{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,18]],"date-time":"2026-11-18T09:05:15Z","timestamp":1794992715973,"version":"4.9.1"},"reference-count":54,"publisher":"BMJ","issue":"4","funder":[{"DOI":"10.13039\/501100000024","name":"Canadian Institutes of Health Research","doi-asserted-by":"publisher","award":["FDN 167273"],"award-info":[{"award-number":["FDN 167273"]}],"id":[{"id":"10.13039\/501100000024","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["U19 CA203654"],"award-info":[{"award-number":["U19 CA203654"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["bmj.com"],"crossmark-restriction":true},"short-container-title":["Thorax"],"accepted":{"date-parts":[[2023,12,4]]},"published-print":{"date-parts":[[2024,4]]},"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Low-dose CT screening can reduce lung cancer-related mortality. However, most screen-detected pulmonary abnormalities do not develop into cancer and it often remains challenging to identify malignant nodules, particularly among indeterminate nodules. We aimed to develop and assess prediction models based on radiological features to discriminate between benign and malignant pulmonary lesions detected on a baseline screen.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>Using four international lung cancer screening studies, we extracted 2060 radiomic features for each of 16\u2009797 nodules (513 malignant) among 6865 participants. After filtering out low-quality radiomic features, 642 radiomic and 9 epidemiological features remained for model development. We used cross-validation and grid search to assess three machine learning (ML) models (eXtreme Gradient Boosted Trees, random forest, least absolute shrinkage and selection operator (LASSO)) for their ability to accurately predict risk of malignancy for pulmonary nodules. We report model performance based on the area under the curve (AUC) and calibration metrics in the held-out test set.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The LASSO model yielded the best predictive performance in cross-validation and was fit in the full training set based on optimised hyperparameters. Our radiomics model had a test-set AUC of 0.93 (95% CI 0.90 to 0.96) and outperformed the established Pan-Canadian Early Detection of Lung Cancer model (AUC 0.87, 95%\u2009CI 0.85 to 0.89) for nodule assessment. Our model performed well among both solid (AUC 0.93, 95%\u2009CI 0.89 to 0.97) and subsolid nodules (AUC 0.91, 95%\u2009CI 0.85 to 0.95).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>We developed highly accurate ML models based on radiomic and epidemiological features from four international lung cancer screening studies that may be suitable for assessing indeterminate screen-detected pulmonary nodules for risk of malignancy.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1136\/thorax-2023-220226","type":"journal-article","created":{"date-parts":[[2024,1,10]],"date-time":"2024-01-10T01:14:40Z","timestamp":1704849280000},"page":"307-315","update-policy":"https:\/\/doi.org\/10.1136\/crossmarkpolicy","source":"Crossref","is-referenced-by-count":109,"title":["Radiomics analysis to predict pulmonary nodule malignancy using machine learning approaches"],"prefix":"10.1136","volume":"79","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8730-3511","authenticated-orcid":false,"given":"Matthew T","family":"Warkentin","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hamad","family":"Al-Sawaihey","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Stephen","family":"Lam","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Geoffrey","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Brenda","family":"Diergaarde","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jian-Min","family":"Yuan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2635-7468","authenticated-orcid":false,"given":"David O","family":"Wilson","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sukhinder","family":"Atkar-Khattra","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Benjamin","family":"Grant","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yonathan","family":"Brhane","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Elham","family":"Khodayari-Moez","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kiera R","family":"Murison","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Martin C","family":"Tammemagi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kieran R","family":"Campbell","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4486-7496","authenticated-orcid":false,"given":"Rayjean J","family":"Hung","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"239","published-online":{"date-parts":[[2024,1,9]]},"reference":[{"key":"2025042101250973000_79.4.307.1","doi-asserted-by":"publisher","DOI":"10.3322\/caac.21660"},{"key":"2025042101250973000_79.4.307.2","unstructured":"Howlader N , Noone A , Krapcho M , et al . SEER cancer Statistics review, 1975-2014, National Cancer Institute. Bethesda, MD. 2017:1\u201312."