{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,6]],"date-time":"2026-11-06T11:39:28Z","timestamp":1793965168660,"version":"4.8.0"},"reference-count":41,"publisher":"Elsevier BV","issue":"12","license":[{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2025,10,27]],"date-time":"2025-10-27T00:00:00Z","timestamp":1761523200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["W2441025"],"award-info":[{"award-number":["W2441025"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001659","name":"German Research Foundation","doi-asserted-by":"publisher","award":["SFB 1470"],"award-info":[{"award-number":["SFB 1470"]}],"id":[{"id":"10.13039\/501100001659","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["cell.com","clinicalkey.com","clinicalkey.com.au","clinicalkey.es","clinicalkey.fr","clinicalkey.jp","elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Cell Reports Medicine"],"published-print":{"date-parts":[[2025,12]]},"DOI":"10.1016\/j.xcrm.2025.102465","type":"journal-article","created":{"date-parts":[[2025,11,21]],"date-time":"2025-11-21T21:13:51Z","timestamp":1763759631000},"page":"102465","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":5,"title":["Multi-center benchmarking of large language models for clinical decision support in lung cancer screening"],"prefix":"10.1016","volume":"6","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-2844-8036","authenticated-orcid":false,"given":"Zhiyun","family":"Duan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xu","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rong","family":"Lu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenyi","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huaning","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yucai","family":"Geng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Natsuki","family":"Takahashi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ying","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qingle","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yang","family":"Song","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongbo","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Han","family":"Tang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fei","family":"Lan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0034-4036","authenticated-orcid":false,"given":"Roland","family":"Eils","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lijie","family":"Tan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.xcrm.2025.102465_bib1","first-page":"209","article-title":"Global Cancer Statistics 2020: GLOBOCAN Estimates of Incidence and Mortality Worldwide for 36 Cancers in 185 Countries","volume":"71","author":"Sung","year":"2021","journal-title":"CA Cancer J. Clin."},{"key":"10.1016\/j.xcrm.2025.102465_bib2","doi-asserted-by":"crossref","first-page":"535","DOI":"10.1016\/S0140-6736(21)00312-3","article-title":"Lung cancer","volume":"398","author":"Thai","year":"2021","journal-title":"Lancet"},{"key":"10.1016\/j.xcrm.2025.102465_bib3","doi-asserted-by":"crossref","DOI":"10.1001\/jamanetworkopen.2023.47176","article-title":"Opportunistic Screening With Low-Dose Computed Tomography and Lung Cancer Mortality in China","volume":"6","author":"Wang","year":"2023","journal-title":"JAMA Netw. Open"},{"key":"10.1016\/j.xcrm.2025.102465_bib4","doi-asserted-by":"crossref","first-page":"395","DOI":"10.1056\/NEJMoa1102873","article-title":"Reduced lung-cancer mortality with low-dose computed tomographic screening","volume":"365","author":"Aberle","year":"2011","journal-title":"N. Engl. J. Med."},{"key":"10.1016\/j.xcrm.2025.102465_bib5","first-page":"50","article-title":"Screening for lung cancer: 2023 guideline update from the American Cancer Society","volume":"74","author":"Wolf","year":"2024","journal-title":"CA Cancer J. Clin."