{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,27]],"date-time":"2026-09-27T14:57:33Z","timestamp":1790521053284,"version":"4.1.0"},"reference-count":28,"publisher":"SAGE Publications","license":[{"start":{"date-parts":[[2026,9,23]],"date-time":"2026-09-23T00:00:00Z","timestamp":1790121600000},"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":["Phlebology"],"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Lipedema is a frequently misdiagnosed chronic condition that significantly impacts patients\u2019 quality of life. As artificial intelligence (AI)-based large language models (LLMs) become increasingly integrated into healthcare communication, their accuracy and consistency in providing patient-centered information require thorough evaluation, especially in rare diseases like lipedema. Therefore, this study aimed to evaluate the accuracy and reproducibility of responses generated by ChatGPT, DeepSeek, and Gemini to questions frequently asked by patients with lipedema.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>This cross-sectional study assessed the accuracy and reproducibility of responses generated by ChatGPT, DeepSeek, and Gemini to 25 commonly asked lipedema-related questions. Each model was queried twice in separate sessions, and answers were evaluated by three independent experts using a four-point rating scale. To ensure the objectivity and consistency of expert evaluations, inter-rater agreement was assessed using Cohen\u2019s kappa coefficient.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>DeepSeek achieved the highest proportion of comprehensive and correct responses (72%), followed by Gemini (64%) and ChatGPT (56%). Accuracy varied across content categories, with notable limitations particularly in treatment, follow-up, and maintenance questions. Reproducibility analysis revealed that DeepSeek produced the most consistent responses across sessions, while ChatGPT and Gemini showed more variability, particularly in treatment and quality-of-life questions. Cohen\u2019s kappa values indicated high inter-rater agreement overall, with perfect agreement in some categories for ChatGPT and DeepSeek.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>LLMs can provide generally accurate and consistent responses to patient-centered questions about lipedema, particularly in areas related to general information and diagnosis. However, reduced accuracy and reproducibility in complex clinical domains suggest that expert oversight is essential when using these tools for patient education.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1177\/02683555261490374","type":"journal-article","created":{"date-parts":[[2026,9,23]],"date-time":"2026-09-23T16:40:59Z","timestamp":1790181659000},"update-policy":"https:\/\/doi.org\/10.1177\/sage-journals-update-policy","source":"Crossref","is-referenced-by-count":0,"title":["Evaluation of the accuracy and reproducibility of large language models (ChatGPT, DeepSeek, Gemini) in responding to patient-centered lipedema questions"],"prefix":"10.1177","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1739-4515","authenticated-orcid":false,"given":"Rabia","family":"San\u0131r","sequence":"first","affiliation":[{"name":"Hali\u00e7 University"},{"name":"Institute of Graduates Studies, Department of Physiotherapy and Rehabilitation, Istanbul University-Cerrahpasa, Istanbul, Turkey"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0597-9444","authenticated-orcid":false,"given":"Esra Nur","family":"T\u00fcrkmen","sequence":"additional","affiliation":[{"name":"Kahramanmara\u015f S\u00fct\u00e7\u00fc \u0130mam University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3895-4486","authenticated-orcid":false,"given":"Esra","family":"Giray","sequence":"additional","affiliation":[{"name":"University