{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,6]],"date-time":"2026-10-06T05:54:04Z","timestamp":1791266044366,"version":"4.1.0"},"reference-count":29,"publisher":"Wiley","issue":"5","license":[{"start":{"date-parts":[[2026,6,29]],"date-time":"2026-06-29T00:00:00Z","timestamp":1782691200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"},{"start":{"date-parts":[[2026,6,29]],"date-time":"2026-06-29T00:00:00Z","timestamp":1782691200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["82102029"],"award-info":[{"award-number":["82102029"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Health Care Science"],"published-print":{"date-parts":[[2026,10]]},"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>The capabilities of general\u2010purpose large language models (LLMs) on specialized medical examinations have not been systematically compared. To evaluate the performance differences among three LLMs\u2014DeepSeek\u2010R1, ChatGPT\u2010o1, and Gemini\u20102.0\u2014in answering questions from China's Standardized Training Examination for Resident Physicians in Radiology, and to assess the impact of different questioning conditions (with\/without answer choices, and the introduction of doubt) on model accuracy.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>A total of 131 questions were analyzed at one time. The LLMs were subjected to two tasks (questions with\/without answer choices). Each task included three conditions: no doubt, weak doubt, and strong doubt, with the latter two presented as follow\u2010up questions after the models' initial responses. Subjective evaluation was conducted using the 5\u2010point Likert scale.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      In both tasks, Gemini\u20102.0 achieved the highest accuracy (0.763\u20130.809) and (0.595\u20130.679). In Task 2, all LLMs' accuracy was lower than in Task 1, but only DeepSeek\u2010R1 showed statistical significance (\n                      <jats:italic>p<\/jats:italic>\n                      \u2009=\u20090.014). The introduction of doubt (weak or strong) did not significantly increase accuracy in Task 1 for any model. In Task 2, only DeepSeek\u2010R1 showed a slight increase in accuracy under doubt conditions. All LLMs performed significantly better on single\u2010choice questions than on multiple\u2010choice questions (\n                      <jats:italic>p<\/jats:italic>\n                      \u2009&lt;\u20090.05) and showed superior performance in case\u2010based questions vs. knowledge\u2010based questions. The subjective evaluation scores were 4.46 for DeepSeek\u2010R1, 3.92 for ChatGPT\u2010o1, and 3.83 for Gemini\u20102.0. It was noted that ChatGPT\u2010o1 negotiated not to answer all questions at once and had missing responses.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>LLMs exhibit variable proficiency in tackling radiology resident examination questions, with Gemini\u20102.0 showing the highest overall accuracy. However, repeated self\u2010examination of LLMs through the introduction of doubt does not consistently or significantly enhance their performance on radiology\u2010related questions.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1002\/hcs2.70085","type":"journal-article","created":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T02:11:17Z","timestamp":1782785477000},"page":"436-447","update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Artificial Intelligence Performance Under Different Conditions in Answering China's Standardized Training Examination for Resident Physician in Radiology: A Comparative Analysis"],"prefix":"10.1002","volume":"5","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4605-9783","authenticated-orcid":false,"given":"Zheng","family":"Zhu","sequence":"first","affiliation":[{"name":"Department of Diagnostic Radiology National Cancer Center\/National Clinical Research Center for Cancer\/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College Beijing China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6606-9535","authenticated-orcid":false,"given":"Yanfeng","family":"Zhao","sequence":"additional","affiliation":[{"name":"Department of Diagnostic Radiology National Cancer Center\/National Clinical Research Center for Cancer\/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College Beijing China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1586-2135","authenticated-orcid":false,"given":"Lin","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Diagnostic Radiology National Cancer Center\/National Clinical Research Center for Cancer\/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College