[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-355378-105":59,"doc-detail-355378-en":131},{"code":4,"msg":5,"data":6},0,"success",[7,13,18,23,28,33,38,43,48,51,55],{"id":8,"doc_module":4,"doc_module_name":9,"category_name":10,"show_sort_weight":11,"slug":12},1,"Document","Story & Novel",90,"story-novel",{"id":14,"doc_module":4,"doc_module_name":9,"category_name":15,"show_sort_weight":16,"slug":17},2,"Literature",80,"literature",{"id":19,"doc_module":4,"doc_module_name":9,"category_name":20,"show_sort_weight":21,"slug":22},4,"Exam",70,"exam",{"id":24,"doc_module":4,"doc_module_name":9,"category_name":25,"show_sort_weight":26,"slug":27},5,"Comic",60,"comic",{"id":29,"doc_module":4,"doc_module_name":9,"category_name":30,"show_sort_weight":31,"slug":32},6,"Technology",50,"technology",{"id":34,"doc_module":4,"doc_module_name":9,"category_name":35,"show_sort_weight":36,"slug":37},7,"Healthcare",40,"healthcare",{"id":39,"doc_module":4,"doc_module_name":9,"category_name":40,"show_sort_weight":41,"slug":42},8,"Research & Report",30,"research-report",{"id":44,"doc_module":4,"doc_module_name":9,"category_name":45,"show_sort_weight":46,"slug":47},9,"Religion & Spirituality",20,"religion-spirituality",{"id":46,"doc_module":4,"doc_module_name":9,"category_name":49,"show_sort_weight":46,"slug":50},"World Cup","world-cup",{"id":52,"doc_module":4,"doc_module_name":9,"category_name":53,"show_sort_weight":52,"slug":54},10,"Lifestyle","lifestyle",{"id":56,"doc_module":4,"doc_module_name":9,"category_name":57,"show_sort_weight":24,"slug":58},19,"General","general",{"code":4,"msg":60,"data":61},"ok",{"site_id":62,"language":63,"slug":64,"title":65,"keywords":66,"description":67,"schema_data":68,"social_meta":124,"head_meta":126,"extra_data":128,"updated_unix":130},105,"en","accuracy-of-large-language-models-in-interpreting-urological-clinical-guidelines-a-comparative-study-with-expert-evaluation","Accuracy of large language models in interpreting urological clinical guidelines - a comparative study with expert evaluation","","Large language models are increasingly explored to support evidence-based decisions in urology, yet their accuracy when interpreting and applying clinical guidelines remains unclear. This expert-validated study evaluated six configurations of Claude, Gemini, and ChatGPT on 25 structured questions across seven major urological cancers. Figures and tables from English EAU guidelines were converted to plain structured text and peer reviewed. Responses were rated by 9–11 uro-oncology specialists on a 5-point Likert scale, yielding 10,500 evaluations.",{"@graph":69,"@context":123},[70,84,106],{"@type":71,"itemListElement":72},"BreadcrumbList",[73,77,79,82],{"item":74,"name":75,"@type":76,"position":8},"https://docshare.wps.com","Home","ListItem",{"item":78,"name":9,"@type":76,"position":14},"https://docshare.wps.com/document/",{"item":80,"name":40,"@type":76,"position":81},"https://docshare.wps.com/document/research-report/",3,{"item":83,"name":65,"@type":76,"position":19},"https://docshare.wps.com/document/accuracy-of-large-language-models-in-interpreting-urological-clinical-guidelines-a-comparative-study-with-expert-evaluation/355378/",{"url":83,"name":65,"@type":85,"image":86,"author":91,"headline":65,"publisher":94,"fileFormat":97,"inLanguage":63,"description":67,"dateModified":98,"datePublished":99,"encodingFormat":97,"isAccessibleForFree":100,"interactionStatistic":101},"DigitalDocument",{"url":87,"@type":88,"width":89,"height":90},"https://docshare.wps.com/thumbnails/accuracy-of-large-language-models-in-interpreting-urological-clinical-guidelines-a-comparative-study-with-expert-evaluation/355378.png","ImageObject",300,407,{"name":92,"@type":93},"Jacob","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-10-30","2026-09-22",true,{"@type":102,"interactionType":103,"userInteractionCount":105},"InteractionCounter",{"@type":104},"ViewAction",16,{"@type":107,"mainEntity":108},"FAQPage",[109,115,119],{"name":110,"@type":111,"acceptedAnswer":112},"What