},{"key":"2025042101250973000_79.4.307.3","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMoa1911793"},{"key":"2025042101250973000_79.4.307.4","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMoa1102873"},{"key":"2025042101250973000_79.4.307.5","doi-asserted-by":"publisher","DOI":"10.1016\/j.jtho.2019.05.044"},{"key":"2025042101250973000_79.4.307.6","doi-asserted-by":"crossref","DOI":"10.1093\/annonc\/mdz169","article-title":"Prolonged lung cancer screening reduced 10-year mortality in the MILD trial: new confirmation of lung cancer screening efficacy","volume":"30","author":"Pastorino","year":"2019","journal-title":"Ann Oncol"},{"key":"2025042101250973000_79.4.307.7","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2012.5521"},{"key":"2025042101250973000_79.4.307.8","unstructured":"American College of Radiology Committee on Lung-RADS . Lung-RADS assessment categories Version1.1. n.d. Available: https:\/\/www.acr.org\/-\/media\/ACR\/Files\/RADS\/Lung-RADS\/LungRADSAssessmentCategoriesv1-1.pdf"},{"key":"2025042101250973000_79.4.307.9","unstructured":"I-ELCAP protocol. n.d. Available: https:\/\/www.ielcap.org\/sites\/default\/files\/I-ELCAP-protocol-summary.pdf"},{"key":"2025042101250973000_79.4.307.10","doi-asserted-by":"publisher","DOI":"10.1016\/j.lungcan.2006.08.006"},{"key":"2025042101250973000_79.4.307.11","doi-asserted-by":"publisher","DOI":"10.1016\/S1470-2045(14)70389-4"},{"key":"2025042101250973000_79.4.307.12","doi-asserted-by":"publisher","DOI":"10.1016\/S1470-2045(17)30861-6"},{"key":"2025042101250973000_79.4.307.13","doi-asserted-by":"publisher","DOI":"10.1136\/thoraxjnl-2015-207221"},{"key":"2025042101250973000_79.4.307.14","doi-asserted-by":"publisher","DOI":"10.1136\/thoraxjnl-2015-207221"},{"key":"2025042101250973000_79.4.307.15","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.14132950"},{"key":"2025042101250973000_79.4.307.16","unstructured":"NCCN practice guidelines in oncology lung cancer screening guideline version 4.2019, Available: https:\/\/www.nccn.org\/professionals\/physician_gls\/default.aspx"},{"key":"2025042101250973000_79.4.307.17","first-page":"67","article-title":"Guidelines for low-dose spiral CT screening of lung cancer in China (2018 edition)","volume":"21","author":"Zhou","year":"2018","journal-title":"Zhongguo Fei Ai Za Zhi"},{"key":"2025042101250973000_79.4.307.18","doi-asserted-by":"publisher","DOI":"10.1148\/rg.2018180017"},{"key":"2025042101250973000_79.4.307.19","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.2017161659"},{"key":"2025042101250973000_79.4.307.20","doi-asserted-by":"crossref","DOI":"10.1136\/bmj.g2253","article-title":"Screening for lung cancer using low dose computed tomography","volume":"348","author":"Tammemagi","year":"2014","journal-title":"BMJ"},{"key":"2025042101250973000_79.4.307.21","doi-asserted-by":"crossref","first-page":"503","DOI":"10.1513\/AnnalsATS.201902-102OC","article-title":"Protocol and rationale for the International lung screening trial","volume":"17","author":"Lim","year":"2020","journal-title":"Annals ATS"},{"key":"2025042101250973000_79.4.307.22","unstructured":"Kakinuma R , Ashizawa K , Kusunoki Y , et al . n.d. The pulmonary nodules management committee of the Japanese society of CT screening. guidelines for the management of pulmonary nodules detected by low-dose CT lung cancer screening version 3."},{"key":"2025042101250973000_79.4.307.23","doi-asserted-by":"publisher","DOI":"10.1016\/j.lungcan.2020.07.007"},{"key":"2025042101250973000_79.4.307.24","doi-asserted-by":"crossref","first-page":"3296","DOI":"10.21037\/jtd.2020.03.68","article-title":"Approaches to lung Nodule risk assessment: clinician intuition versus prediction models","volume":"12","author":"Fox","year":"2020","journal-title":"J Thorac Dis"},{"key":"2025042101250973000_79.4.307.25","doi-asserted-by":"publisher","DOI":"10.4103\/atm.ATM_110_19"},{"key":"2025042101250973000_79.4.307.26","doi-asserted-by":"publisher","DOI":"10.1158\/0008-5472.CAN-17-0339"},{"key":"2025042101250973000_79.4.307.27","doi-asserted-by":"publisher","DOI":"10.1038\/s41568-018-0016-5"},{"key":"2025042101250973000_79.4.307.28","doi-asserted-by":"crossref","first-page":"916","DOI":"10.1016\/j.ccell.2021.04.002","article-title":"Artificial intelligence for clinical oncology","volume":"39","author":"Kann","year":"2021","journal-title":"Cancer Cell"},{"key":"2025042101250973000_79.4.307.29","doi-asserted-by":"publisher","DOI":"10.1016\/S1470-2045(17)30579-1"},{"key":"2025042101250973000_79.4.307.30","first-page":"225","article-title":"Lung cancer screening with low-dose computed tomography: Canadian experience","volume":"58","author":"Roberts","year":"2007","journal-title":"Can Assoc Radiol J"},{"key":"2025042101250973000_79.4.307.31","doi-asserted-by":"publisher","DOI":"10.1016\/j.lungcan.2009.03.030"},{"key":"2025042101250973000_79.4.307.32","doi-asserted-by":"publisher","DOI":"10.1164\/rccm.200802-336OC"},{"key":"2025042101250973000_79.4.307.33","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMoa1211776"},{"key":"2025042101250973000_79.4.307.34","doi-asserted-by":"publisher","DOI":"10.1016\/j.mri.2012.05.001"},{"key":"2025042101250973000_79.4.307.35","unstructured":"San Jose Estepar R , Ross JC , Harmouche R , et al . Chest imaging platform: an open-source library and workstation for quantitative chest imaging. In: C66 Lung imaging II: New probes and emerging technologies. American Thoracic Society, 2015: A4975\u20135."