],"date-time":"2026-10-16T13:01:22Z","timestamp":1792155682602,"version":"4.4.0"},"reference-count":57,"publisher":"JMIR Publications Inc.","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J Med Internet Res"],"abstract":"Abstract<\/jats:title>\n \n Background<\/jats:title>\n Rare hematologic diseases are frequently underdiagnosed or misdiagnosed due to their clinical complexity. Whether new-generation large language models (LLMs), particularly those using chain-of-thought reasoning, can improve diagnostic accuracy remains unclear.<\/jats:p>\n <\/jats:sec>\n \n Objective<\/jats:title>\n This study aimed to evaluate the diagnostic performance of new-generation commercial LLMs in rare hematologic diseases and to determine whether the LLM output enhances physicians\u2019 diagnostic accuracy.<\/jats:p>\n <\/jats:sec>\n \n Methods<\/jats:title>\n We conducted a 2-phase study. In the retrospective phase, we evaluated 7 mainstream LLMs on 158 nonpublic real-world admission records covering 9 rare hematologic diseases, assessed diagnostic performance using top-10 accuracy and mean reciprocal rank (MRR), and evaluated ranking stability via Jaccard similarity and entropy. Spearman rank correlation was used to examine the association between physicians\u2019 diagnoses and LLM-generated outputs. In the prospective phase, 28 physicians with varying levels of experience diagnosed 5 cases each, gaining access to LLM-generated diagnoses across 3 sequential steps to assess whether LLMs can improve diagnostic accuracy.<\/jats:p>\n <\/jats:sec>\n \n Results<\/jats:title>\n In the retrospective phase, ChatGPT-o1-preview demonstrated the highest top-10 accuracy (70.3%) and MRR (0.577), and DeepSeek-R1 ranked second. Diagnostic performance was low for amyloid light-chain (AL) amyloidosis; Castleman disease; Erdheim-Chester disease; and polyneuropathy, organomegaly, endocrinopathy, monoclonal gammopathy, and skin changes (POEMS) syndrome. Interestingly, higher accuracy often correlated with lower ranking stability across most LLMs. The physician performance showed a strong correlation with both top-10 accuracy (\u03c1=0.565) and MRR (\u03c1=0.650). In the prospective phase, LLMs significantly improved the diagnostic accuracy of less-experienced physicians; no significant benefit was observed for specialists. However, when LLMs generated biased responses, physician performance often failed to improve or even declined.<\/jats:p>\n <\/jats:sec>\n \n Conclusions<\/jats:title>\n Without fine-tuning, new-generation commercial LLMs, particularly those with chain-of-thought reasoning, can identify diagnoses of rare hematologic diseases with high accuracy and significantly enhance the diagnostic performance of less-experienced physicians. Nevertheless, biased LLM outputs may mislead clinicians, highlighting the need for critical appraisal and cautious clinical integration with appropriate safeguard systems.<\/jats:p>\n <\/jats:sec>","DOI":"10.2196\/77334","type":"journal-article","created":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T10:38:41Z","timestamp":1760092721000},"page":"e77334-e77334","source":"Crossref","is-referenced-by-count":13,"title":["Performance of Large Language Models in Diagnosing Rare Hematologic Diseases and the Impact of Their Diagnostic Outputs on Physicians: Combined Retrospective and Prospective