{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T16:15:24Z","timestamp":1783786524279,"version":"3.55.0"},"reference-count":36,"publisher":"SAGE Publications","license":[{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/journals.sagepub.com\/page\/policies\/text-and-data-mining-license"}],"content-domain":{"domain":["journals.sagepub.com"],"crossmark-restriction":true},"short-container-title":["DIGITAL HEALTH"],"published-print":{"date-parts":[[2026,2]]},"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>This study evaluated the performance of five Large Language Models based on actual cases to provide guidance for selecting appropriate models for clinical decision-making.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>This study aimed to assess the performance of large language models (LLMs) in clinical decision-making for internal medicine and to provide evidence-based guidance for model selection in clinical practice.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We conducted a retrospective cross-sectional study with 405 cases across nine subspecialties: cardiovascular, respiratory, gastroenterology, nephrology, rheumatology, endocrinology, neurology, hematology, and infectious diseases. Two senior clinicians evaluated outputs on five dimensions: diagnosis, diagnostic criteria, differential diagnosis, examinations, and treatment. Statistical analyses were performed via the Kruskal\u2012Wallis tests and Pairwise comparisons were performed by Dunn's test with p-value adjusted by BH procedure.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      Overall, significant performance differences were observed among models (\n                      <jats:italic toggle=\"yes\">p<\/jats:italic>\n                      \u2009=\u20090.001). All models performed worst in respiratory (\n                      <jats:italic toggle=\"yes\">p<\/jats:italic>\n                      \u2009&lt;\u20090.05). Gemini significantly outperformed others in differential diagnosis\u2014the weakest area across all models (\n                      <jats:italic toggle=\"yes\">p<\/jats:italic>\n                      \u2009&lt;\u20090.05). Claude scored significantly lower than other LLMs in Card and Heme (\n                      <jats:italic toggle=\"yes\">p<\/jats:italic>\n                      \u2009&lt;\u20090.05). Subgroup analysis indicated that the most pronounced performance disparities were observed in the Card (\n                      <jats:italic toggle=\"yes\">p<\/jats:italic>\n                      \u2009&lt;\u20090.05).\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>GPT, O1, and Gemini demonstrated superior performance in clinical decision-making for internal medicine among all LLMs, whereas Claude showed the poorest performance. All LLMs demonstrated deficiencies in differential diagnosis and poor management for respiratory diseases. The complexity of subspecialty might be a performance differentiator for LLMs and O1 might have potential suitability for complex subspecialties like cardiology.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1177\/20552076261433073","type":"journal-article","created":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T08:01:52Z","timestamp":1774425712000},"update-policy":"https:\/\/doi.org\/10.1177\/sage-journals-update-policy","source":"Crossref","is-referenced-by-count":1,"title":["Performances of five large language models in clinical decision-making for internal medicine: A comparative study"],"prefix":"10.1177","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7350-4424","authenticated-orcid":false,"given":"Dan","family":"Wu","sequence":"first","affiliation":[{"name":"The Affiliated Guangdong Second Provincial General Hospital of Jinan University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9881-6873","authenticated-orcid":false,"given":"Jingjing","family":"Lu","sequence":"additional","affiliation":[{"name":"The First Affiliated Hospital of Guangzhou University of Chinese Medicine"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9491-5815","authenticated-orcid":false,"given":"Danghan","family":"Xu","sequence":"additional","affiliation":[{"name":"Guangzhou Yuansheng Ruihang Medical Information Technology Co., Guangzhou, Guangdong, China"},{"name":"Huazhou Community Health Service Center of Haizhu District of Guangzhou, Guangzhou, Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"179","published-online":{"date-parts":[[2026,3,25]]},"reference":[{"key":"e_1_3_4_2_2","doi-asserted-by":"publisher","DOI":"10.3389\/fpubh.2025.1527424"},{"key":"e_1_3_4_3_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.xcrm.2024.101547"},{"key":"e_1_3_4_4_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2022.106854"},{"key":"e_1_3_4_5_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.tcm.2020.11.007"},{"key":"e_1_3_4_6_2","doi-asserted-by":"publisher","DOI":"10.7150\/ijms.77205"},{"key":"e_1_3_4_7_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.lanepe.2024.101064"},{"key":"e_1_3_4_8_2","doi-asserted-by":"publisher","DOI":"10.1055\/a-2031-0691"},{"key":"e_1_3_4_9_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.gie.2020.04.044"},{"key":"e_1_3_4_10_2","doi-asserted-by":"publisher","DOI":"10.1093\/eurheartj\/ehaa159"},{"key":"e_1_3_4_11_2","doi-asserted-by":"publisher","DOI":"10.2459\/JCM.0000000000001664"},{"key":"e_1_3_4_12_2","doi-asserted-by":"publisher","DOI":"10.3390\/jpm15050205"},{"key":"e_1_3_4_13_2","article-title":"ChatGPT-4 