},{"key":"10.1016\/j.xcrm.2025.102465_bib6","doi-asserted-by":"crossref","first-page":"962","DOI":"10.1001\/jama.2021.1117","article-title":"Screening for Lung Cancer: US Preventive Services Task Force Recommendation Statement","volume":"325","author":"Krist","year":"2021","journal-title":"JAMA"},{"key":"10.1016\/j.xcrm.2025.102465_bib7","doi-asserted-by":"crossref","first-page":"503","DOI":"10.1056\/NEJMoa1911793","article-title":"Reduced Lung-Cancer Mortality with Volume CT Screening in a Randomized Trial","volume":"382","author":"de Koning","year":"2020","journal-title":"N. Engl. J. Med."},{"key":"10.1016\/j.xcrm.2025.102465_bib8","doi-asserted-by":"crossref","first-page":"1930","DOI":"10.1038\/s41591-023-02448-8","article-title":"Large language models in medicine","volume":"29","author":"Thirunavukarasu","year":"2023","journal-title":"Nat. Med."},{"key":"10.1016\/j.xcrm.2025.102465_bib9","doi-asserted-by":"crossref","first-page":"3940","DOI":"10.1097\/JS9.0000000000000686","article-title":"Auxiliary use of ChatGPT in surgical diagnosis and treatment","volume":"109","author":"Au","year":"2023","journal-title":"Int. J. Surg."},{"key":"10.1016\/j.xcrm.2025.102465_bib10","doi-asserted-by":"crossref","first-page":"405","DOI":"10.1016\/S1473-3099(23)00113-5","article-title":"ChatGPT and antimicrobial advice: the end of the consulting infection doctor?","volume":"23","author":"Howard","year":"2023","journal-title":"Lancet Infect. Dis."},{"key":"10.1016\/j.xcrm.2025.102465_bib11","article-title":"Large language models enable tumor-type classification and localization of cancers of unknown primary from genomic data","volume":"6","author":"Liu","year":"2025","journal-title":"Cell Rep. Med."},{"key":"10.1016\/j.xcrm.2025.102465_bib12","doi-asserted-by":"crossref","first-page":"932","DOI":"10.1038\/s41591-024-03416-6","article-title":"A generalist medical language model for disease diagnosis assistance","volume":"31","author":"Liu","year":"2025","journal-title":"Nat. Med."},{"key":"10.1016\/j.xcrm.2025.102465_bib13","doi-asserted-by":"crossref","DOI":"10.1148\/radiol.230922","article-title":"How AI Responds to Common Lung Cancer Questions: ChatGPT vs Google Bard","volume":"307","author":"Rahsepar","year":"2023","journal-title":"Radiology"},{"key":"10.1016\/j.xcrm.2025.102465_bib14","doi-asserted-by":"crossref","DOI":"10.1148\/radiol.231362","article-title":"Potential of ChatGPT and GPT-4 for Data Mining of Free-Text CT Reports on Lung Cancer","volume":"308","author":"Fink","year":"2023","journal-title":"Radiology"},{"key":"10.1016\/j.xcrm.2025.102465_bib15","article-title":"Assessments of lung nodules by an artificial intelligence chatbot using longitudinal CT images","volume":"6","author":"Mao","year":"2025","journal-title":"Cell Rep. Med."},{"key":"10.1016\/j.xcrm.2025.102465_bib16","doi-asserted-by":"crossref","first-page":"2546","DOI":"10.1038\/s41591-025-03727-2","article-title":"Benchmark evaluation of DeepSeek large language models in clinical decision-making","volume":"31","author":"Sandmann","year":"2025","journal-title":"Nat. Med."},{"key":"10.1016\/j.xcrm.2025.102465_bib17","doi-asserted-by":"crossref","first-page":"2550","DOI":"10.1038\/s41591-025-03726-3","article-title":"Comparative benchmarking of the DeepSeek large language model on medical tasks and clinical reasoning","volume":"31","author":"Tordjman","year":"2025","journal-title":"Nat. Med."},{"key":"10.1016\/j.xcrm.2025.102465_bib18","doi-asserted-by":"crossref","first-page":"e441","DOI":"10.1016\/S2589-7500(24)00111-0","article-title":"From text to treatment: the crucial role of validation for generative large language models in health care","volume":"6","author":"de Hond","year":"2024","journal-title":"Lancet Digit. Health"},{"key":"10.1016\/j.xcrm.2025.102465_bib19","doi-asserted-by":"crossref","first-page":"159","DOI":"10.2307\/2529310","article-title":"The measurement of observer agreement for categorical data","volume":"33","author":"Landis","year":"1977","journal-title":"Biometrics"},{"key":"10.1016\/j.xcrm.2025.102465_bib20","article-title":"Scientists