Study"],"prefix":"10.2196","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9511-9044","authenticated-orcid":false,"given":"Hongbin","family":"Yu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-9894-4398","authenticated-orcid":false,"given":"Tian","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7975-9965","authenticated-orcid":false,"given":"Xin","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2924-7002","authenticated-orcid":false,"given":"Yunfan","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9194-8320","authenticated-orcid":false,"given":"Qinyu","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3527-1874","authenticated-orcid":false,"given":"Chenlu","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7772-8011","authenticated-orcid":false,"given":"Kai","family":"Shen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9470-7167","authenticated-orcid":false,"given":"He","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5576-1788","authenticated-orcid":false,"given":"Wenjiao","family":"Tang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5194-1394","authenticated-orcid":false,"given":"Xushu","family":"Zhong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0896-2506","authenticated-orcid":false,"given":"Xiao","family":"Shuai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3044-4086","authenticated-orcid":false,"given":"Xinmei","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4665-4870","authenticated-orcid":false,"given":"Yi","family":"Liao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7087-6022","authenticated-orcid":false,"given":"Chiyi","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5226-3828","authenticated-orcid":false,"given":"Huanling","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8708-9711","authenticated-orcid":false,"given":"Yu","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1010","published-online":{"date-parts":[[2025,10,9]]},"reference":[{"issue":"9","key":"R1","doi-asserted-by":"publisher","first-page":"1116","DOI":"10.1038\/s41431-024-01604-z","article-title":"Time to diagnosis and determinants of diagnostic delays of people living with a rare disease: results of a rare barometer retrospective patient survey","volume":"32","author":"Faye","journal-title":"Eur J Hum Genet"},{"issue":"1","key":"R2","doi-asserted-by":"publisher","DOI":"10.1186\/s13073-022-01026-w","article-title":"A guide for the diagnosis of rare and undiagnosed disease: beyond the exome","volume":"14","author":"Marwaha","journal-title":"Genome Med"},{"key":"R3","doi-asserted-by":"publisher","DOI":"10.2196\/44420","article-title":"Patient journey toward a diagnosis of light chain amyloidosis in a national sample: cross-sectional web-based study","volume":"7","author":"Dou","journal-title":"JMIR Form Res"},{"issue":"6","key":"R4","doi-asserted-by":"publisher","first-page":"357","DOI":"10.1182\/bloodadvances.2016001784","article-title":"The clinical spectrum of Erdheim-Chester disease: an observational cohort study","volume":"1","author":"Estrada-Veras","journal-title":"Blood Adv"},{"issue":"1","key":"R5","doi-asserted-by":"publisher","DOI":"10.4084\/MJHID.2017.051","article-title":"POEMS syndrome: an update","volume":"9","author":"Nozza","journal-title":"Mediterr J Hematol Infect Dis"},{"issue":"9","key":"R6","doi-asserted-by":"publisher","first-page":"3687","DOI":"10.1111\/cas.15879","article-title":"Clinical and prognostic features of Langerhans cell histiocytosis in adults","volume":"114","author":"Sato","journal-title":"Cancer Sci"},{"issue":"1611785","key":"R7","doi-asserted-by":"publisher","DOI":"10.3389\/pore.2024.1611785","article-title":"Diagnostic challenges in patients with Castleman disease, a single center experience from Hungary","volume":"30","author":"Br\u00fag\u00f3s","journal-title":"Pathol Oncol Res"},{"key":"R8","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2024.102900","article-title":"Transformers and large language models in healthcare: a review","volume":"154","author":"Nerella","journal-title":"Artif Intell