was the primary aim of this study?","Question",{"text":113,"@type":114},"To evaluate how accurately large language models interpret and apply urological clinical guidelines across major urological cancers.","Answer",{"name":116,"@type":111,"acceptedAnswer":117},"How were the models evaluated in this expert-validated design?",{"text":118,"@type":114},"Six configurations of Claude, Gemini, and ChatGPT were tested using 25 structured questions per cancer, with guideline content adapted into plain structured text and rated on a five-point Likert scale by 9–11 uro-oncology specialists.",{"name":120,"@type":111,"acceptedAnswer":121},"Which model performed best and how should results be interpreted?",{"text":122,"@type":114},"Claude achieved the highest overall accuracy, but the authors recommend cautious interpretation due to recency bias and rapid LLM technological evolution.","https://schema.org",{"og:url":83,"og:type":125,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":127,"canonical":83},"index,follow",{"doc_id":129,"site_id":62},355378,1790546468,{"code":4,"msg":5,"data":132},{"doc_id":129,"user_id":133,"nickname":92,"user_avatar":134,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":135,"file_id":136,"file_url":137,"file_type":138,"file_size":139,"view_count":105,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":140,"language":141,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":142,"faqs":143,"seo_title":144,"seo_description":67,"update_tm":145,"read_time":146,"preview_page_count":19,"preview_urls":147},962084931830,"https://ap-avatar.wpscdn.com/davatar_a8503ba1806abce46bf441b54a3ca4cd","TherapeuTic advances in  \nurology Original Research  \n\n| Accuracy of large language models in interpreting urological clinical guidelines:\u003Cbr>a comparative study with expert evaluation\u003Cbr>Ángel Borque-Fernando, Denis Navarro, Manuel Doblare, Luis M. Esteban,\u003Cbr>Daniel Perez-Fentes, Mario Álvarez-Maestro, Rafael A. Medina-López, Oscar Rodríguez Faba, José Rubio-Briones, Sergio Fernández-Pello, Jesús María Fernández-Gómez,\u003Cbr>Tomás Fernández Aparicio, Félix Guerrero Ramos, Laura Izquierdo and\u003Cbr>José Luis Álvarez-Ossorio Fernández\u003Cbr>Abstract\u003Cbr>Background: Large language models (LLMs) are increasingly being explored to supporting evidence-based decision-making in urology, but their accuracy in interpreting and applying clinical guidelines remains uncertain.\u003Cbr>Objectives: We aimed to evaluate the ability of LLMs to interpret and apply clinical guidelines across the full spectrum of major urological cancers.\u003Cbr>Design: This expert-validated study evaluated six configurations of three top LLMs (Claude, Gemini, and ChatGPT) using 25 structured questions for each of the seven major urological cancers: prostate cancer, upper tract urothelial carcinoma, muscle-invasive and non-muscleinvasive bladder cancer, renal cell carcinoma, penile cancer, and testicular cancer.\u003Cbr>Methods: Both simple and rephrased prompts were used to assess the impact of prompt engineering on response quality. All figures and tables from the English-language EAU guidelines were systematically converted into plain, structured text and peer reviewed by multidisciplinary experts before evaluating the LLM responses. Each response was\u003Cbr>independently rated by 9–11 uro-oncology specialists using a five-point Likert scale (1: incorrect/unacceptable, 5: optimal), resulting in 10,500 evaluations.\u003Cbr>Results: Claude achieved the highest overall accuracy, with 45.9% of responses rated as optimal (Likert 5) and 87% as optimal/acceptable (Likert 4–5) . Tumor-specific performance peaked in muscle-invasive bladder (56 . 