{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,5]],"date-time":"2026-10-05T08:54:25Z","timestamp":1791190465449,"version":"4.1.0"},"reference-count":21,"publisher":"Wiley","license":[{"start":{"date-parts":[[2026,10,5]],"date-time":"2026-10-05T00:00:00Z","timestamp":1791158400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"},{"start":{"date-parts":[[2026,10,5]],"date-time":"2026-10-05T00:00:00Z","timestamp":1791158400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Neurourology and Urodynamics"],"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Objectives<\/jats:title>\n                    <jats:p>Interpretation of urodynamic studies is complex and subject to substantial inter\u2010observer variability, even among experienced clinicians. While artificial intelligence has shown promise in urology, evidence regarding the performance of large language models (LLMs) in urodynamic trace interpretation remains limited. This study aimed to systematically compare the performance of multiple contemporary LLMs in interpreting standard urodynamic traces using an adapted ELEGANCE framework.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>In this retrospective, single\u2010centre comparative study, 119 anonymised urodynamic machine printouts retrieved from the institutional patient archive were independently interpreted by five LLM\u2010based platforms (ChatGPT\u20105.2, Gemini 3, Perplexity AI Pro, DeepSeek\u2010V3.2, and Grok 4.1). Case\u2010specific expert reference interpretations were produced by one of three urologists, whereas all LLM\u2010generated interpretations were independently evaluated by all three urologists. LLM\u2010generated interpretations were assessed using an adapted version of the \u201cExpert\u2010Led Evaluation of Generative AI Competence and Excellence\u201d (ELEGANCE) questionnaire, which evaluates relevance, completeness, applicability, structure, language\/terminology, satisfaction, and hallucination. Between\u2010model comparisons were performed using Friedman and post\u2010hoc Wilcoxon signed\u2010rank tests.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      Overall ELEGANCE scores differed significantly among models (\u03c7\n                      <jats:sup>2<\/jats:sup>\n                      [4]\u2009=\u200912.67,\n                      <jats:italic>p<\/jats:italic>\n                      \u2009=\u20090.013). Gemini achieved the highest mean score (25.77\u2009\u00b1\u20093.74), followed by Perplexity, DeepSeek, and ChatGPT\u20105.2, while Grok demonstrated significantly lower performance. Gemini consistently outperformed other models in clinically oriented domains, including relevance, completeness, and applicability (all\n                      <jats:italic>p<\/jats:italic>\n                      \u2009&lt;\u20090.05). No hallucinations were identified in any model output. Inter\u2010rater reliability among the three expert reviewers was good (average\u2010measures ICC\u2009=\u20090.898, 95% CI 0.853\u20130.929;\n                      <jats:italic>p<\/jats:italic>\n                      \u2009&lt;\u20090.001).\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>Contemporary LLMs can generate structured interpretations of urodynamic traces, with meaningful performance differences across the evaluated platforms. While strengths in structure and terminology are evident, limitations in clinical reasoning persist. LLMs may serve as valuable assistive tools for standardisation and quality assurance in urodynamics but are not yet suitable for autonomous clinical decision\u2010making.