{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T16:03:24Z","timestamp":1781885004346,"version":"3.54.5"},"reference-count":36,"publisher":"SAGE Publications","issue":"11","license":[{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"},{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/journals.sagepub.com\/page\/policies\/text-and-data-mining-license"}],"funder":[{"name":"Hallym University Research Fund 2024","award":["HURF-2024-46"],"award-info":[{"award-number":["HURF-2024-46"]}]}],"content-domain":{"domain":["journals.sagepub.com"],"crossmark-restriction":true},"short-container-title":["Orthopaedic Journal of Sports Medicine"],"published-print":{"date-parts":[[2025,11]]},"abstract":"<jats:sec>\n                    <jats:title>Background:<\/jats:title>\n                    <jats:p>Large language model (LLM)\u2013based chatbots, such as ChatGPT and Gemini, have become widely used sources of medical information. No study has assessed the performance of LLM chatbots in providing clinically reliable information on high tibial osteotomy (HTO).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Purpose:<\/jats:title>\n                    <jats:p>To evaluate the accuracy and relevance of different LLM chatbots in responding to frequently asked questions (FAQs) about HTO.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Study Design:<\/jats:title>\n                    <jats:p>Cross-sectional study.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods:<\/jats:title>\n                    <jats:p>A total of 35 FAQs about HTO were curated from online sources and categorized into 6 categories: general\/procedure related, indications for surgery and outcomes, risks and complications of surgery, pain and postoperative recovery, specific activities after surgery, and alternatives to and variations of HTO. These questions were used as input to 5 different LLM chatbots: ChatGPT-3.5, ChatGPT-4, ChatGPT\u20134 Omni, Gemini Advanced and Gemini 1.5. Responses were collected from July 12 to 14, 2024 (ChatGPT-3.5, ChatGPT-4, ChatGPT\u20134 Omni, and Gemini Advanced) and on September 26, 2024 (Gemini 1.5). Two independent orthopaedic surgeons assessed the responses using a 5-point Likert scale (1 = very incorrect\/very irrelevant, 5 = very accurate\/very relevant). Responses were anonymized to blind evaluators to chatbot identities. Differences in accuracy among chatbots were assessed using analysis of variance, and differences in relevance using the Kruskal-Wallis test.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results:<\/jats:title>\n                    <jats:p>\n                      LLM chatbots demonstrated the following mean accuracy scores: GPT-3.5 (4.66 \u00b1 0.64), GPT-4 (4.66 \u00b1 0.54), GPT\u20134 Omni (4.94 \u00b1 0.24), and Gemini 1.5 (4.86 \u00b1 0.36), while Gemini Advanced showed significantly lower scores (3.83 \u00b1 1.40) (\n                      <jats:italic toggle=\"yes\">P<\/jats:italic>\n                      &lt; .001) in answering HTO-related FAQs. Particularly, Gemini Advanced exhibited lower accuracy scores in the categories of indications and outcomes (\n                      <jats:italic toggle=\"yes\">P<\/jats:italic>\n                      = .002) and alternatives and variations (\n                      <jats:italic toggle=\"yes\">P<\/jats:italic>\n                      = .015). There were no significant differences among the models regarding general\/procedure related (\n                      <jats:italic toggle=\"yes\">P<\/jats:italic>\n                      = .12), risks and complications (\n                      <jats:italic toggle=\"yes\">P<\/jats:italic>\n                      = .50), pain and postoperative recovery (\n                      <jats:italic toggle=\"yes\">P<\/jats:italic>\n                      = .53), and specific activities after surgery (\n                      <jats:italic toggle=\"yes\">P<\/jats:italic>\n                      = .09). All models provided relevant answers to all questions (35\/35; 100%), except for Gemini Advanced (30\/35; 85.7%).\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion:<\/jats:title>\n                    <jats:p>This study showed that ChatGPT-3.5, ChatGPT-4, ChatGPT\u20134 Omni, and Gemini 1.5 provided accurate and relevant responses on HTO, whereas Gemini Advanced exhibited limitations and underperformed in comparison with the other models.