[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-seo-357546-105":3,"detail-sidebar-cat-0-en-105":81,"doc-detail-357546-en":131},{"code":4,"msg":5,"data":6},0,"ok",{"site_id":7,"language":8,"slug":9,"title":10,"keywords":11,"description":12,"schema_data":13,"social_meta":74,"head_meta":76,"extra_data":78,"updated_unix":80},105,"en","automated-identification-of-keratinocyte-cancers-in-pathology-reports-using-large-language-models","Automated identification of keratinocyte cancers in pathology reports using large language models","","Keratinocyte cancers (KCs) are common in white-skinned populations but remain underrepresented in cancer registries because reporting rules vary by jurisdiction. Manual extraction of KC subtypes from medical reports is slow and labor-intensive, especially when reports contain multiple co-excised lesions. Fine-tuned Meta-AI LLaMA 3.1-8B-Instruct on 26,179 reviewed Australian pathology reports, achieving F1-scores above 0.90 for key KC subtypes and strong external validation across cohorts. The locally running QSkin-llama model classifies lesion counts, diagnoses, and anatomical sites with high scalability.",{"@graph":14,"@context":73},[15,34,56],{"@type":16,"itemListElement":17},"BreadcrumbList",[18,23,27,31],{"item":19,"name":20,"@type":21,"position":22},"https://docshare.wps.com","Home","ListItem",1,{"item":24,"name":25,"@type":21,"position":26},"https://docshare.wps.com/document/","Document",2,{"item":28,"name":29,"@type":21,"position":30},"https://docshare.wps.com/document/research-report/","Research & Report",3,{"item":32,"name":10,"@type":21,"position":33},"https://docshare.wps.com/document/automated-identification-of-keratinocyte-cancers-in-pathology-reports-using-large-language-models/357546/",4,{"url":32,"name":10,"@type":35,"image":36,"author":41,"headline":10,"publisher":44,"fileFormat":47,"inLanguage":8,"description":12,"dateModified":48,"datePublished":49,"encodingFormat":47,"isAccessibleForFree":50,"interactionStatistic":51},"DigitalDocument",{"url":37,"@type":38,"width":39,"height":40},"https://docshare.wps.com/thumbnails/automated-identification-of-keratinocyte-cancers-in-pathology-reports-using-large-language-models/357546.png","ImageObject",300,407,{"name":42,"@type":43},"Anna Hans","Person",{"url":19,"name":45,"@type":46},"DocShare","Organization","application/pdf","2026-10-29","2026-09-23",true,{"@type":52,"interactionType":53,"userInteractionCount":55},"InteractionCounter",{"@type":54},"ViewAction",16,{"@type":57,"mainEntity":58},"FAQPage",[59,65,69],{"name":60,"@type":61,"acceptedAnswer":62},"Why are keratinocyte cancers underrepresented in cancer registries?","Question",{"text":63,"@type":64},"Reporting requirements differ greatly across jurisdictions, limiting consistent representation in registries.","Answer",{"name":66,"@type":61,"acceptedAnswer":67},"How was the large language model developed in this study?",{"text":68,"@type":64},"The authors fine-tuned Meta-AI LLaMA 3.1-8B-Instruct on 26,179 manually reviewed Australian pathology reports with histologically confirmed KCs.",{"name":70,"@type":61,"acceptedAnswer":71},"What performance did the model achieve for keratinocyte cancer subtypes?",{"text":72,"@type":64},"The model reached F1-scores above 0.90 for four KC subtypes of interest, with robust external validation showing F1-scores between 0.73 and 0.86.","https://schema.org",{"og:url":32,"og:type":75,"og:title":10,"og:site_name":45,"og:description":12},"article",{"robots":77,"canonical":32},"index,follow",{"doc_id":79,"site_id":7},357546,1790461863,{"code":4,"msg":82,"data":83},"success",[84,88,92,96,101,106,111,115,120,123,127],{"id":22,"doc_module":4,"doc_module_name":25,"category_name":85,"show_sort_weight":86,"slug":87},"Story & Novel",90,"story-novel",{"id":26,"doc_module":4,"doc_module_name":25,"category_name":89,"show_sort_weight":90,"slug":91},"Literature",80,"literature",{"id":33,"doc_module":4,"doc_module_name":25,"category_name":93,"show_sort_weight":94,"slug":95},"Exam",70,"exam",{"id":97,"doc_module":4,"doc_module_name":25,"category_name":98,"show_sort_weight":99,"slug":100},5,"Comic",60,"comic",{"id":102,"doc_module":4,"doc_module_name":25,"category_name":103,"show_sort_weight":104,"slug":105},6,"Technology",50,"technology",{"id":107,"doc_module":4,"doc_module_name":25,"category_name":108,"show_sort_weight":109,"slug":110},7,"Healthcare",40,"healthcare",{"id":112,"doc_module":4,"doc_module_name":25,"category_name":29,"show_sort_weight":113,"slug":114},8,30,"research-report",{"id":116,"doc_module":4,"doc_module_name":25,"category_name":117,"show_sort_weight":118,"slug":119},9,"Religion & Spirituality",20,"religion-spirituality",{"id":118,"doc_module":4,"doc_module_name":25,"category_name":121,"show_sort_weight":118,"slug":122},"World Cup","world-cup",{"id":124,"doc_module":4,"doc_module_name":25,"category_name":125,"show_sort_weight":124,"slug":126},10,"Lifestyle","lifestyle",{"id":128,"doc_module":4,"doc_module_name":25,"category_name":129,"show_sort_weight":97,"slug":130},19,"General","general",{"code":4,"msg":82,"data":132},{"doc_id":79,"user_id":133,"nickname":42,"user_avatar":134,"doc_module":4,"category_id":112,"category_name":29,"doc_title":10,"doc_description":12,"doc_content":135,"file_id":136,"file_url":137,"file_type":138,"file_size":139,"view_count":55,"is_deleted":4,"is_public":22,"is_downloadable":22,"audit_status":22,"page_count":128,"language":140,"language_code":8,"site_id":7,"html_lang":8,"table_of_contents":141,"faqs":142,"seo_title":143,"seo_description":12,"update_tm":144,"read_time":145,"preview_page_count":33,"preview_urls":146},5909892332657,"https://ap-avatar.wpscdn.com/davatar_994ba38a5ba835b3df7d355c54d3ed8d","OPEN ACCESS  \nCitation: Helder M, Olsen CM, Pandeya N, Wang H, Whiteman DC, Trzaskowski M, et al.(2026) Automated identification of keratinocyte cancers in pathology reports using large language models. PLOS Digit Health 5(7):  \ne0001547. [https://doi.org/10.1371/journal](https://doi.org/10.1371/journal). pdig.0001547  \nEditor: Laura Sbaffi, The University of Sheffield, UNITED KINGDOM OF GREAT BRITAIN AND NORTHERN IRELAND  \nReceived: April 28, 2026  \nAccepted: June 18, 2026  \nPublished: July 9, 2026  \nCopyright: © 2026 Helder et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.  \nData availability statement: As the fine-tuned QSkin-llama-3 . 1-8b model weights were derived from personal information, these will be made available to researchers upon request and execution of a data use agreement. Requests  \nRESEARCH ARTICLE  \nAutomated identification of keratinocyte cancersin pathology reports using large language models  \nMarloes Helder1,2*, Catherine M. Olsen3,4, Nirmala Pandeya3,5, Huanwei Wang1,2, David C. Whiteman3,5,6, Maciej Trzaskowski1,7,8,9, Matthew H. Law1,2,10*  \n1 Genetics and Skin Cancer, Population Health, QIMR Berghofer, Brisbane, Queensland, Australia,  \n2 School of Biomedical Sciences, Faculty of Health, Queensland University of Technology, Brisbane, Queensland, Australia, 3 Cancer Control, Population Health, QIMR Berghofer, Brisbane, Queensland, Australia, 4 Frazer Institute, Faculty of Health, Medicine and Behavioural Sciences, The University of Queensland, Brisbane, Queensland, Australia, 5 School of Public Health, University of Queensland, Brisbane, Queensland, Australia, 6 School of Public Health, Queensland University of Technology, Brisbane, Queensland, Australia, 7 Institute of Molecular