{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,13]],"date-time":"2026-10-13T16:37:27Z","timestamp":1791909447327,"version":"4.3.4"},"reference-count":49,"publisher":"American Medical Association (AMA)","issue":"12","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["JAMA Netw Open"],"abstract":"Importance<\/jats:title>Lung cancer screening with chest computed tomography (CT) prevents lung cancer death; however, fewer than 5% of eligible Americans are screened. CXR-LC, an open-source deep learning tool that estimates lung cancer risk from existing chest radiograph images and commonly available electronic medical record (EMR) data, may enable automated identification of high-risk patients as a step toward improving lung cancer screening participation.<\/jats:p><\/jats:sec>Objective<\/jats:title>To validate CXR-LC using EMR data to identify individuals at high-risk for lung cancer to complement 2022 US Centers for Medicare &amp;amp; Medicaid Services (CMS) lung cancer screening eligibility guidelines.<\/jats:p><\/jats:sec>Design, Setting, and Participants<\/jats:title>This prognostic study compared CXR-LC estimates with CMS screening guidelines using patient data from a large US hospital system. Included participants were persons who currently or formerly smoked cigarettes with an outpatient posterior-anterior chest radiograph between January 1, 2013, and December 31, 2014, with no history of lung cancer or screening CT. Data analysis was performed between May 2021 and June 2022.<\/jats:p><\/jats:sec>Exposures<\/jats:title>CXR-LC lung cancer screening eligibility (previously defined as having a 3.297% or greater 12-year risk) based on inputs (chest radiograph image, age, sex, and whether currently smoking) extracted from the EMR.<\/jats:p><\/jats:sec>Main Outcomes and Measures<\/jats:title>6-year incident lung cancer.<\/jats:p><\/jats:sec>Results<\/jats:title>A total of 14\u202f737 persons were included in the study population (mean [SD] age, 62.6 [6.8] years; 7154 [48.5%] male; 204 [1.4%] Asian, 1051 [7.3%] Black, 432 [2.9%] Hispanic, 12\u202f330 [85.2%] White) with a 2.4% rate of incident lung cancer over 6 years (361 patients with cancer). CMS eligibility could be determined in 6277 patients (42.6%) using smoking pack-year and quit-date from the EMR. Patients eligible by both CXR-LC and 2022 CMS criteria had a high rate of lung cancer (83 of 974 patients [8.5%]), higher than those eligible by 2022 CMS criteria alone (5 of 177 patients [2.8%]; P<\/jats:italic>\u2009&amp;lt;\u2009.001). Patients eligible by CXR-LC but not 2022 CMS criteria also had a high 6-year incidence of lung cancer (121 of 3703 [3.3%]). In the 8460 cases (57.4%) where CMS eligibility was unknown, CXR-LC eligible patients had a 5-fold higher rate of lung cancer than ineligible (127 of 5177 [2.5%] vs 18 of 2283 [0.5%]; P<\/jats:italic>\u2009&amp;lt;\u2009.001). Similar results were found in subgroups, including female patients and Black persons.<\/jats:p><\/jats:sec>Conclusions and Relevance<\/jats:title>Using routine chest radiographs and other data automatically extracted from the EMR, CXR-LC identified high-risk individuals who may benefit from lung cancer screening CT.<\/jats:p><\/jats:sec>","DOI":"10.1001\/jamanetworkopen.2022.48793","type":"journal-article","created":{"date-parts":[[2022,12,28]],"date-time":"2022-12-28T16:34:42Z","timestamp":1672245282000},"page":"e2248793","source":"Crossref","is-referenced-by-count":35,"title":["Validation of a Deep Learning\u2013Based Model to Predict Lung Cancer Risk Using Chest Radiographs and Electronic Medical Record Data"],"prefix":"10.1001","volume":"5","author":[{"given":"Vineet K.","family":"Raghu","sequence":"first","affiliation":[{"name":"Cardiovascular Imaging Research Center, Department of Radiology, Massachusetts General Hospital & Harvard Medical School, Boston, Massachusetts"},{"name":"Program for Artificial Intelligence in Medicine, Brigham and Women\u2019s Hospital & Harvard Medical School, Boston, Massachusetts"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anika S.","family":"Walia","sequence":"additional","affiliation":[{"name":"Cardiovascular Imaging Research Center, Department of Radiology, Massachusetts General Hospital & Harvard Medical School, Boston, Massachusetts"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aniket N.","family":"Zinzuwadia","sequence":"additional","affiliation":[{"name":"Cardiovascular Imaging Research Center, Department of Radiology, Massachusetts General Hospital & Harvard Medical School, Boston, Massachusetts"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Reece J.","family":"Goiffon","sequence":"additional","affiliation":[{"name":"Division of Abdominal Imaging, Department of Radiology, Massachusetts General Hospital & Harvard Medical School, Boston, Massachusetts"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jo-Anne O.","family":"Shepard","sequence":"additional","affiliation":[{"name":"Division