Med"},{"issue":"11","key":"R9","doi-asserted-by":"publisher","DOI":"10.3390\/jcm13113041","article-title":"Clinical and surgical applications of large language models: a systematic review","volume":"13","author":"Pressman","journal-title":"J Clin Med"},{"issue":"1","key":"R10","doi-asserted-by":"publisher","DOI":"10.1186\/s12911-024-02459-6","article-title":"Assessing the research landscape and clinical utility of large language models: a scoping review","volume":"24","author":"Park","journal-title":"BMC Med Inform Decis Mak"},{"key":"R11","unstructured":"Holohan M . A boy saw 17 doctors over 3 years for chronic pain. chatgpt found the diagnosis. Today. Sep 12, 2023. URL: https:\/\/www.today.com\/health\/mom-chatgpt-diagnosis-pain-rcna101843 [Accessed 15-07-2024]"},{"key":"R12","doi-asserted-by":"crossref","unstructured":"Mehnen L Gruarin S Vasileva M Knapp B . ChatGPT as a medical doctor? A diagnostic accuracy study on common and rare diseases. medRxiv. Preprint posted online on Apr 27, 2023. [doi: 10.1101\/2023.04.20.23288859]","DOI":"10.1101\/2023.04.20.23288859"},{"issue":"6","key":"R13","doi-asserted-by":"publisher","DOI":"10.3390\/diagnostics15060672","article-title":"Evaluating the use of generative artificial intelligence to support genetic counseling for rare diseases","volume":"15","author":"Jeon","journal-title":"Diagnostics (Basel)"},{"issue":"6","key":"R14","doi-asserted-by":"publisher","first-page":"3395","DOI":"10.1007\/s40123-023-00789-8","article-title":"What can GPT-4 do for diagnosing rare eye diseases? A pilot study","volume":"12","author":"Hu","journal-title":"Ophthalmol Ther"},{"key":"R15","doi-asserted-by":"publisher","DOI":"10.1016\/j.jns.2024.123360","article-title":"Faster and better than a physician?: assessing diagnostic proficiency of ChatGPT in misdiagnosed individuals with neuromyelitis optica spectrum disorder","volume":"468","author":"Shan","journal-title":"J Neurol Sci"},{"key":"R16","doi-asserted-by":"publisher","DOI":"10.2196\/69929","article-title":"Performance of ChatGPT-4o and four open-source large language models in generating diagnoses based on China\u2019s rare disease catalog: comparative study","volume":"27","author":"Zhong","journal-title":"J Med Internet Res"},{"key":"R17","unstructured":"Wei J Wang X Schuurmans D et al. Chain-of-thought prompting elicits reasoning in large language models. arXiv. Preprint posted online on Jan 28, 2022. [doi: 10.48550\/arXiv.2201.11903]"},{"key":"R18","unstructured":"DeepSeek-AIGuo D Yang D et al. DeepSeek-R1: incentivizing reasoning capability in LLMs via reinforcement learning. arXiv. Preprint posted online on Jan 22, 2025. [doi: 10.48550\/arXiv.2501.12948]"},{"key":"R19","unstructured":"OpenAI. Updated chain of thought in OpenAI o3-mini for free and paid users, and in o3-mini-high for paid users. X. 2025. URL: https:\/\/x.com\/openai\/status\/1887616278661112259 [Accessed 30-09-2025]"},{"key":"R20","doi-asserted-by":"crossref","unstructured":"Wu Z Hasan A Wu J et al. Chain-of-thought (CoT) prompting strategies for medical error detection and correction. arXiv. Preprint posted online on Jun 13, 2024. [doi: 10.48550\/arXiv.2406.09103]","DOI":"10.18653\/v1\/2024.clinicalnlp-1.33"},{"key":"R21","doi-asserted-by":"crossref","unstructured":"Chen J Gui C Gao A et al. CoD, towards an interpretable medical agent using chain of diagnosis. Presented at: Proceedings of the 2025 Conference on Association for Computational Linguistics (ACL \u201925); Jul 27 to Aug 1, 2025; Vienna, Austria. [doi: 10.18653\/v1\/2025.findings-acl.740]","DOI":"10.18653\/v1\/2025.findings-acl.740"},{"issue":"8","key":"R22","doi-asserted-by":"publisher","first-page":"2546","DOI":"10.1038\/s41591-025-03727-2","article-title":"Benchmark