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1002\/nau.70470","type":"journal-article","created":{"date-parts":[[2026,10,5]],"date-time":"2026-10-05T08:21:54Z","timestamp":1791188514000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Comparative Performance of Large Language Models in Urodynamic Trace Interpretation Using an Adapted Expert\u2010Led Evaluation of Generative AI Competence and Excellence Framework"],"prefix":"10.1002","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3492-8467","authenticated-orcid":false,"given":"Oguzhan","family":"Akpinar","sequence":"first","affiliation":[{"name":"Department of Urology, Bursa Yuksek Ihtisas Training and Research Hospital University of Health Sciences Bursa Turkiye"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3130-9046","authenticated-orcid":false,"given":"Anil","family":"Erkan","sequence":"additional","affiliation":[{"name":"Department of Urology, Bursa Yuksek Ihtisas Training and Research Hospital University of Health Sciences Bursa Turkiye"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1589-322X","authenticated-orcid":false,"given":"Alper","family":"Keskin","sequence":"additional","affiliation":[{"name":"Department of Urology, Bursa Yuksek Ihtisas Training and Research Hospital University of Health Sciences Bursa Turkiye"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7249-4332","authenticated-orcid":false,"given":"Muhammet","family":"Guzelsoy","sequence":"additional","affiliation":[{"name":"Department of Urology, Bursa Yuksek Ihtisas Training and Research Hospital University of Health Sciences Bursa Turkiye"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2026,10,5]]},"reference":[{"key":"e_1_2_11_2_1","doi-asserted-by":"publisher","DOI":"10.1016\/J.EUROS.2022.08.013"},{"key":"e_1_2_11_3_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpurol.2024.12.010"},{"key":"e_1_2_11_4_1","doi-asserted-by":"publisher","DOI":"10.1097\/01.AOG.0000227778.77189.2D"},{"key":"e_1_2_11_5_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-06291-2"},{"key":"e_1_2_11_6_1","doi-asserted-by":"publisher","DOI":"10.1038\/s44387-025-00011-z"},{"key":"e_1_2_11_7_1","doi-asserted-by":"publisher","DOI":"10.1002\/NAU.24292"},{"key":"e_1_2_11_8_1","doi-asserted-by":"publisher","DOI":"10.1016\/J.JURO.2017.12.051"},{"key":"e_1_2_11_9_1","doi-asserted-by":"publisher","DOI":"10.1002\/NAU.23124"},{"key":"e_1_2_11_10_1","doi-asserted-by":"publisher","DOI":"10.1002\/NAU.70074"},{"key":"e_1_2_11_11_1","doi-asserted-by":"publisher","DOI":"10.1007\/S11884-023-00734-2\/METRICS"},{"key":"e_1_2_11_12_1","doi-asserted-by":"publisher","DOI":"10.1016\/J.UROLOGY.2021.09.027"},{"key":"e_1_2_11_13_1","doi-asserted-by":"publisher","DOI":"10.1002\/NAU.25490"},{"key":"e_1_2_11_14_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-025-01752-2"},{"key":"e_1_2_11_15_1","doi-asserted-by":"publisher","DOI":"10.1002\/NAU.70160"},{"key":"e_1_2_11_16_1","doi-asserted-by":"publisher","DOI":"10.3390\/ai6110287"},{"key":"e_1_2_11_17_1","doi-asserted-by":"publisher","DOI":"10.2196\/72062"},{"key":"e_1_2_11_18_1","doi-asserted-by":"publisher","DOI":"10.1002\/nau.70160"},{"key":"e_1_2_11_19_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-025-01670-7"},{"key":"e_1_2_11_20_1","doi-asserted-by":"publisher","DOI":"10.1038\/s43856-025-01021-3"},{"key":"e_1_2_11_21_1","doi-asserted-by":"publisher","DOI":"10.1016\/J.JPUROL.2021.05.004"},{"key":"e_1_2_11_22_1","doi-asserted-by":"publisher","DOI":"10.2196\/64963"}],"container-title":["Neurourology and Urodynamics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/nau.70470","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/nau.70470","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/nau.70470","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,5]],"date-time":"2026-10-05T08:21:55Z","timestamp":1791188515000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1002\/nau.70470"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10,5]]},"references-count":21,"alternative-id":["10.1002\/nau.70470"],"URL":"https:\/\/doi.org\/10.1002\/nau.70470","archive":["Portico"],"relation":{},"ISSN":["0733-2467","1520-6777"],"issn-type":[{"value":"0733-2467","type":"print"},{"value":"1520-6777","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,10,5]]},"assertion":[{"value":"2026-06-13","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-09-26","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-10-05","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"nau.70470"}}