[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-337197-105":59,"doc-detail-337197-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","automated-pathologic-tn-classification-prediction-and-rationale-generation-from-lung-cancer-surgical-pathology-reports-using-a-large-language-model-fine-tuned-with-chain-of-thought-algorithm-development-and-validation-study","Automated Pathologic TN Classification Prediction and Rationale Generation From Lung Cancer Surgical Pathology Reports Using a Large Language Model Fine-Tuned With Chain-of-Thought - Algorithm Development and Validation Study","","Traditional rule-based NLP methods in EHR systems can handle clinical text effectively, yet they are often slow and error-prone when applied to unstructured documentation due to heavy manual parsing requirements. Large language models enable automated interpretation of medical context and may support pathologic staging, but they struggle to adapt quickly to updates of specialized guidelines. This study fine-tunes an LLM for lung cancer pathologic TN classification using current guideline content, then evaluates performance and rationale extraction from surgical pathology reports.",{"@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":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/automated-pathologic-tn-classification-prediction-and-rationale-generation-from-lung-cancer-surgical-pathology-reports-using-a-large-language-model-fine-tuned-with-chain-of-thought-algorithm-development-and-validation-study/337197/",{"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/automated-pathologic-tn-classification-prediction-and-rationale-generation-from-lung-cancer-surgical-pathology-reports-using-a-large-language-model-fine-tuned-with-chain-of-thought-algorithm-development-and-validation-study/337197.png","ImageObject",300,407,{"name":92,"@type":93},"Theodora","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-11-12","2026-09-21",true,{"@type":102,"interactionType":103,"userInteractionCount":34},"InteractionCounter",{"@type":104},"ViewAction",{"@type":106,"mainEntity":107},"FAQPage",[108,114,118],{"name":109,"@type":110,"acceptedAnswer":111},"Why are rule-based NLP approaches limited for lung cancer staging from surgical pathology reports?","Question",{"text":112,"@type":113},"They can be effective but are time-consuming and error-prone for unstructured data, mainly due to substantial manual effort to parse and extract information from diverse documentation types.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"What is the objective of the fine-tuned language model in this study?",{"text":117,"@type":113},"To evaluate fine-tuned generative language models for automatically inferring pathologic TN classifications and extracting their rationale from lung cancer surgical pathology reports.",{"name":119,"@type":110,"acceptedAnswer":120},"How was model performance measured and which model performed best?",{"text":121,"@type":113},"Performance was assessed using exact match ratio (EMR) for classification accuracy and semantic match ratio (SMR) for contextual alignment of rationales. The Orca2_13b model achieved the highest performance with an EMR of 0.934 and an SMR of 0.864.","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},337197,1790549536,{"code":4,"msg":5,"data":131},{"doc_id":128,"user_id":132,"nickname":92,"user_avatar":133,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":134,"file_id":135,"file_url":136,"file_type":137,"file_size":138,"view_count":34,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":139,"language":140,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":141,"faqs":142,"seo_title":143,"seo_description":67,"update_tm":144,"read_time":145,"preview_page_count":19,"preview_urls":146},687197207919,"https://ap-avatar.wpscdn.com/avatar/a000253d6f5f7c60be?x-image-process=image/resize,m_fixed,w_180,h_180&k=1779446848396160552","JMIR MEDICAL INFORMATICS Kim et al  \nOriginal Paper  \nAutomated Pathologic TN Classification Prediction and Rationale Generation From Lung Cancer Surgical Pathology Reports Using a Large Language Model Fine-Tuned With Chain-of-Thought: Algorithm Development and Validation Study  \n\n| Sanghwan Kim 1*, MS; Sowon Jang2*, MD; Borham Kim3, BS; Leonard Sunwoo2, MD, PhD; Seok Kim3, MPH; Jin-Haeng Chung4,5, MD, PhD; Sejin Nam1, PhD; Hyeongmin Cho1, MS; Donghyoung Lee 1 ; Keehyuck Lee6*, MD, MBA; Sooyoung Yoo3, PhD |\n| --- |\n| 1ezCaretech Research & Development Center, Seoul, Republic of Korea\u003Cbr>2Department of Radiology, Seoul National University Bundang Hospital, Seongnam, Republic of Korea\u003Cbr>3Office of eHealth Research and Business, Seoul National University Bundang Hospital, Seongnam, Republic of Korea 4Department of Pathology, Seoul National University College of Medicine, Seoul, Republic of Korea\u003Cbr>5Department of Pathology and Translational Medicine, Seoul National University Bundang Hospital, Seongnam, Republic of Korea 6Department of Family