{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T18:19:25Z","timestamp":1783621165638,"version":"3.55.0"},"reference-count":28,"publisher":"Public Library of Science (PLoS)","issue":"7","license":[{"start":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T00:00:00Z","timestamp":1783555200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100013103","name":"QIMR Berghofer Medical Research Institute","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100013103","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001793","name":"Queensland University of Technology","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001793","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000925","name":"National Health and Medical Research Council","doi-asserted-by":"publisher","award":["2026567"],"award-info":[{"award-number":["2026567"]}],"id":[{"id":"10.13039\/501100000925","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000925","name":"National Health and Medical Research Council","doi-asserted-by":"publisher","award":["2030931"],"award-info":[{"award-number":["2030931"]}],"id":[{"id":"10.13039\/501100000925","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000925","name":"National Health and Medical Research Council","doi-asserted-by":"publisher","award":["2034568"],"award-info":[{"award-number":["2034568"]}],"id":[{"id":"10.13039\/501100000925","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100021260","name":"Australian Skin and Skin Cancer Research Centre","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100021260","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000925","name":"National Health and Medical Research Council","doi-asserted-by":"publisher","award":["APP1185416"],"award-info":[{"award-number":["APP1185416"]}],"id":[{"id":"10.13039\/501100000925","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000925","name":"National Health and Medical Research Council","doi-asserted-by":"publisher","award":["552429"],"award-info":[{"award-number":["552429"]}],"id":[{"id":"10.13039\/501100000925","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["www.plosdigitalhealth.org"],"crossmark-restriction":false},"short-container-title":["PLOS Digit Health"],"abstract":"<jats:p>Keratinocyte 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 disease phenotyping for large health datasets.<\/jats:p>","DOI":"10.1371\/journal.pdig.0001547","type":"journal-article","created":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T17:44:06Z","timestamp":1783619046000},"page":"e0001547","update-policy":"https:\/\/doi.org\/10.1371\/journal.pdig.corrections_policy","source":"Crossref","is-referenced-by-count":0,"title":["Automated identification of keratinocyte cancers in pathology reports using large language models"],"prefix":"10.1371","volume":"5","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-9323-7657","authenticated-orcid":true,"given":"Marloes","family":"Helder","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Catherine M.","family":"Olsen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nirmala","family":"Pandeya","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huanwei","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"David C.","family":"Whiteman","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Maciej","family":"Trzaskowski","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4303-8821","authenticated-orcid":true,"given":"Matthew H.","family":"Law","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2026,7,9]]},"reference":[{"key":"pdig.0001547.ref001","first-page":"120","article-title":"Epidemiology of Skin Cancer.","author":"U Leiter","year":"2014","journal-title":"Sunlight, Vitamin D and Skin Cancer. New York, NY: Springer"},{"issue":"1","key":"pdig.0001547.ref002","doi-asserted-by":"crossref","first-page":"3212203","DOI":"10.17061\/phrp3212203","article-title":"Keratinocyte cancer incidence in Australia: a review of population-based incidence trends and estimates of lifetime risk","volume":"32","author":"CM Olsen","year":"2022","journal-title":"Public