Bioscience, University of Queensland, Brisbane, Queensland, Australia, 8 Genomics, Imaging, and AI Lab, Population Health, QIMR Berghofer, Brisbane, Queensland, Australia, 9 Co-Founder and Managing Director of Profenso, Brisbane, Queensland, Australia, 10 School of Biomedical Sciences, Faculty of Health, Medicine and Behavioural Sciences, University of Queensland, Brisbane, Queensland, Australia  \n* [marloes.helder@qimrb.edu.au](marloes.helder@qimrb.edu.au) (MH); [matthew.law@qimrb.edu.au](matthew.law@qimrb.edu.au) (MHL)  \nAbstract  \nKeratinocyte cancers (KCs) are the most prevalent cancers in white-skinned individuals, yet remain underrepresented in cancer registries because reporting requirements differ greatly across jurisdictions. Manual extraction of KC subtypes from medical reports is labor-intensive and time-consuming, particularly as reports often document multiple co-excised skin lesions. Artificial intelligence offers automated solutions for disease phenotyping from unstructured clinical text. We fine-tuned the open-source large language model Meta-AI (LLaMA) 3. 1-8B-Instruct on 26,179 manually reviewed pathology reports from 10,326 Australian QSkin Sun and health study participants who had histologically confirmed KCs. Independently validation was performed on 217 pathology reports from the Skin Tumors in Allograft Recipients cohort. The model achieved F1-scores above 0.90 for the four KC subtypes of interest: squamous cell carcinoma, basal cell carcinoma, keratoacanthoma, and intraepidermal carcinoma. Frequency-weighted mean F1-scores reached 0.84 (95% confidence interval: 0.843- 0.846) for diagnosis classification and 0.83 (95% confidence interval: 0.826-0.828) for anatomical site. External validation demonstrated robust performance with F1-scores between 0.73-0.86 for the four KCs of interest. Our fine-tuned model QSkin-llama- 3. 1-8b works locally. It accurately classifies lesion counts, diagnoses, and anatomical sites. It processes 24 pathology reports per minute with minimal preprocessing, enabling scalable automated ","cbCaicGuqlxZrZQr","https://ap.wps.com/l/cbCaicGuqlxZrZQr","pdf",1005534,"English","# Abstract\n## Model training and validation\n## Performance metrics and external validation\n## Local deployment and scalability","[{\"question\":\"Why are keratinocyte cancers underrepresented in cancer registries?\",\"answer\":\"Reporting requirements differ greatly across jurisdictions, limiting consistent representation in registries.\"},{\"question\":\"How was the large language model developed in this study?\",\"answer\":\"The authors fine-tuned Meta-AI LLaMA 3.1-8B-Instruct on 26,179 manually reviewed Australian pathology reports with histologically confirmed KCs.\"},{\"question\":\"What performance did the model achieve for keratinocyte cancer subtypes?\",\"answer\":\"The model reached F1-scores above 0.90 for four KC subtypes of interest, with robust external validation showing F1-scores between 0.73 and 0.86.\"}]","Automated identification of keratinocyte cancers in pathology reports using large language models | PDF",1790130320,48,[147,151,155,159],{"page_no":22,"url":148,"width":149,"height":150},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/14379435219c382b8069e5e2258609a4.webp",983,1272,{"page_no":26,"url":152,"width":153,"height":154},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/133347c448312337a6ecb96dcc434aa1.webp",982,1270,{"page_no":30,"url":156,"width":157,"height":158},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/351e364e42540ff5f8cf5e55bfc70130.webp",981,1269,{"page_no":33,"url":160,"width":161,"height":162},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/c2a227cba580f1fc2db9bccac1dc0574.webp",980,1268]