evaluation of DeepSeek large language models in clinical decision-making","volume":"31","author":"Sandmann","journal-title":"Nat Med"},{"issue":"9","key":"R23","doi-asserted-by":"publisher","first-page":"1884","DOI":"10.1093\/jamia\/ocae184","article-title":"The potential and pitfalls of using a large language model such as ChatGPT, GPT-4, or LLaMA as a clinical assistant","volume":"31","author":"Zhang","journal-title":"J Am Med Inform Assoc"},{"key":"R24","doi-asserted-by":"crossref","unstructured":"Chen X Mao X Guo Q Wang L Zhang S Chen T . RareBench: can LLMs serve as rare diseases specialists? Presented at: KDD \u201924: The 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining; Aug 25-29, 2024; Barcelona, Spain. [doi: 10.1145\/3637528.3671576]","DOI":"10.1145\/3637528.3671576"},{"key":"R25","doi-asserted-by":"publisher","DOI":"10.2196\/51391","article-title":"Learning to make rare and complex diagnoses with generative ai assistance: qualitative study of popular large language models","volume":"10","author":"Abdullahi","journal-title":"JMIR Med Educ"},{"key":"R26","doi-asserted-by":"publisher","DOI":"10.3389\/fmed.2024.1380148","article-title":"Evaluation of large language models as a diagnostic aid for complex medical cases","volume":"11","author":"R\u00edos-Hoyo","journal-title":"Front Med (Lausanne)"},{"key":"R27","doi-asserted-by":"publisher","DOI":"10.1136\/bmj.h5527","article-title":"STARD 2015: an updated list of essential items for reporting diagnostic accuracy studies","volume":"351","author":"Bossuyt","journal-title":"BMJ"},{"key":"R28","unstructured":"Notice on the publication of the first list of rare diseases [Article in Chinese]. The Government of the People\u2019s Republic of China. 2018. URL: https:\/\/www.gov.cn\/zhengce\/zhengceku\/2018-12\/31\/content_5435167.htm [Accessed 30-09-2025]"},{"key":"R29","unstructured":"Notice on the publication of the second list of rare diseases [Article in Chinese]. The Government of the People\u2019s Republic of China. 2023. URL: https:\/\/www.gov.cn\/zhengce\/zhengceku\/202309\/content_6905273.htm [Accessed 30-09-2025]"},{"key":"R30","unstructured":"Rare diseases at FDA. US Food & Drug Administration. 2024. URL: https:\/\/www.fda.gov\/patients\/rare-diseases-fda [Accessed 30-09-2025]"},{"key":"R31","unstructured":"Rare diseases. European Commission. URL: https:\/\/health.ec.europa.eu\/rare-diseases-and-european-reference-networks\/rare-diseases_en#latest-updates-and-documents [Accessed 30-09-2025]"},{"key":"R32","unstructured":"Notice of the Ministry of Science and Technology on soliciting public opinions on the \"Detailed rules for the implementation of the regulations on the administration of human genetic resources\" [Article in Chinese]. Ministry of Science and Technology of the People\u2019s Republic of China. 2022. URL: https:\/\/www.most.gov.cn\/tztg\/202203\/t20220322_179904.html [Accessed 06-10-2025]"},{"issue":"22","key":"R33","doi-asserted-by":"publisher","first-page":"1646","DOI":"10.3760\/cma.j.cn112137-20210302-00534","article-title":"Guidelines for the diagnosis and treatment of systemic light chain amyloidosis (2021 revision) [Article in Chinese]","volume":"101","author":"Chinese Collaborative Group for Systemic Light Chain Amyloidosis, National Clinical Research Center for Kidney Diseases, National Clinical Research Center for Hematologic Diseases","journal-title":"Zhonghua Yi Xue Za Zhi"},{"issue":"7","key":"R34","doi-asserted-by":"publisher","first-page":"529","DOI":"10.3760\/cma.j.issn.0253-2727.2021.07.001","article-title":"The consensus of the diagnosis and treatment of Castleman disease in China (2021) [Article in Chinese]","volume":"42","author":"Hematology Committee of