},{"key":"2025042101250973000_79.4.307.36","doi-asserted-by":"crossref","first-page":"15256","DOI":"10.1364\/OE.18.015256","article-title":"An open-source Toolkit for the volumetric measurement of CT lung lesions","volume":"18","author":"Krishnan","year":"2010","journal-title":"Opt Express"},{"key":"2025042101250973000_79.4.307.37","doi-asserted-by":"publisher","DOI":"10.2307\/1268522"},{"key":"2025042101250973000_79.4.307.38","unstructured":"Van G , Drake FL . Python 3 reference manual. Scotts Valley, CA: CreateSpace, 2009."},{"key":"2025042101250973000_79.4.307.39","unstructured":"R Core Team . R: A language and environment for statistical computing. Vienna, Austria: R Foundation for Statistical Computing, 2021. Available: https:\/\/www.R-project.org\/"},{"key":"2025042101250973000_79.4.307.40","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMoa1214726"},{"key":"2025042101250973000_79.4.307.41","doi-asserted-by":"publisher","DOI":"10.1038\/ncomms5105"},{"key":"2025042101250973000_79.4.307.42","doi-asserted-by":"crossref","DOI":"10.3389\/fonc.2021.658887","article-title":"Radiomics-based features for prediction of histological subtypes in central lung cancer","volume":"11","author":"Li","year":"2021","journal-title":"Front Oncol"},{"key":"2025042101250973000_79.4.307.43","doi-asserted-by":"crossref","first-page":"300","DOI":"10.1097\/RCT.0000000000000836","article-title":"Radiomics for classifying histological subtypes of lung cancer based on Multiphasic contrast-enhanced computed tomography","volume":"43","author":"E","year":"2019","journal-title":"J Comput Assist Tomogr"},{"key":"2025042101250973000_79.4.307.44","doi-asserted-by":"crossref","DOI":"10.3389\/fonc.2020.542957","article-title":"CT Radiomics in predicting EGFR Mutation in non-small cell lung cancer: A single institutional study","volume":"10","author":"Wu","year":"2020","journal-title":"Front Oncol"},{"key":"2025042101250973000_79.4.307.45","doi-asserted-by":"crossref","DOI":"10.3389\/fonc.2020.00028","article-title":"Radiomics signature as a predictive factor for EGFR mutations in advanced lung adenocarcinoma","volume":"10","author":"Hong","year":"2020","journal-title":"Front Oncol"},{"key":"2025042101250973000_79.4.307.46","doi-asserted-by":"crossref","first-page":"4742","DOI":"10.1007\/s00330-019-06024-y","article-title":"Identifying EGFR mutations in lung adenocarcinoma by noninvasive imaging using Radiomics features and random forest modeling","volume":"29","author":"Jia","year":"2019","journal-title":"Eur Radiol"},{"key":"2025042101250973000_79.4.307.47","doi-asserted-by":"publisher","DOI":"10.1158\/0008-5472.CAN-17-0122"},{"key":"2025042101250973000_79.4.307.48","doi-asserted-by":"publisher","DOI":"10.1016\/j.cllc.2016.02.001"},{"key":"2025042101250973000_79.4.307.49","doi-asserted-by":"publisher","DOI":"10.1136\/thoraxjnl-2019-214104"},{"key":"2025042101250973000_79.4.307.50","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.2021204433"},{"key":"2025042101250973000_79.4.307.51","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.212182"},{"key":"2025042101250973000_79.4.307.52","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-019-0447-x"},{"key":"2025042101250973000_79.4.307.53","first-page":"236","article-title":"Management of screen-detected lung nodules: A Canadian partnership against cancer guidance document","volume":"4","author":"Lam","year":"2020","journal-title":"Canadian J Resp, Crit Care, Sleep Med"},{"key":"2025042101250973000_79.4.307.54","doi-asserted-by":"publisher","DOI":"10.1164\/rccm.201903-0505OC"}],"container-title":["Thorax"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1136\/thorax-2023-220226","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,21]],"date-time":"2025-04-21T07:00:30Z","timestamp":1745218830000},"score":1,"resource":{"primary":{"URL":"https:\/\/thorax.bmj.com\/lookup\/doi\/10.1136\/thorax-2023-220226"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,1,9]]},"references-count":54,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2024,3,15]]},"published-print":{"date-parts":[[2024,4]]}},"alternative-id":["10.1136\/thorax-2023-220226"],"URL":"https:\/\/doi.org\/10.1136\/thorax-2023-220226","relation":{"has-preprint":[{"id-type":"doi","id":"10.1101\/2022.10.03.22280659","asserted-by":"object"}]},"ISSN":["0040-6376","1468-3296"],"issn-type":[{"value":"0040-6376","type":"print"},{"value":"1468-3296","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,1,9]]}}}