flock to DeepSeek: how they\u2019re using the blockbuster AI model","author":"Gibney","year":"2025","journal-title":"Nature"},{"key":"10.1016\/j.xcrm.2025.102465_bib21","doi-asserted-by":"crossref","DOI":"10.1001\/jamanetworkopen.2023.43689","article-title":"Leveraging Large Language Models for Decision Support in Personalized Oncology","volume":"6","author":"Benary","year":"2023","journal-title":"JAMA Netw. Open"},{"key":"10.1016\/j.xcrm.2025.102465_bib22","doi-asserted-by":"crossref","DOI":"10.2196\/54706","article-title":"Physician Versus Large Language Model Chatbot Responses to Web-Based Questions From Autistic Patients in Chinese: Cross-Sectional Comparative Analysis","volume":"26","author":"He","year":"2024","journal-title":"J. Med. Internet Res."},{"key":"10.1016\/j.xcrm.2025.102465_bib23","doi-asserted-by":"crossref","first-page":"371","DOI":"10.1001\/jamaophthalmol.2023.6917","article-title":"Assessment of a Large Language Model\u2019s Responses to Questions and Cases About Glaucoma and Retina Management","volume":"142","author":"Huang","year":"2024","journal-title":"JAMA Ophthalmol."},{"key":"10.1016\/j.xcrm.2025.102465_bib24","doi-asserted-by":"crossref","DOI":"10.1148\/radiol.240528","article-title":"Best Practices for Large Language Models in Radiology","volume":"315","author":"Bluethgen","year":"2025","journal-title":"Radiology"},{"key":"10.1016\/j.xcrm.2025.102465_bib25","doi-asserted-by":"crossref","DOI":"10.1148\/radiol.242575","article-title":"Generative Large Language Models Trained for Detecting Errors in Radiology Reports","volume":"315","author":"Sun","year":"2025","journal-title":"Radiology"},{"key":"10.1016\/j.xcrm.2025.102465_bib26","doi-asserted-by":"crossref","DOI":"10.1148\/radiol.242134","article-title":"Leveraging Large Language Models to Generate Clinical Histories for Oncologic Imaging Requisitions","volume":"314","author":"Bhayana","year":"2025","journal-title":"Radiology"},{"key":"10.1016\/j.xcrm.2025.102465_bib27","doi-asserted-by":"crossref","DOI":"10.2196\/65547","article-title":"Large Language Models in Summarizing Radiology Report Impressions for Lung Cancer in Chinese: Evaluation Study","volume":"27","author":"Hu","year":"2025","journal-title":"J. Med. Internet Res."},{"key":"10.1016\/j.xcrm.2025.102465_bib28","doi-asserted-by":"crossref","first-page":"41","DOI":"10.1038\/s41746-024-01029-4","article-title":"Prompt engineering in consistency and reliability with the evidence-based guideline for LLMs","volume":"7","author":"Wang","year":"2024","journal-title":"npj Digit. Med."},{"key":"10.1016\/j.xcrm.2025.102465_bib29","doi-asserted-by":"crossref","first-page":"1149","DOI":"10.3758\/BRM.41.4.1149","article-title":"Statistical power analyses using G\u2217Power 3.1: Tests for correlation and regression analyses","volume":"41","author":"Faul","year":"2009","journal-title":"Behav. Res. Methods"},{"key":"10.1016\/j.xcrm.2025.102465_bib30","doi-asserted-by":"crossref","first-page":"1016","DOI":"10.1001\/jama.2021.1799","article-title":"Screening for Lung Cancer","volume":"325","author":"Jin","year":"2021","journal-title":"JAMA"},{"key":"10.1016\/j.xcrm.2025.102465_bib31","doi-asserted-by":"crossref","DOI":"10.1148\/radiol.241073","article-title":"Open-Source Large Language Models in Radiology: A Review and Tutorial for Practical Research and Clinical Deployment","volume":"314","author":"Savage","year":"2025","journal-title":"Radiology"},{"key":"10.1016\/j.xcrm.2025.102465_bib32","doi-asserted-by":"crossref","first-page":"956","DOI":"10.1001\/jamaoncol.2024.0836","article-title":"Physician and Artificial Intelligence Chatbot Responses to Cancer Questions From Social Media","volume":"10","author":"Chen","year":"2024","journal-title":"JAMA Oncol."