Chinese Medical Association","journal-title":"Zhonghua Xue Ye Xue Za Zhi"},{"issue":"7","key":"R35","doi-asserted-by":"publisher","first-page":"812","DOI":"10.1002\/ajh.25495","article-title":"POEMS syndrome: 2019 update on diagnosis, risk-stratification, and management","volume":"94","author":"Dispenzieri","journal-title":"Am J Hematol"},{"issue":"8","key":"R36","doi-asserted-by":"publisher","first-page":"624","DOI":"10.3760\/cma.j.issn.0253-2727.2022.08.002","article-title":"Chinese guideline for diagnosis and treatment of lymphoplasmacytic lymphoma\/Walderstr\u00f6m macroglobulinemia (2022) [Article in Chinese]","volume":"43","author":"Hematology Oncology Committee of China Anti-Cancer Association","journal-title":"Zhonghua Xue Ye Xue Za Zhi"},{"issue":"10","key":"R37","doi-asserted-by":"publisher","first-page":"793","DOI":"10.3760\/cma.j.issn.0253-2727.2021.10.001","article-title":"Chinese guidelines on the diagnosis and treatment of acquired hemophilia A (2021) [Article in Chinese]","volume":"42","author":"Thrombosis and Hemostasis Group, Chinese Society of Hematology Chinese Medical Association","journal-title":"Zhonghua Xue Ye Xue Za Zhi"},{"issue":"17","key":"R38","doi-asserted-by":"publisher","first-page":"2601","DOI":"10.1182\/blood.2021014343","article-title":"International expert consensus recommendations for the diagnosis and treatment of Langerhans cell histiocytosis in adults","volume":"139","author":"Goyal","journal-title":"Blood"},{"issue":"6","key":"R39","doi-asserted-by":"publisher","DOI":"10.3760\/cma.j.cn115356-20240520-00067","article-title":"Chinese expert consensus on common primary cutaneous T-cell lymphoma (2024 version) [Article in Chinese]","volume":"33","author":"Lymphoma Expert Committee of Chinese Society of Clinical Oncology (CSCO)","journal-title":"J Leuk Lymphoma"},{"issue":"1","key":"R40","doi-asserted-by":"publisher","first-page":"7","DOI":"10.3760\/cma.j.issn.0253-2727.2022.01.002","article-title":"Chinese guideline on the diagnosis and management of thrombotic thrombocytopenic purpura (2022) [Article in Chinese]","volume":"43","author":"Thrombosis and Hemostasis Group, Chinese Society of Hematology, Chinese Medical Association","journal-title":"Zhonghua Xue Ye Xue Za Zhi"},{"key":"R41","unstructured":"Claude 35 Sonnet Model Card addendum. Anthropic. 2024. URL: https:\/\/www-cdn.anthropic.com\/fed9cc193a14b84131812372d8d5857f8f304c52\/Model_Card_Claude_3_Addendum.pdf [Accessed 30-09-2025]"},{"key":"R42","doi-asserted-by":"publisher","DOI":"10.1017\/S0016672315000166","article-title":"The long tail and rare disease research: the impact of next-generation sequencing for rare Mendelian disorders","volume":"97","author":"Shen","journal-title":"Genet Res"},{"key":"R43","unstructured":"Holtzman A Buys J Du L Forbes M Choi Y . The curious case of neural text degeneration. Presented at: 8th International Conference on Learning Representations (ICLR \u201920); Apr 26 to May 1, 2020:1-16; URL: https:\/\/openreview.net\/pdf?id=rygGQyrFvH [Accessed 06-10-2025]"},{"issue":"23","key":"R44","doi-asserted-by":"publisher","first-page":"2275","DOI":"10.1001\/jama.2023.22295","article-title":"Measuring the impact of ai in the diagnosis of hospitalized patients: a randomized clinical vignette survey study","volume":"330","author":"Jabbour","journal-title":"JAMA"},{"key":"R45","unstructured":"The 2022 comprehensive ranking of rare disease specialty departments [Article in Chinese]. CN-Healthcare China\u2019s Hospital Rankings. 