[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-353849-105":59,"doc-detail-353849-en":135},{"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":128,"head_meta":130,"extra_data":132,"updated_unix":134},105,"en","comparison-of-large-language-models-and-expert-multidisciplinary-team-decisions-in-colorectal-cancer-original-research","Comparison of large language models and expert multidisciplinary team decisions in colorectal cancer - Original research","","Objectives evaluate how large language models simulate multidisciplinary team (MDT) decision-making in colorectal cancer, a malignancy requiring complex treatment planning. Methods retrospectively analyze 1423 real-world MDT cases from Peking University Cancer Hospital (Jan 2023–Dec 2024), testing three LLMs and selecting only cases with consistent outputs across three runs per model. Concordance uses agreement percentages and Cohen’s kappa. Results O3 shows best intramodel stability (81.0%); predictors include treatment-naïve status, non-metastatic disease, and colon tumor location. Conclusions LLMs partially replicate MDT recommendations and should complement, not replace, clinicians.",{"@graph":69,"@context":127},[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/comparison-of-large-language-models-and-expert-multidisciplinary-team-decisions-in-colorectal-cancer-original-research/353849/",{"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/comparison-of-large-language-models-and-expert-multidisciplinary-team-decisions-in-colorectal-cancer-original-research/353849.png","ImageObject",300,407,{"name":92,"@type":93},"Ophelia","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-11-18","2026-09-22",true,{"@type":102,"interactionType":103,"userInteractionCount":105},"InteractionCounter",{"@type":104},"ViewAction",18,{"@type":107,"mainEntity":108},"FAQPage",[109,115,119,123],{"name":110,"@type":111,"acceptedAnswer":112},"What is the study’s primary objective?","Question",{"text":113,"@type":114},"To evaluate whether large language models can simulate multidisciplinary team (MDT) decision-making in colorectal cancer and replicate expert recommendations.","Answer",{"name":116,"@type":111,"acceptedAnswer":117},"How were cases and models evaluated?",{"text":118,"@type":114},"The study retrospectively analyzed 1423 MDT-discussed colorectal cancer cases and tested three LLMs, including only cases with consistent outputs across three runs per model. Concordance with expert MDT consensus was measured with agreement percentages and Cohen’s kappa.",{"name":120,"@type":111,"acceptedAnswer":121},"Which model performed best for stability and how did it relate to expert agreement?",{"text":122,"@type":114},"O3 showed the highest intramodel stability (81.0% agreement; Fleiss’ kappa 0.794). Concordance with MDT consensus was similar across models, ranging roughly from 62.5% to 65.4%.",{"name":124,"@type":111,"acceptedAnswer":125},"What factors were associated with higher concordance with expert MDT decisions?",{"text":126,"@type":114},"Multivariable analysis of O3 outputs identified treatment-naïve status, non-metastatic disease, and colon tumor location as independent predictors of higher concordance.","https://schema.org",{"og:url":83,"og:type":129,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":131,"canonical":83},"index,follow",{"doc_id":133,"site_id":62},353849,1790733802,{"code":4,"msg":5,"data":136},{"doc_id":133,"user_id":137,"nickname":92,"user_avatar":138,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":139,"file_id":140,"file_url":141,"file_type":142,"file_size":143,"view_count":105,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":39,"language":144,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":145,"faqs":146,"seo_title":147,"seo_description":67,"update_tm":148,"read_time":46,"preview_page_count":19,"preview_urls":149},7971461741311,"https://ap-avatar.wpscdn.com/avatar/74000253aff267980c6?x-image-process=image/resize,m_fixed,w_180,h_180&k=1779345379180704826","Open access Original research  \nComparison of large language models and expert multidisciplinary team decisions in colorectal cancer  \nBoyang Qu,1 Longhao Cao,2,3 Chen Wu,4 Yongjiu Chen,1 Tingting Sun,1 Junpeng Pei,1 Lei Huang,1 Xiaotong Hou,1 Dawei Li,2 Aiwen Wu  1  \nTo cite: Qu B, Cao L, Wu C, et al. Comparison of large language models and expert multidisciplinary team decisions in colorectal cancer. BMJ Health Care Inform 2026;33:e101780 . doi:10 . 1136/ bmjhci-2025-101780  \n► Additional supplemental material is published online only. To view, please visit the journal online ([https://doi.org/10.1136/](https://doi.org/10.1136/)[ ](https://doi.org/10.1136/)[bmjhci-2025-101780](bmjhci-2025-101780)) .  \nBQ and LC contributed equally.  \nReceived 31 August 2025 Accepted 10 February 2026  \n© Author(s) (or their employer(s)) 2026. Re-use permitted under CC BY-NC. No commercial re-use. See rights and permissions. Published by BMJ Group.  \nFor numbered affiliations see end of article.  \nCorrespondence to  \nDr Aiwen Wu; [drwuaw@sina.com](drwuaw@sina.com)  \nDr Dawei Li;  \n[lidawei@pku.edu.cn](lidawei@pku.edu.cn)  \nABSTRACT  \nObjectives To evaluate the ability of large language models (LLMs) to simulate multidisciplinary team (MDT) decision-making in colorectal cancer, a malignancy that often requires complex treatment planning.  \nMethods We retrospectively analysed 1423 colorectal cancer cases discussed at MDT meetings at Peking University Cancer Hospital between January 2023 and December 2024. Three LLMs—OpenAI o3-mini-2025- 01-31, DeepSeek-R1 671b and Qwen qwq-plus-2025- 03-05—were tested for their ability to replicate MDT recommendations using a standardised treatment categorisation framework. Each case was processed three times per model; only cases with consistent outputs across all three runs were included. Concordance between AI-generated decisions and expert MDT consensus was assessed using agreement percentages and Cohen’s kappa.  \nResults O3 demonstrated the highest intramodel stability, with an agreement rate of 81 .0%(Fleiss’ kappa=0 .794), yielding 1153 cases with consistent outputs. Concordance with MDT consensus was comparable across the three models, ranging from 62.5% to 65.4% . Multivariable analysis of O3 outputs identified treatment-naïve status, non-metastatic disease and colon tumour location as independent predictors of higher concordance with experts.  \nDiscussion LLMs showed fair overall agreement with expert MDT decisions, with stronger performance in standardised and less complex clinical scenarios. Areas of higher concordance included treatment-naïve nonmetastatic colon cancer, treated non-metastatic rectal cancer and treated non-metastatic colon cancer. Conclusion LLMs can partially replicate expert MDT recommendations in colorectal cancer. Their integration into clinical workflows should aim to complement, rather than replace, human expertise.   \nINTRODUCTION  \nArtificial intelligence, particularly large language models (LLMs), is driving transformative changes in healthcare by learning from vast amounts of medical data.1–5 These technologies facilitate intelligent medical record analysis, automated medical image interpretation, clinical decision support for  \nWHAT IS ALREADY KNOWN ON THIS TOPIC  \n\n| ⇒ Multidisciplinary team (MDT) decision-making improves outcomes in colorectal cancer but is complex and resource intensive. Recent small studies suggest that large language models (LLMs) may support MDT decisions in oncology, yet evidence from large real-world colorectal cancer cohorts and across multiple models remains limited.\u003Cbr>WHAT THIS STUDY ADDS |\n| --- |\n| ⇒ Using 1423 real-world MDT cases, this study demonstrates that three LLMs achieve only fair agreement with expert MDT decisions, with concordance rates around 63%–65% . Model agreement was higher in more standardised scenarios, particularly non-metastatic colon cancer and previously treated disease, and lower in complex or indeterminate decision c","cbCaihVmCqzXjAoB","https://ap.wps.com/l/cbCaihVmCqzXjAoB","pdf",1161157,"English","# Abstract\n## Objectives\n## Methods\n## Results\n## Discussion\n## Conclusion\n# Introduction\n## Background\n## Prior research\n# What is already known on this topic\n# What this study adds\n# How this study might affect research, practice or policy","[{\"question\":\"What is the study’s primary objective?\",\"answer\":\"To evaluate whether large language models can simulate multidisciplinary team (MDT) decision-making in colorectal cancer and replicate expert recommendations.\"},{\"question\":\"How were cases and models evaluated?\",\"answer\":\"The study retrospectively analyzed 1423 MDT-discussed colorectal cancer cases and tested three LLMs, including only cases with consistent outputs across three runs per model. Concordance with expert MDT consensus was measured with agreement percentages and Cohen’s kappa.\"},{\"question\":\"Which model performed best for stability and how did it relate to expert agreement?\",\"answer\":\"O3 showed the highest intramodel stability (81.0% agreement; Fleiss’ kappa 0.794). Concordance with MDT consensus was similar across models, ranging roughly from 62.5% to 65.4%.\"},{\"question\":\"What factors were associated with higher concordance with expert MDT decisions?\",\"answer\":\"Multivariable analysis of O3 outputs identified treatment-naïve status, non-metastatic disease, and colon tumor location as independent predictors of higher concordance.\"}]","Comparison of large language models and expert multidisciplinary team decisions in colorectal cancer - Original research | PDF",1790107537,[150,154,158,162],{"page_no":8,"url":151,"width":152,"height":153},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/a7191f28cbc23d7b382d9e31fad936b8.webp",983,1310,{"page_no":14,"url":155,"width":156,"height":157},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/a99deac55a3a6511167c8382e159b0a6.webp",982,1309,{"page_no":81,"url":159,"width":160,"height":161},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/1ec6f8f8746629cb2fa444f69ccd4273.webp",981,1308,{"page_no":19,"url":163,"width":164,"height":165},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/2a557a4e59d25ba84673243cb810b440.webp",980,1306]