and the global burden of disease study: advancing personalized healthcare through artificial intelligence in clinical and translational medicine","volume":"15","author":"Temsah MH","year":"2023","unstructured":"Temsah MH, et al. ChatGPT-4 and the global burden of disease study: advancing personalized healthcare through artificial intelligence in clinical and translational medicine. Cureus 2023; 15: e39384.","journal-title":"Cureus"},{"key":"e_1_3_4_14_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10916-025-02181-4"},{"key":"e_1_3_4_15_2","first-page":"70","article-title":"Comparative analysis of the performance of the large language models ChatGPT-3.5, ChatGPT-4 and open AI-o1 in the field of programmed cell death in myeloma","volume":"16","author":"Kun W","year":"2025","unstructured":"Kun W, et al. Comparative analysis of the performance of the large language models ChatGPT-3.5, ChatGPT-4 and open AI-o1 in the field of programmed cell death in myeloma. Discov Oncol 2025; 16: 70.","journal-title":"Discov Oncol"},{"key":"e_1_3_4_16_2","article-title":"Deepseek in healthcare: revealing opportunities and steering challenges of a new open-source artificial intelligence frontier","volume":"17","author":"Temsah A","year":"2025","unstructured":"Temsah A, et al. Deepseek in healthcare: revealing opportunities and steering challenges of a new open-source artificial intelligence frontier. Cureus 2025; 17: e79221.","journal-title":"Cureus"},{"key":"e_1_3_4_17_2","doi-asserted-by":"publisher","DOI":"10.3390\/curroncol31040137"},{"key":"e_1_3_4_18_2","doi-asserted-by":"publisher","DOI":"10.5530\/jscires.20041161"},{"key":"e_1_3_4_19_2","doi-asserted-by":"publisher","DOI":"10.1111\/bioe.13222"},{"key":"e_1_3_4_20_2","doi-asserted-by":"publisher","DOI":"10.3390\/ejihpe14030045"},{"key":"e_1_3_4_21_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10916-024-02098-4"},{"key":"e_1_3_4_22_2","doi-asserted-by":"publisher","DOI":"10.1038\/s43856-024-00717-2"},{"key":"e_1_3_4_23_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.iswa.2024.200441"},{"key":"e_1_3_4_24_2","first-page":"415","article-title":"Integrated innovation between technology and organization","volume":"4","author":"Guan JLJ","year":"2007","unstructured":"Guan JLJ. Integrated innovation between technology and organization. Int J Innov Technol Manag 2007; 4: 415\u2013432.","journal-title":"Int J Innov Technol Manag"},{"key":"e_1_3_4_25_2","volume-title":"Internal Medicine","author":"Shu Z","year":"2016","unstructured":"Shu Z. Internal Medicine. Beijing: The People's Health Press, 2016."},{"key":"e_1_3_4_26_2","article-title":"Assessing the potential of GPT-4 to perpetuate racial and gender biases in health care: a model evaluation study","volume":"6","author":"Zack T","year":"2024","unstructured":"Zack T, et al. Assessing the potential of GPT-4 to perpetuate racial and gender biases in health care: a model evaluation study. Lan Digit Health 2024; 6: e12\u2013e22.","journal-title":"Lan Digit Health"},{"key":"e_1_3_4_27_2","doi-asserted-by":"publisher","DOI":"10.1001\/jamasurg.2019.4917"},{"key":"e_1_3_4_28_2","doi-asserted-by":"publisher","DOI":"10.1186\/s12912-025-03348-7"},{"key":"e_1_3_4_29_2","first-page":"19","article-title":"A comprehensive review on synergy of multi-modal data and AI technologies in medical diagnosis","volume":"11","author":"Xu X","year":"2024","unstructured":"Xu X, et al. A comprehensive review on synergy of multi-modal data and AI technologies in medical diagnosis. Bioeng (Basel) 2024; 11: 19.","journal-title":"Bioeng (Basel)"},{"key":"e_1_3_4_30_2","doi-asserted-by":"publisher","DOI":"10.2196\/59505"},{"key":"e_1_3_4_31_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.socscimed.2020.113172"},{"key":"e_1_3_4_32_2","doi-asserted-by":"publisher","DOI":"10.4103\/njcp.njcp_552_22"},{"key":"e_1_3_4_33_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41569-020-00445-9"},{"key":"e_1_3_4_34_2","doi-asserted-by":"crossref","unstructured":"Awotunde JB et al. Privacy and security concerns in IoT-based healthcare systems. In: The Fusion of Internet of Things Artificial Intelligence and Cloud Computing in Health Care. 2021. p. 105-134.","DOI":"10.1007\/978-3-030-75220-0_6"},{"key":"e_1_3_4_35_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-020-00323-1"},{"key":"e_1_3_4_36_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.csm.2024.08.005"},{"key":"e_1_3_4_37_2","doi-asserted-by":"publisher","DOI":"10.1044\/2025_AJSLP-24-00225"}],"container-title":["DIGITAL HEALTH"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/20552076261433073","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/full-xml\/10.1177\/20552076261433073","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/20552076261433073","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,28]],"date-time":"2026-04-28T17:56:23Z","timestamp":1777398983000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/10.1177\/20552076261433073"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2]]},"references-count":36,"alternative-id":["10.1177\/20552076261433073"],"URL":"https:\/\/doi.org\/10.1177\/20552076261433073","relation":{},"ISSN":["2055-2076","2055-2076"],"issn-type":[{"value":"2055-2076","type":"print"},{"value":"2055-2076","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2]]},"article-number":"20552076261433073"}}