Health Res Pract"},{"issue":"4","key":"pdig.0001547.ref003","doi-asserted-by":"crossref","first-page":"329","DOI":"10.1111\/1753-6405.12806","article-title":"Keratinocyte cancers in South Australia: incidence, geographical variability and service trends","volume":"42","author":"P Adelson","year":"2018","journal-title":"Aust N Z J Public Health"},{"issue":"7","key":"pdig.0001547.ref004","doi-asserted-by":"crossref","first-page":"1382","DOI":"10.1016\/j.jid.2016.02.804","article-title":"Prevalence of Skin Cancer and Related Skin Tumors in High-Risk Kidney and Liver Transplant Recipients in Queensland, Australia","volume":"136","author":"MR Iannacone","year":"2016","journal-title":"J Invest Dermatol"},{"key":"pdig.0001547.ref005","author":"Australian Bureau of Statistics"},{"key":"pdig.0001547.ref006","doi-asserted-by":"crossref","first-page":"18","DOI":"10.1016\/j.ejca.2021.04.029","article-title":"Epidemiology of cutaneous melanoma and keratinocyte cancer in white populations 1943-2036","volume":"152","author":"C Garbe","year":"2021","journal-title":"Eur J Cancer"},{"key":"pdig.0001547.ref007","doi-asserted-by":"crossref","DOI":"10.1071\/PU24008","article-title":"Beyond the blind spot: considering the benefits of comprehensive skin cancer surveillance","volume":"35","author":"C Olsen","year":"2025","journal-title":"Public Health Res Pract"},{"issue":"1","key":"pdig.0001547.ref008","doi-asserted-by":"crossref","first-page":"159","DOI":"10.1186\/s12913-025-13965-2","article-title":"Assessing skin cancer histopathology reporting against minimum dataset standards in a low-resource setting","volume":"26","author":"S Taha","year":"2025","journal-title":"BMC Health Serv Res"},{"issue":"1","key":"pdig.0001547.ref009","doi-asserted-by":"crossref","first-page":"86","DOI":"10.1111\/1753-6405.12738","article-title":"Multiplicity of skin cancers in Queensland and their cost burden to government and patients","volume":"42","author":"LG Gordon","year":"2018","journal-title":"Aust N Z J Public Health"},{"issue":"3","key":"pdig.0001547.ref010","doi-asserted-by":"crossref","first-page":"514","DOI":"10.3390\/diagnostics11030514","article-title":"Artificial Intelligence in Colorectal Cancer Diagnosis Using Clinical Data: Non-Invasive Approach","volume":"11","author":"N Lorenzovici","year":"2021","journal-title":"Diagnostics (Basel)"},{"issue":"1","key":"pdig.0001547.ref011","doi-asserted-by":"crossref","first-page":"43","DOI":"10.1186\/s13000-024-01464-7","article-title":"Challenges and barriers of using large language models (LLM) such as ChatGPT for diagnostic medicine with a focus on digital pathology - a recent scoping review","volume":"19","author":"E Ullah","year":"2024","journal-title":"Diagn Pathol"},{"key":"pdig.0001547.ref012","doi-asserted-by":"crossref","first-page":"711","DOI":"10.1200\/CCI.19.00152","article-title":"Web Application for the Automated Extraction of Diagnosis and Site From Pathology Reports for Keratinocyte Cancers","volume":"4","author":"BS Thompson","year":"2020","journal-title":"JCO Clin Cancer Inform"},{"key":"pdig.0001547.ref013","doi-asserted-by":"crossref","DOI":"10.2196\/65984","article-title":"Large Language Model Applications for Health Information Extraction in Oncology: Scoping Review","volume":"11","author":"D Chen","year":"2025","journal-title":"JMIR Cancer"},{"key":"pdig.0001547.ref014","doi-asserted-by":"crossref","first-page":"110621","DOI":"10.1016\/j.compbiomed.2025.110621","article-title":"Extracting critical clinical indicators and survival prediction of lung cancer from pathology reports using large language models","volume":"195","author":"Y-C Chang","year":"2025","journal-title":"Comput Biol Med"},{"key":"pdig.0001547.ref015","doi-asserted-by":"crossref","DOI":"10.2196\/71176","article-title":"Language Models for Multilabel Document Classification of Surgical Concepts in Exploratory Laparotomy Operative Notes: Algorithm Development Study","volume":"13","author":"JA Balch","year":"2025","journal-title":"JMIR Med Inform"},{"key":"pdig.0001547.ref016","article-title":"DRG-LLaMA: Tuning LLaMA Model to Predict Diagnosis-Related Group for Hospitalized Patients","author":"H Wang","year":"2023","journal-title":"arXiv"},{"key":"pdig.0001547.ref017","doi-asserted-by":"crossref","DOI":"10.1177\/17562848251328577","article-title":"Utilizing large language models for gastroenterology research: a conceptual framework","volume":"18","author":"P Berry","year":"2025","journal-title":"Ther Adv Gastroenterol"},{"issue":"1","key":"pdig.0001547.ref018","doi-asserted-by":"crossref","first-page":"27300","DOI":"10.1038\/s41598-025-10709-4","article-title":"Cancer type, stage and prognosis assessment from pathology reports using LLMs","volume":"15","author":"R Saluja","year":"2025","journal-title":"Sci Rep"},{"key":"pdig.0001547.ref019","article-title":"Open-Source Hybrid Large Language Model Integrated System for Extraction of Breast Cancer Treatment Pathway From Free-Text Clinical Notes","volume":"9","author":"A Tariq","year":"2025","journal-title":"JCO Clin Cancer Inform"},{"issue":"4","key":"pdig.0001547.ref020","doi-asserted-by":"crossref","first-page":"142","DOI":"10.3390\/ai7040142","article-title":"Mapping the LLM Landscape: A Cross-Family Survey of Architectures, Alignment Methods, and Benchmark Performance","volume":"7","author":"D Bhati","year":"2026","journal-title":"AI"},{"issue":"4","key":"pdig.0001547.ref021","doi-asserted-by":"crossref","first-page":"929","DOI":"10.1093\/ije\/dys107","article-title":"Cohort profile: the QSkin Sun and Health Study","volume":"41","author":"CM Olsen","year":"2012","journal-title":"Int J Epidemiol"},{"key":"pdig.0001547.ref022","doi-asserted-by":"crossref","first-page":"1179550619865278","DOI":"10.1177\/1179550619865278","article-title":"Nonmelanoma Facial Skin Cancer: A Review of Diagnostic Strategies, Surgical Treatment, and Reconstructive Techniques","volume":"12","author":"I Badash","year":"2019","journal-title":"Clin Med Insights Ear Nose Throat"},{"issue":"8","key":"pdig.0001547.ref023","doi-asserted-by":"crossref","first-page":"1700","DOI":"10.1016\/j.jid.2017.03.027","article-title":"Cigarette Smoking and the Risks of Basal Cell Carcinoma and Squamous Cell Carcinoma","volume":"137","author":"JC Dusingize","year":"2017","journal-title":"Journal of Investigative Dermatology"},{"key":"pdig.0001547.ref024","article-title":"The Llama 3 Herd of Models","author":"A Grattafiori","year":"2024","journal-title":"arXiv"},{"issue":"3","key":"pdig.0001547.ref025","doi-asserted-by":"crossref","first-page":"545","DOI":"10.1093\/jamia\/ocaf002","article-title":"RAMIE: retrieval-augmented multi-task information extraction with large language models on dietary supplements","volume":"32","author":"Z Zhan","year":"2025","journal-title":"J Am Med Inform Assoc"},{"key":"pdig.0001547.ref026","author":"EJ Hu","year":"2021"},{"key":"pdig.0001547.ref027","article-title":"Comparing Retrieval-Augmentation and Parameter-Efficient Fine-Tuning for Privacy-Preserving Personalization of Large Language Models","author":"A Salemi","year":"2025","journal-title":"arXiv"},{"key":"pdig.0001547.ref028","doi-asserted-by":"crossref","first-page":"106022","DOI":"10.1016\/j.ijmedinf.2025.106022","article-title":"From text to data: Open-source large language models in extracting cancer related medical attributes from German pathology reports","volume":"203","author":"S Bartels","year":"2025","journal-title":"Int J Med Inform"}],"container-title":["PLOS Digital Health"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pdig.0001547","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T17:44:12Z","timestamp":1783619052000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pdig.0001547"}},"subtitle":[],"editor":[{"given":"Laura","family":"Sbaffi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,7,9]]},"references-count":28,"journal-issue":{"issue":"7","published-online":{"date-parts":[[2026,7,9]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pdig.0001547","relation":{},"ISSN":["2767-3170"],"issn-type":[{"value":"2767-3170","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,9]]}}}