2024. URL: https:\/\/rank.cn-healthcare.com\/fudan\/specialty-general\/year\/2022\/sid\/47 [Accessed 03-10-2025]"},{"key":"R46","doi-asserted-by":"publisher","DOI":"10.2196\/63733","article-title":"Designing clinical decision support systems (CDSS)-a user-centered lens of the design characteristics, challenges, and implications: systematic review","volume":"27","author":"Bayor","journal-title":"J Med Internet Res"},{"key":"R47","doi-asserted-by":"publisher","DOI":"10.1136\/bmj.m3216","article-title":"Computerised clinical decision support systems and absolute improvements in care: meta-analysis of controlled clinical trials","volume":"370","author":"Kwan","journal-title":"BMJ"},{"issue":"1","key":"R48","doi-asserted-by":"publisher","DOI":"10.1186\/s13023-020-01536-z","article-title":"Diagnosis of rare diseases: a scoping review of clinical decision support systems","volume":"15","author":"Schaaf","journal-title":"Orphanet J Rare Dis"},{"key":"R49","doi-asserted-by":"publisher","DOI":"10.1177\/20552076251339522","article-title":"Indecision on the use of artificial intelligence in healthcare-a qualitative study of patient perspectives on trust, responsibility and self-determination using AI-CDSS","volume":"11","author":"Schneider","journal-title":"Digit Health"},{"issue":"5","key":"R50","doi-asserted-by":"publisher","first-page":"101265","DOI":"10.1016\/j.aucc.2025.101265","article-title":"Beyond hype: Separating large language model-driven health literacy from clinical decision support system diagnostic rigour","volume":"38","author":"Yu","journal-title":"Aust Crit Care"},{"issue":"1","key":"R51","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-022-34025-x","article-title":"Uncertainty-informed deep learning models enable high-confidence predictions for digital histopathology","volume":"13","author":"Dolezal","journal-title":"Nat Commun"},{"key":"R52","unstructured":"Jabbour S Fouhey D Banovic N et al. On the limits of selective AI prediction: a case study in clinical decision making. arXiv. Preprint posted online on Aug 11, 2025. [doi: 10.48550\/arXiv.2508.07617]"},{"issue":"1","key":"R53","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1038\/s41746-020-00367-3","article-title":"Second opinion needed: communicating uncertainty in medical machine learning","volume":"4","author":"Kompa","journal-title":"NPJ Digit Med"},{"issue":"1","key":"R54","doi-asserted-by":"publisher","first-page":"159","DOI":"10.1038\/s41746-025-01550-0","article-title":"Enhancing diagnostic capability with multi-agents conversational large language models","volume":"8","author":"Chen","journal-title":"NPJ Digit Med"},{"issue":"11","key":"R55","doi-asserted-by":"publisher","DOI":"10.1056\/AIcs2400502","article-title":"Combining multiple large language models improves diagnostic accuracy","volume":"1","author":"Barabucci","journal-title":"NEJM AI"},{"key":"R56","unstructured":"Wang X Wei J Schuurmans D et al. Self-consistency improves chain of thought reasoning in language models. arXiv. Preprint posted online on Mar 21, 2022. [doi: 10.48550\/arXiv.2203.11171]"},{"issue":"24","key":"R57","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2426153122","article-title":"Human-AI collectives most accurately diagnose clinical vignettes","volume":"122","author":"Z\u00f6ller","journal-title":"Proc Natl Acad Sci U S A"}],"container-title":["Journal of Medical Internet Research"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.jmir.org\/2025\/1\/e77334","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T18:09:28Z","timestamp":1782842968000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.jmir.org\/2025\/1\/e77334"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,9]]},"references-count":57,"URL":"https:\/\/doi.org\/10.2196\/77334","relation":{},"ISSN":["1438-8871"],"issn-type":[{"value":"1438-8871","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,9]]},"article-number":"v27i9e77334"}}