Beijing China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoyi","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Diagnostic Radiology National Cancer Center\/National Clinical Research Center for Cancer\/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College Beijing China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yongming","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Education National Cancer Center\/National Clinical Research Center for Cancer\/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College Beijing China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinming","family":"Zhao","sequence":"additional","affiliation":[{"name":"Department of Diagnostic Radiology National Cancer Center\/National Clinical Research Center for Cancer\/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College Beijing China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2026,6,29]]},"reference":[{"key":"e_1_2_13_2_1","doi-asserted-by":"publisher","DOI":"10.34133\/research.0655"},{"key":"e_1_2_13_3_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-025-03727-2"},{"key":"e_1_2_13_4_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.diii.2023.02.003"},{"key":"e_1_2_13_5_1","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2024.21700"},{"key":"e_1_2_13_6_1","volume-title":"Selected Exercise Set for the Standardized Training Plan Textbook of Resident Physicians: Radiology Volume","author":"National Health Commission","year":"2019"},{"key":"e_1_2_13_7_1","doi-asserted-by":"publisher","DOI":"10.21037\/jtd-2025b-03"},{"key":"e_1_2_13_8_1","doi-asserted-by":"publisher","DOI":"10.1001\/jamainternmed.2024.0295"},{"key":"e_1_2_13_9_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-025-01536-y"},{"key":"e_1_2_13_10_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-025-03726-3"},{"key":"e_1_2_13_11_1","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.241668"},{"key":"e_1_2_13_12_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10916-025-02213-z"},{"key":"e_1_2_13_13_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pdig.0000198"},{"key":"e_1_2_13_14_1","doi-asserted-by":"publisher","DOI":"10.1002\/ca.24243"},{"key":"e_1_2_13_15_1","doi-asserted-by":"publisher","DOI":"10.2196\/63430"},{"key":"e_1_2_13_16_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jclinane.2025.111839"},{"key":"e_1_2_13_17_1","doi-asserted-by":"publisher","DOI":"10.2196\/45312"},{"key":"e_1_2_13_18_1","doi-asserted-by":"publisher","DOI":"10.2196\/65146"},{"key":"e_1_2_13_19_1","doi-asserted-by":"publisher","DOI":"10.2196\/54393"},{"key":"e_1_2_13_20_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00405-023-08051-4"},{"key":"e_1_2_13_21_1","doi-asserted-by":"publisher","DOI":"10.1186\/s12903-025-05926-2"},{"key":"e_1_2_13_22_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.amjmed.2023.06.012"},{"key":"e_1_2_13_23_1","doi-asserted-by":"publisher","DOI":"10.2196\/51319"},{"key":"e_1_2_13_24_1","doi-asserted-by":"publisher","DOI":"10.1186\/s12909-025-06916-2"},{"key":"e_1_2_13_25_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00276-025-03723-8"},{"key":"e_1_2_13_26_1","doi-asserted-by":"publisher","DOI":"10.1055\/s-0044-1792040"},{"key":"e_1_2_13_27_1","doi-asserted-by":"publisher","DOI":"10.1055\/s-0043-1777746"},{"key":"e_1_2_13_28_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jormas.2025.102644"},{"key":"e_1_2_13_29_1","doi-asserted-by":"publisher","DOI":"10.1055\/s-0044-1788605"},{"key":"e_1_2_13_30_1","doi-asserted-by":"publisher","DOI":"10.1186\/s12909-025-07875-4"}],"container-title":["Health Care Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/hcs2.70085","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/hcs2.70085","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/hcs2.70085","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,6]],"date-time":"2026-10-06T05:17:13Z","timestamp":1791263833000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1002\/hcs2.70085"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,29]]},"references-count":29,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2026,10]]}},"alternative-id":["10.1002\/hcs2.70085"],"URL":"https:\/\/doi.org\/10.1002\/hcs2.70085","archive":["Portico"],"relation":{},"ISSN":["2771-1749","2771-1757"],"issn-type":[{"value":"2771-1749","type":"print"},{"value":"2771-1757","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,29]]},"assertion":[{"value":"2025-12-30","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-02-08","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-06-29","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}