Medicine, Seoul National University Bundang Hospital, Seongnam, Republic of Korea\u003Cbr>*these authors contributed equally\u003Cbr>Corresponding Author:\u003Cbr>Sooyoung Yoo, PhD\u003Cbr>Office of eHealth Research and Business Seoul National University Bundang Hospital Healthcare Innovation Park\u003Cbr>Seongnam, 13605 Republic of Korea Phone: 82 317878980\u003Cbr>[Email:](Email: yoosoo0@snubh.org)[ ](Email: yoosoo0@snubh.org)[yoosoo0@snubh.org](Email: yoosoo0@snubh.org)\u003Cbr>Abstract |\n\nBackground: Traditional rule-based natural language processing approaches in electronic health record systems are effective but are often time-consuming and prone to errors when handling unstructured data. This is primarily due to the substantial manual effort required to parse and extract information from diverse types of documentation. Recent advancements in large language model (LLM) technology have made it possible to automatically interpret medical context and support pathologic staging. However, existing LLMs encounter challenges in rapidly adapting to specialized guideline updates. In this study, we fine-tunedan LLM specifically for lung cancer pathologic staging, enabling it to incorporate the latest guidelines for pathologic TN classification.  \nObjective: This study aims to evaluate the performance of fine-tuned generative language models in automatically inferring pathologic TN classifications and extracting their rationale from lung cancer surgical pathology reports. By addressing the inefficiencies and extensive parsing efforts associated with rule-based methods, this approach seeks to enable rapid and accurate reclassification aligned with the latest cancer staging guidelines.  \nMethods: We conducted a comparative performance evaluation of 6 open-source LLMs for automated TN classification and rationale generation, using 3216 deidentified lung cancer surgical pathology reports based on the American Joint Committee on Cancer (AJCC) Cancer Staging Manual8th edition, collected from a tertiary hospital. The dataset was preprocessed by segmenting each report according to lesion location and morphological diagnosis. Performance was assessed using exact match ratio (EMR) and semantic match ratio (SMR) as evaluation metrics, which measure classification accuracy and the contextual alignment of the generated rationales, respectively.  \nResults: Among the 6 models, the Orca2_ 13b model achieved the highest performance with an EMR of 0.934 and an SMR of 0.864. The Orca2_ 7b model also demonstrated strong performance, recording an EMR of 0.914 and an SMR of 0.854. In contrast, the Llama2_ 7b model achieved an EMR of 0.864 and an SMR of 0.771, while the Llama2_ 13b model showed an EMR of 0.762  \n[https://medinform.jmir.org/2024/1/e67056](https://medinform.jmir.org/2024/1/e67056)  \nXSL• FO  \nRenderX  \nJMIR Med Inform 2024 | vol. 12 | e67056 | p. 1 (page number not for citation purposes)  \nand an SMR of 0.690. The Mistral_ 7b and Llama3_","cbCaiqk5sfANYh4z","https://ap.wps.com/l/cbCaiqk5sfANYh4z","pdf",604269,13,"English","# Abstract\n## Background\n## Objective\n## Methods\n## Results\n## Conclusions\n# Introduction","[{\"question\":\"Why are rule-based NLP approaches limited for lung cancer staging from surgical pathology reports?\",\"answer\":\"They can be effective but are time-consuming and error-prone for unstructured data, mainly due to substantial manual effort to parse and extract information from diverse documentation types.\"},{\"question\":\"What is the objective of the fine-tuned language model in this study?\",\"answer\":\"To evaluate fine-tuned generative language models for automatically inferring pathologic TN classifications and extracting their rationale from lung cancer surgical pathology reports.\"},{\"question\":\"How was model performance measured and which model performed best?\",\"answer\":\"Performance was assessed using exact match ratio (EMR) for classification accuracy and semantic match ratio (SMR) for contextual alignment of rationales. The Orca2_13b model achieved the highest performance with an EMR of 0.934 and an SMR of 0.864.\"}]","Automated Pathologic TN Classification Prediction and Rationale Generation From Lung Cancer Surgical Pathology Reports Using a Large Language Model Fine-Tuned With Chain-of-Thought - Algorithm Development and Validation Study | PDF",1790018100,33,[147,151,155,159],{"page_no":8,"url":148,"width":149,"height":150},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/1eaefa141b69ed5627b7bd26439a6951.webp",983,1390,{"page_no":14,"url":152,"width":153,"height":154},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/1f76bf0920fc31e805ec7f96247918ce.webp",982,1388,{"page_no":81,"url":156,"width":157,"height":158},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/34a1105f49fa3784f4e5b8a71dfe9de0.webp",981,1387,{"page_no":19,"url":160,"width":161,"height":162},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/93647678722ccb95e7f3b6c2320ec30f.webp",980,1385]