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1177\/23259671251385127","type":"journal-article","created":{"date-parts":[[2025,11,19]],"date-time":"2025-11-19T19:08:06Z","timestamp":1763579286000},"update-policy":"https:\/\/doi.org\/10.1177\/sage-journals-update-policy","source":"Crossref","is-referenced-by-count":3,"title":["A Comparative Analysis of GPT-3.5, GPT-4, GPT\u20134 Omni, Gemini Advanced, and Gemini 1.5 in Answering Frequently Asked Questions Regarding High Tibial Osteotomy"],"prefix":"10.1177","volume":"13","author":[{"given":"Seong Hyeon","family":"Kim","sequence":"first","affiliation":[{"name":"Department of Orthopaedic Surgery, Dongtan Sacred Heart Hospital, Hallym University College of Medicine, Hwaseong, Gyeonggi-do, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ji-Sun","family":"Shin","sequence":"additional","affiliation":[{"name":"Department of Orthopaedic Surgery, Dongtan Sacred Heart Hospital, Hallym University College of Medicine, Hwaseong, Gyeonggi-do, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hyobeom","family":"Lee","sequence":"additional","affiliation":[{"name":"Department of Orthopaedic Surgery, Center for Joint Diseases, Kyung Hee University Hospital at Gangdong, Gangdong-gu, Seoul, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Seung Yong","family":"Shin","sequence":"additional","affiliation":[{"name":"Department of Orthopaedic Surgery, Dongtan Sacred Heart Hospital, Hallym University College of Medicine, Hwaseong, Gyeonggi-do, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ki Man","family":"Kang","sequence":"additional","affiliation":[{"name":"Hdream Orthopedic Clinic, Hwaseong, Gyeonggi-do, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Si Young","family":"Song","sequence":"additional","affiliation":[{"name":"Department of Orthopaedic Surgery, Dongtan Sacred Heart Hospital, Hallym University College of Medicine, Hwaseong, Gyeonggi-do, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"179","published-online":{"date-parts":[[2025,11,19]]},"reference":[{"key":"e_1_3_3_2_2","doi-asserted-by":"publisher","DOI":"10.59400\/cai.v2i1.1378"},{"issue":"4","key":"e_1_3_3_3_2","article-title":"Redefining healthcare with artificial intelligence (AI): the contributions of ChatGPT, Gemini, and Co-pilot","volume":"16","author":"Alhur A.","year":"2024","unstructured":"Alhur A. Redefining healthcare with artificial intelligence (AI): the contributions of ChatGPT, Gemini, and Co-pilot. Cureus. 2024;16(4):e57795.","journal-title":"Cureus"},{"issue":"2","key":"e_1_3_3_4_2","article-title":"Artificial hallucinations in ChatGPT: implications in scientific writing","volume":"15","author":"Alkaissi H","year":"2023","unstructured":"Alkaissi H, McFarlane SI. Artificial hallucinations in ChatGPT: implications in scientific writing. Cureus. 2023;15(2):e35179.","journal-title":"Cureus"},{"key":"e_1_3_3_5_2","doi-asserted-by":"publisher","DOI":"10.1016\/S0140-6736(23)00216-7"},{"key":"e_1_3_3_6_2","doi-asserted-by":"publisher","DOI":"10.1177\/10225536251350411"},{"key":"e_1_3_3_7_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.arth.2024.03.017"},{"key":"e_1_3_3_8_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10439-023-03172-7"},{"key":"e_1_3_3_9_2","doi-asserted-by":"publisher","DOI":"10.1186\/s40634-023-00700-1"},{"key":"e_1_3_3_10_2","unstructured":"Claburn T. OpenAI Says Natively Multimodal GPT-4o Eats Text Visuals Sound\u2014and Emits the Same: the o Is Not Short for \u201cOh Sh\u2026\u201d for Google and Co. Updated May 13 2024. Accessed July 4 2025. https:\/\/www.theregister.com\/2024\/05\/13\/openai_gpt4o\/"},{"key":"e_1_3_3_11_2","unstructured":"Clark M Bailey S. Chatbots in Health Care: Connecting Patients to Information: Emerging Health Technologies. Canadian Agency for Drugs and Technologies in Health; 2024. Accessed March 20 2025 CADTH Horizon Scans report No. EH0122. https:\/\/www.ncbi.nlm.nih.gov\/books\/NBK602381\/"},{"key":"e_1_3_3_12_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.apergo.2024.104367"},{"key":"e_1_3_3_13_2","unstructured":"Gemini Team Google: Georgiev P Lei VI Burnell R et al. Gemini 1.5: Unlocking Multimodal Understanding Across Millions of Tokens of Context. ArXiv. Revised December 16 2024. Accessed July 4 2025 