7% optimal, 93% optimal/acceptable), penile (49 . 5%, 95%), and testicular cancer (60 . 9%, 94%) . Gemini and ChatGPT showed lower optimal rates but acceptable performance (68%–70% optimal/acceptable) . Rephrased prompts did not consistently outperform simple versions. All models showed acceptable accuracy, but the results should be interpreted cautiously due to recency bias and fast LLM tech evolution. Conclusion: This study demonstrates the value of rigorous plain language adaptation and expert validation in benchmarking LLMs, supporting their potential as decision-support tools in uro-oncology.\u003Cbr>Keywords: artificial intelligence, clinical, decision support systems, large language models, natural language processing, practice guidelines as topic, urologic neoplasms, validation study\u003Cbr>Received: 26 August 2025; revised manuscript accepted: 27 February 2026. | TherAdv Urol\u003Cbr>2026, Vol. 18: 1–17\u003Cbr>DOI: 10. 1177/\u003Cbr>17562872261436905 © The Author(s), 2026. Article reuse guidelines:\u003Cbr>[sagepub.com/journals](sagepub.com/journals)permissions\u003Cbr>Correspondence to:\u003Cbr>Ángel Borque-Fernando\u003Cbr>Unidad de Próstata, Servicio de Urología, Hospital Universitario Miguel Servet, Zaragoza, Spain\u003Cbr>Área de Urología, Departamento de Cirugía, Facultad de Medicina, Universidad de Zaragoza, Zaragoza, Spain\u003Cbr>Grupo de Investigación“URO-SERVET,” IISAragón, Zaragoza, Spain Grupo de Ingeniería y Ciencia de Datos Aplicada, Escuela Universitaria Politécnica de La Almunia, Universidad de Zaragoza, Zaragoza, Spain\u003Cbr>[dr.borque@gmail.com](dr.borque@gmail.com)\u003Cbr>Denis Navarro\u003Cbr>Department of Electronic Engineering and Communications I3A, Universidad de Zaragoza, Zaragoza, Spain\u003Cbr>Manuel Doblare\u003Cbr>Aragón Institute of Engineering Research (I3A), Zaragoza, Spain Aragón Institute of Health Research (IIS Aragón), Zaragoza, Spain\u003Cbr>Luis M. Esteban\u003Cbr>Escuela Universitaria Politécnica de La Almunia, Instituto de Biocomputacion y Física de Sistemas Complejos, Universidad de Zaragoza","cbCaifFzukz9vmZN","https://ap.wps.com/l/cbCaifFzukz9vmZN","pdf",4007327,17,"English","# Abstract\n## Background\n## Objectives\n## Design\n## Methods\n## Results\n## Conclusion\n# Keywords","[{\"question\":\"What was the primary aim of this study?\",\"answer\":\"To evaluate how accurately large language models interpret and apply urological clinical guidelines across major urological cancers.\"},{\"question\":\"How were the models evaluated in this expert-validated design?\",\"answer\":\"Six configurations of Claude, Gemini, and ChatGPT were tested using 25 structured questions per cancer, with guideline content adapted into plain structured text and rated on a five-point Likert scale by 9–11 uro-oncology specialists.\"},{\"question\":\"Which model performed best and how should results be interpreted?\",\"answer\":\"Claude achieved the highest overall accuracy, but the authors recommend cautious interpretation due to recency bias and rapid LLM technological evolution.\"}]","Accuracy of large language models in interpreting urological clinical guidelines - a comparative study with expert evaluation | PDF",1790118224,43,[148,152,156,160],{"page_no":8,"url":149,"width":150,"height":151},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/b7141c3b83042fda83ebf79109d3cd7f.webp",983,1310,{"page_no":14,"url":153,"width":154,"height":155},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/80509160b970177e8d496cc7d515ef7a.webp",982,1309,{"page_no":81,"url":157,"width":158,"height":159},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/7bb030f535f33346817b13244de81142.webp",981,1308,{"page_no":19,"url":161,"width":162,"height":163},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/6e1484c290fd2c153ca7cffb948312f2.webp",980,1306]