[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-339914-105":59,"doc-detail-339914-en":130},{"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":123,"head_meta":125,"extra_data":127,"updated_unix":129},105,"en","breast-cancer-in-the-era-of-generative-artificial-intelligence-assistant-tools-for-clinical-doctors-based-on-chatgpt-correspondence","Breast cancer in the era of generative artificial intelligence: assistant tools for clinical doctors based on ChatGPT - Correspondence","","Letter to the editor examining the clinical relevance of large language models for breast cancer care. It questions how response heterogeneity arises from differences in training time, data sources, dataset size and diversity, and optimization methods, emphasizing that medical knowledge updates rapidly. It further addresses evaluation design, arguing that expert panels should be diverse across centers, regions, and countries to ensure representativeness in judging model performance and applicability across healthcare systems, cultures, and patient characteristics.",{"@graph":69,"@context":122},[70,84,105],{"@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":35,"@type":76,"position":81},"https://docshare.wps.com/document/healthcare/",3,{"item":83,"name":65,"@type":76,"position":19},"https://docshare.wps.com/document/breast-cancer-in-the-era-of-generative-artificial-intelligence-assistant-tools-for-clinical-doctors-based-on-chatgpt-correspondence/339914/",{"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/breast-cancer-in-the-era-of-generative-artificial-intelligence-assistant-tools-for-clinical-doctors-based-on-chatgpt-correspondence/339914.png","ImageObject",300,407,{"name":92,"@type":93},"Asher","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-10-23","2026-09-21",true,{"@type":102,"interactionType":103,"userInteractionCount":39},"InteractionCounter",{"@type":104},"ViewAction",{"@type":106,"mainEntity":107},"FAQPage",[108,114,118],{"name":109,"@type":110,"acceptedAnswer":111},"Why does the letter emphasize heterogeneity in LLM responses for breast cancer?","Question",{"text":112,"@type":113},"It attributes differences to how GPT series models are trained on large internet corpora at different times, leading to distinct training data, knowledge bases, and coverage of evolving medical information.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"How does the letter connect model release timing to clinical accuracy?",{"text":117,"@type":113},"It argues that medical knowledge and guidelines can change yearly or faster, so models released at different times may differ in timeliness and therefore produce different answers to the same medical questions.",{"name":119,"@type":110,"acceptedAnswer":120},"What evaluation approach does the letter recommend for expert panels?",{"text":121,"@type":113},"It recommends recruiting evaluators from multiple centers, regions, and countries so performance assessments reflect variations in healthcare resources, cultural backgrounds, patient characteristics, and clinical practice standards.","https://schema.org",{"og:url":83,"og:type":124,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":126,"canonical":83},"index,follow",{"doc_id":128,"site_id":62},339914,1790620477,{"code":4,"msg":5,"data":131},{"doc_id":128,"user_id":132,"nickname":92,"user_avatar":133,"doc_module":4,"category_id":34,"category_name":35,"doc_title":65,"doc_description":67,"doc_content":134,"file_id":135,"file_url":136,"file_type":137,"file_size":138,"view_count":39,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":14,"language":139,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":140,"faqs":141,"seo_title":142,"seo_description":67,"update_tm":143,"read_time":24},687197207639,"https://ap-avatar.wpscdn.com/davatar_a8503ba1806abce46bf441b54a3ca4cd","’Correspondence  \nBreast cancer in the era of generative artificial intelligence: assistant tools for clinical doctors based on ChatGPT  \nYue Zheng, MDa,b , Xu Sun, MDc , Kai Kang, MDa,b , Ailin Zhao, MDc,*, Yijun Wu, MDa,b,*  \nDear Editor,  \nLarge Language Models (LLMs) have garnered widespread attention in the field of artificial intelligence (AI) due to their outstanding contextual understanding and responsiveness[1] . However, the potential of LLMs in the diagnosis, treatment, and care of breast cancer remains insufficiently explored. The study conducted by Deng et al. [2] represents a significant step forward in understanding the potential application of LLMs in the clinical context of breast cancer. The comparison between ChatGPT-3.5, ChatGPT-4.0, and Claude2 sheds light on the varying capabilities of these models and underscores the importance of domain-specific optimization in advancing the utility of AI in critical medical scenarios.  \nAfter carefully reading the article, we have several questions for the authors and fellow researchers to gain a more comprehensive understanding of the paper.  \nFirstly, regarding the heterogeneity issue in LLMs responses. The GPT series models are trained on vast amounts of internet text data, implying that their knowledge and language patterns are built upon the foundation of current internet information[3] . However, the medical field is a constantly updating and evolving domain, with new research findings, clinical guidelines, and medical technologies emerging continuously, resulting in a rapid pace of knowledge updatesin medicine. ChatGPT-3.5, ChatGPT- 4.0, and Claude2 being models released at different points in time, would have differences in their training data and knowledge bases. For example, ChatGPT-3.5 might have been trained in  \naDivision of Thoracic Tumor Multimodality Treatment, Cancer Center, West China Hospital, Sichuan University, bLaboratory of Clinical Cell Therapy, West China Hospital, Sichuan University and cDepartment of Hematology, West China Hospital,  \nSichuan University, Chengdu, Sichuan, People ’s Republic of China Yue Zheng, Xu Sun, and Kai Kang contributed equally to this work.  \nSponsorships or competing interests that maybe relevant to content are disclosed atthe end of this article.  \n*Corresponding authors. Address: Department of Hematology, West China Hospital, Sichuan University, Chengdu, Sichuan 610041, People ’s Republic of China.  \nTel.: +28 854 221 14. E-mail: [irenez20@outlook.com](irenez20@outlook.com) (A. Zhao); Division of Thoracic Tumor Multimodality Treatment, Cancer Center, West China Hospital, Sichuan University, Chengdu, Sichuan, People ’s Republic of China.  \n[E-mail: wuyj01029@wchscu.cn](E-mail: wuyj01029@wchscu.cn) (Y. Wu).  \nCopyright © 2024 The Author(s). Published by Wolters Kluwer Health, Inc. This is an open access article distributed under the Creative Commons Attribution-ShareAlike License 4.0, which allows others to remix, tweak, and build upon the work, even for commercial purposes, as long as the author is credited and the new creations are licensed under the identical terms.  \nInternational Journal of Surgery (2024) 110:5304–5305  \nReceived 25 April 2024; Accepted 25 April 2024  \nPublished online 8 May 2024  \n[http://dx.doi.org/10.1097/JS9.0000000000001597](http://dx.doi.org/10.1097/JS9.0000000000001597)  \nearlier stages, potentially leaning toward earlier medical research findings and clinical practices. As time progresses, ChatGPT-4.0 and Claude2 may incorporate updated and more extensive data and knowledge, better reflecting current medical practices and the latest research findings. However, even models released at the same time may have differences in the knowledge they encompass[4] . This depends on factors such as the sources of training data, the size and diversity of datasets, and optimization techniques of training algorithms. In addition to the temporal aspect of the models themselves, the pace of medical information update","cbCaik98hnJSuwyV","https://ap.wps.com/l/cbCaik98hnJSuwyV","pdf",203773,"English","# Correspondence\n## Context and motivation\n## Heterogeneity in LLM responses\n## Timeliness and medical knowledge updates\n## Diversity of expert panels for evaluation","[{\"question\":\"Why does the letter emphasize heterogeneity in LLM responses for breast cancer?\",\"answer\":\"It attributes differences to how GPT series models are trained on large internet corpora at different times, leading to distinct training data, knowledge bases, and coverage of evolving medical information.\"},{\"question\":\"How does the letter connect model release timing to clinical accuracy?\",\"answer\":\"It argues that medical knowledge and guidelines can change yearly or faster, so models released at different times may differ in timeliness and therefore produce different answers to the same medical questions.\"},{\"question\":\"What evaluation approach does the letter recommend for expert panels?\",\"answer\":\"It recommends recruiting evaluators from multiple centers, regions, and countries so performance assessments reflect variations in healthcare resources, cultural backgrounds, patient characteristics, and clinical practice standards.\"}]","Breast cancer in the era of generative artificial intelligence: assistant tools for clinical doctors based on ChatGPT - Correspondence | PDF",1790033051]