https:\/\/arxiv.org\/abs\/2403.05530"},{"key":"e_1_3_3_14_2","unstructured":"Goldman S. ChatGPT Launched Six Months Ago. Its Impact\u2014and Fallout Is Just Beginning. VentureBeat. Updated May 30 2023. Accessed July 4 2025. https:\/\/venturebeat.com\/ai\/chatgpt-launched-six-months-ago-its-impact-and-fallout-is-just-beginning-the-ai-beat\/"},{"key":"e_1_3_3_15_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-024-66708-4"},{"key":"e_1_3_3_16_2","doi-asserted-by":"publisher","DOI":"10.21203\/rs.3.rs-2566942\/v1"},{"key":"e_1_3_3_17_2","doi-asserted-by":"publisher","DOI":"10.1007\/s00167-023-07529-2"},{"key":"e_1_3_3_18_2","doi-asserted-by":"publisher","DOI":"10.1186\/s43019-023-00200-7"},{"key":"e_1_3_3_19_2","doi-asserted-by":"publisher","DOI":"10.1007\/s00167-021-06506-x"},{"key":"e_1_3_3_20_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jseint.2024.11.012"},{"key":"e_1_3_3_21_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.arthro.2023.10.044"},{"issue":"5","key":"e_1_3_3_22_2","article-title":"Unlocking health literacy: the ultimate guide to hypertension education from ChatGPT versus Google Gemini","volume":"16","author":"Lee TJ","year":"2024","unstructured":"Lee TJ, Campbell DJ, Patel S, et al. Unlocking health literacy: the ultimate guide to hypertension education from ChatGPT versus Google Gemini. Cureus. 2024;16(5):e59898.","journal-title":"Cureus"},{"key":"e_1_3_3_23_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ajem.2024.05.001"},{"key":"e_1_3_3_24_2","doi-asserted-by":"publisher","DOI":"10.2106\/JBJS.23.00209"},{"issue":"6","key":"e_1_3_3_25_2","article-title":"Artificial intelligence in ophthalmology: a comparative analysis of GPT-3.5, GPT-4, and human expertise in answering StatPearls questions","volume":"15","author":"Moshirfar M","year":"2023","unstructured":"Moshirfar M, Altaf AW, Stoakes IM, Tuttle JJ, Hoopes PC. Artificial intelligence in ophthalmology: a comparative analysis of GPT-3.5, GPT-4, and human expertise in answering StatPearls questions. Cureus. 2023;15(6):e40822.","journal-title":"Cureus"},{"key":"e_1_3_3_26_2","doi-asserted-by":"publisher","DOI":"10.1007\/s00167-023-07372-5"},{"key":"e_1_3_3_27_2","doi-asserted-by":"publisher","DOI":"10.1186\/s43019-024-00214-9"},{"key":"e_1_3_3_28_2","unstructured":"Reusens M Borchert P De Weerdt J Baesens B. Native Design Bias: Studying the Impact of English Nativeness on Language Model Performance. arXiv. Revised October 7 2024. Accessed March 20 2025 https:\/\/arxiv.org\/abs\/2406.17385"},{"key":"e_1_3_3_29_2","doi-asserted-by":"publisher","DOI":"10.1186\/s12909-024-05630-9"},{"key":"e_1_3_3_30_2","doi-asserted-by":"publisher","DOI":"10.1186\/s13054-023-04380-2"},{"key":"e_1_3_3_31_2","unstructured":"Shah P. Rank for People Also Ask: Ultimate Infinite Questions Google PAA Handbook. Outranking. Accessed July 4 2025. https:\/\/www.outranking.io\/people-also-ask-handbook\/"},{"key":"e_1_3_3_32_2","doi-asserted-by":"publisher","DOI":"10.4300\/JGME-5-4-18"},{"key":"e_1_3_3_33_2","doi-asserted-by":"publisher","DOI":"10.1186\/s12903-025-05554-w"},{"key":"e_1_3_3_34_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.arth.2024.02.005"},{"key":"e_1_3_3_35_2","doi-asserted-by":"publisher","DOI":"10.1007\/s00264-024-06182-9"},{"key":"e_1_3_3_36_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.urology.2023.07.010"},{"key":"e_1_3_3_37_2","doi-asserted-by":"publisher","DOI":"10.1186\/s43019-024-00218-5"}],"container-title":["Orthopaedic Journal of Sports Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/23259671251385127","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/full-xml\/10.1177\/23259671251385127","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/23259671251385127","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:30:14Z","timestamp":1777595414000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/10.1177\/23259671251385127"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11]]},"references-count":36,"journal-issue":{"issue":"11","published-print":{"date-parts":[[2025,11]]}},"alternative-id":["10.1177\/23259671251385127"],"URL":"https:\/\/doi.org\/10.1177\/23259671251385127","relation":{},"ISSN":["2325-9671","2325-9671"],"issn-type":[{"value":"2325-9671","type":"print"},{"value":"2325-9671","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11]]},"article-number":"23259671251385127"}}