of Health Sciences"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6906-991X","authenticated-orcid":false,"given":"Figen","family":"Ayhan","sequence":"additional","affiliation":[{"name":"Atilim University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3724-571X","authenticated-orcid":false,"given":"G\u00fclseren","family":"Aky\u00fcz","sequence":"additional","affiliation":[{"name":"Lifemed Medical Center"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"179","published-online":{"date-parts":[[2026,9,23]]},"reference":[{"key":"e_1_3_7_2_2","doi-asserted-by":"publisher","DOI":"10.1111\/ddg.15513"},{"key":"e_1_3_7_3_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-025-68232-z"},{"key":"e_1_3_7_4_2","first-page":"20180309","article-title":"Lipedema: friend and foe","volume":"33","author":"Torre YS","year":"2018","unstructured":"Torre YS, Wadeea R, Rosas V, et al. Lipedema: friend and foe. Horm Mol Biol Clin Invest 2018; 33: 20180309. https:\/\/doi.org\/10.1515\/hmbci-2017-0076","journal-title":"Horm Mol Biol Clin Invest"},{"key":"e_1_3_7_5_2","first-page":"396","article-title":"Lipedema-pathogenesis, diagnosis, and treatment options","volume":"117","author":"Kruppa P","year":"2020","unstructured":"Kruppa P, Georgiou I, Biermann N, et al. Lipedema-pathogenesis, diagnosis, and treatment options. Dtsch Arztebl Int 2020; 117: 396\u2013403. https:\/\/doi.org\/10.3238\/arztebl.2020.0396","journal-title":"Dtsch Arztebl Int"},{"key":"e_1_3_7_6_2","doi-asserted-by":"publisher","DOI":"10.1111\/j.1365-2133.2009.09413.x"},{"key":"e_1_3_7_7_2","doi-asserted-by":"publisher","DOI":"10.1016\/S0025-6196(25)37697-4"},{"key":"e_1_3_7_8_2","doi-asserted-by":"publisher","DOI":"10.12968\/jowc.2020.29.Sup11b.1"},{"key":"e_1_3_7_9_2","doi-asserted-by":"publisher","DOI":"10.2147\/IJWH.S106227"},{"key":"e_1_3_7_10_2","first-page":"523","volume-title":"Annales de Dermatologie et de V\u00e9n\u00e9r\u00e9ologie","author":"Truchetet F","year":"2015","unstructured":"Truchetet F, Le lip\u0153d\u00e8me BA. Le reconna\u00eetre et que faire OMIM 614103. In: Annales de Dermatologie et de V\u00e9n\u00e9r\u00e9ologie. Elsevier, 2015, pp. 523\u2013529."},{"key":"e_1_3_7_11_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ygyno.2023.11.008"},{"key":"e_1_3_7_12_2","first-page":"20240520","article-title":"Integrating AI in lipedema management: assessing the efficacy of GPT-4 as a consultation assistant","volume":"14","author":"Leypold T","year":"2024","unstructured":"Leypold T, Lingens LF, Beier JP, et al. Integrating AI in lipedema management: assessing the efficacy of GPT-4 as a consultation assistant. Life (Basel) 2024; 14: 20240520. https:\/\/doi.org\/10.3390\/life14050646","journal-title":"Life (Basel)"},{"key":"e_1_3_7_13_2","unstructured":"GoogleTrends. Lip\u00f6dem (2025). https:\/\/trends.google.com\/trends\/explore?q=lipodemnedir&date=now1-d&geo=TR"},{"key":"e_1_3_7_14_2","unstructured":"Clinic C. Lipedema (2023). https:\/\/my.clevelandclinic.org\/health\/diseases\/17175-lipedema"},{"key":"e_1_3_7_15_2","unstructured":"Rockson DSG. Lipedema FAQs (2022). https:\/\/lymphaticnetwork.org\/images\/uploads\/LERN_Lipedema_FAQs.pdf"},{"key":"e_1_3_7_16_2","unstructured":"Editors TT. What is lipedema? Symptoms and treatment options (2023). https:\/\/turanturan.com.tr\/en\/lipedama\/lipedema-treatment\/#lipodem-hakkinda-sik-sorulan-sorular"},{"key":"e_1_3_7_17_2","unstructured":"Wright T. Understanding lipedema: comprehensive FAQ for diagnosis treatment and management (2025). https:\/\/lipedema.net\/frequently-asked-questions-about-lipedema\/"},{"key":"e_1_3_7_18_2","doi-asserted-by":"publisher","DOI":"10.5606\/tftrd.2025.15876"},{"key":"e_1_3_7_19_2","doi-asserted-by":"publisher","DOI":"10.1097\/RHU.0000000000001840"},{"issue":"20250618","key":"e_1_3_7_20_2","doi-asserted-by":"crossref","first-page":"e0326351","DOI":"10.1371\/journal.pone.0326351","article-title":"Evaluating