},{"key":"10.1016\/j.xcrm.2025.102465_bib33","article-title":"GPT versus Resident Physicians \u2014 A Benchmark Based on Official Board Scores","volume":"1","author":"Katz","year":"2024","journal-title":"NEJM"},{"key":"10.1016\/j.xcrm.2025.102465_bib34","doi-asserted-by":"crossref","first-page":"8236","DOI":"10.1038\/s41467-024-52415-1","article-title":"Evaluating the use of large language models to provide clinical recommendations in the Emergency Department","volume":"15","author":"Williams","year":"2024","journal-title":"Nat. Commun."},{"key":"10.1016\/j.xcrm.2025.102465_bib35","doi-asserted-by":"crossref","DOI":"10.1148\/radiol.232715","article-title":"Evaluation of Reliability, Repeatability, Robustness, and Confidence of GPT-3.5 and GPT-4 on a Radiology Board-style Examination","volume":"311","author":"Krishna","year":"2024","journal-title":"Radiology"},{"key":"10.1016\/j.xcrm.2025.102465_bib36","doi-asserted-by":"crossref","first-page":"77","DOI":"10.1038\/s41591-024-03328-5","article-title":"An evaluation framework for clinical use of large language models in patient interaction tasks","volume":"31","author":"Johri","year":"2025","journal-title":"Nat. Med."},{"key":"10.1016\/j.xcrm.2025.102465_bib37","doi-asserted-by":"crossref","first-page":"1399","DOI":"10.1007\/s11604-024-01634-z","article-title":"Diagnostic performances of Claude 3 Opus and Claude 3.5 Sonnet from patient history and key images in Radiology\u2019s \u201cDiagnosis Please\u201d cases","volume":"42","author":"Kurokawa","year":"2024","journal-title":"Jpn. J. Radiol."},{"key":"10.1016\/j.xcrm.2025.102465_bib38","doi-asserted-by":"crossref","DOI":"10.1001\/jamanetworkopen.2023.30320","article-title":"Comparison of Ophthalmologist and Large Language Model Chatbot Responses to Online Patient Eye Care Questions","volume":"6","author":"Bernstein","year":"2023","journal-title":"JAMA Netw. Open"},{"key":"10.1016\/j.xcrm.2025.102465_bib39","doi-asserted-by":"crossref","DOI":"10.2196\/55318","article-title":"An Empirical Evaluation of Prompting Strategies for Large Language Models in Zero-Shot Clinical Natural Language Processing: Algorithm Development and Validation Study","volume":"12","author":"Sivarajkumar","year":"2024","journal-title":"JMIR Med. Inform."},{"key":"10.1016\/j.xcrm.2025.102465_bib40","doi-asserted-by":"crossref","DOI":"10.2196\/74142","article-title":"Evaluating the Reasoning Capabilities of Large Language Models for Medical Coding and Hospital Readmission Risk Stratification: Zero-Shot Prompting Approach","volume":"27","author":"Naliyatthaliyazchayil","year":"2025","journal-title":"J. Med. Internet Res."},{"key":"10.1016\/j.xcrm.2025.102465_bib41","doi-asserted-by":"crossref","DOI":"10.1001\/jamanetworkopen.2024.22275","article-title":"Readability and Information Quality in Cancer Information From a Free vs Paid Chatbot","volume":"7","author":"Musheyev","year":"2024","journal-title":"JAMA Netw. Open"}],"container-title":["Cell Reports Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S2666379125005385?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S2666379125005385?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T15:50:45Z","timestamp":1790265045000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S2666379125005385"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12]]},"references-count":41,"journal-issue":{"issue":"12","published-print":{"date-parts":[[2025,12]]}},"alternative-id":["S2666379125005385"],"URL":"https:\/\/doi.org\/10.1016\/j.xcrm.2025.102465","relation":{},"ISSN":["2666-3791"],"issn-type":[{"value":"2666-3791","type":"print"}],"subject":[],"published":{"date-parts":[[2025,12]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Multi-center benchmarking of large language models for clinical decision support in lung cancer screening","name":"articletitle","label":"Article Title"},{"value":"Cell Reports Medicine","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.xcrm.2025.102465","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2025 The Authors. Published by Elsevier Inc.","name":"copyright","label":"Copyright"}],"article-number":"102465"}}