the readability, quality, and reliability of responses generated by ChatGPT, gemini, and perplexity on the most commonly asked questions about ankylosing spondylitis","volume":"20","author":"Kara M","year":"2025","unstructured":"Kara M, Ozduran E, Kara MM, et al. Evaluating the readability, quality, and reliability of responses generated by ChatGPT, gemini, and perplexity on the most commonly asked questions about ankylosing spondylitis. PLoS One 2025; 20(20250618): e0326351. https:\/\/doi.org\/10.1371\/journal.pone.0326351","journal-title":"PLoS One"},{"key":"e_1_3_7_21_2","first-page":"294","article-title":"Emergency medicine assistants in the field of toxicology, comparison of ChatGPT-3.5 and GEMINI artificial intelligence systems","volume":"31","author":"Bedel HA","year":"2024","unstructured":"Bedel HA, Bedel C, Selvi F, et al. Emergency medicine assistants in the field of toxicology, comparison of ChatGPT-3.5 and GEMINI artificial intelligence systems. Acta Med Litu 2024; 31: 294\u2013301. https:\/\/doi.org\/10.15388\/Amed.2024.31.2.18","journal-title":"Acta Med Litu"},{"key":"e_1_3_7_22_2","first-page":"20240301","article-title":"Accuracy of treatment recommendations by pragmatic evidence search and artificial intelligence: an exploratory study","volume":"14","author":"Baig Z","year":"2024","unstructured":"Baig Z, Lawrence D, Ganhewa M, et al. Accuracy of treatment recommendations by pragmatic evidence search and artificial intelligence: an exploratory study. Diagnostics (Basel) 2024; 14: 20240301. https:\/\/doi.org\/10.3390\/diagnostics14050527","journal-title":"Diagnostics (Basel)"},{"key":"e_1_3_7_23_2","doi-asserted-by":"publisher","DOI":"10.36740\/WLek\/195125"},{"key":"e_1_3_7_24_2","first-page":"20250228","article-title":"Management of dupuytren's disease: a multi-centric comparative analysis between experienced hand surgeons versus artificial intelligence","volume":"15","author":"Seth I","year":"2025","unstructured":"Seth I, Marcaccini G, Lim K, et al. Management of dupuytren's disease: a multi-centric comparative analysis between experienced hand surgeons versus artificial intelligence. Diagnostics (Basel) 2025; 15: 20250228. https:\/\/doi.org\/10.3390\/diagnostics15050587","journal-title":"Diagnostics (Basel)"},{"key":"e_1_3_7_25_2","doi-asserted-by":"publisher","DOI":"10.1186\/s13049-024-01266-2"},{"key":"e_1_3_7_26_2","doi-asserted-by":"publisher","DOI":"10.2196\/47479"},{"key":"e_1_3_7_27_2","doi-asserted-by":"publisher","DOI":"10.1111\/ddg.13036"},{"key":"e_1_3_7_28_2","doi-asserted-by":"publisher","DOI":"10.1164\/rccm.201908-1581ST"},{"key":"e_1_3_7_29_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmi.2025.03.002"}],"container-title":["Phlebology: The Journal of Venous Disease"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/02683555261490374","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/full-xml\/10.1177\/02683555261490374","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/02683555261490374","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,27]],"date-time":"2026-09-27T14:26:00Z","timestamp":1790519160000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/10.1177\/02683555261490374"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,23]]},"references-count":28,"alternative-id":["10.1177\/02683555261490374"],"URL":"https:\/\/doi.org\/10.1177\/02683555261490374","relation":{},"ISSN":["0268-3555","1758-1125"],"issn-type":[{"value":"0268-3555","type":"print"},{"value":"1758-1125","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,23]]},"article-number":"02683555261490374"}}