of Thoracic Imaging and Intervention, Department of Radiology, Massachusetts General Hospital & Harvard Medical School, Boston, Massachusetts"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hugo J. W. L.","family":"Aerts","sequence":"additional","affiliation":[{"name":"Cardiovascular Imaging Research Center, Department of Radiology, Massachusetts General Hospital & Harvard Medical School, Boston, Massachusetts"},{"name":"Program for Artificial Intelligence in Medicine, Brigham and Women\u2019s Hospital & Harvard Medical School, Boston, Massachusetts"},{"name":"Department of Radiology and Nuclear Medicine, CARIM School for Cardiovascular Diseases and GROW School for Oncology and Reproduction, Maastricht University, the Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Inga T.","family":"Lennes","sequence":"additional","affiliation":[{"name":"Division of Hematology and Oncology, Department of Medicine, Massachusetts General Hospital & Harvard Medical School, Boston, Massachusetts"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michael T.","family":"Lu","sequence":"additional","affiliation":[{"name":"Cardiovascular Imaging Research Center, Department of Radiology, Massachusetts General Hospital & Harvard Medical School, Boston, Massachusetts"},{"name":"Program for Artificial Intelligence in Medicine, Brigham and Women\u2019s Hospital & Harvard Medical School, Boston, Massachusetts"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"10","published-online":{"date-parts":[[2022,12,28]]},"reference":[{"issue":"3","key":"zoi221379r1","doi-asserted-by":"publisher","first-page":"209","DOI":"10.3322\/caac.v71.3","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"},{"issue":"5","key":"zoi221379r3","doi-asserted-by":"publisher","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"},{"issue":"6","key":"zoi221379r4","doi-asserted-by":"publisher","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"},{"issue":"3","key":"zoi221379r6","doi-asserted-by":"publisher","first-page":"243","DOI":"10.21037\/tlcr","article-title":"Selecting lung cancer screenees using risk prediction models-where do we go from here.","volume":"7","author":"Tammem\u00e4gi","year":"2018","journal-title":"Transl Lung Cancer Res"},{"issue":"2","key":"zoi221379r7","doi-asserted-by":"publisher","first-page":"278","DOI":"10.1148\/radiol.2018180212","article-title":"Barriers to lung cancer screening engagement from the patient and provider perspective.","volume":"290","author":"Wang","year":"2019","journal-title":"Radiology"},{"issue":"9","key":"zoi221379r8","doi-asserted-by":"publisher","first-page":"1278","DOI":"10.1001\/jamaoncol.2016.6416","article-title":"Lung cancer screening with low-dose computed tomography in the United States, 2010 to 2015.","volume":"3","author":"Jemal","year":"2017","journal-title":"JAMA Oncol"},{"issue":"3","key":"zoi221379r10","doi-asserted-by":"publisher","first-page":"184","DOI":"10.3322\/caac.v69.3","article-title":"Cancer screening in the United States, 2019: a review of current American Cancer Society guidelines and current issues in cancer screening.","volume":"69","author":"Smith","year":"2019","journal-title":"CA Cancer J Clin"},{"issue":"9","key":"zoi221379r11","doi-asserted-by":"publisher","first-page":"1318","DOI":"10.1001\/jamaoncol.2019.1402","article-title":"Evaluation of USPSTF lung cancer screening guidelines among African American adult smokers.","volume":"5","author":"Aldrich","year":"2019","journal-title":"JAMA Oncol"},{"issue":"1","key":"zoi221379r12","doi-asserted-by":"publisher","first-page":"248","DOI":"10.1016\/j.chest.2021.06.066","article-title":"Addressing sex disparities in lung cancer screening eligibility: USPSTF vs PLCOm2012 criteria.","volume":"161","author":"Pasquinelli","year":"2022","journal-title":"Chest"},{"issue":"4","key":"zoi221379r13","doi-asserted-by":"publisher","first-page":"399","DOI":"10.1513\/AnnalsATS.201907-556CME","article-title":"Disparities in lung cancer screening: a review.","volume":"17","author":"Haddad","year":"2020","journal-title":"Ann Am Thorac Soc"},{"issue":"3","key":"zoi221379r14","doi-asserted-by":"publisher","DOI":"10.1093\/jnci\/dju489","article-title":"Age at cancer diagnosis for blacks compared with whites in the United States.","volume":"107","author":"Robbins","year":"2015","journal-title":"J Natl Cancer Inst"},{"issue":"4","key":"zoi221379r15","doi-asserted-by":"publisher","first-page":"333","DOI":"10.1056\/NEJMoa033250","article-title":"Ethnic and racial differences in the smoking-related risk of lung cancer.","volume":"354","author":"Haiman","year":"2006","journal-title":"N Engl J Med"},{"issue":"7","key":"zoi221379r17","doi-asserted-by":"publisher","first-page":"689","DOI":"10.1016\/S2213-2600(21)00210-1","article-title":"The 2021 USPSTF lung cancer screening guidelines: a new frontier.","volume":"9","author":"Potter","year":"2021","journal-title":"Lancet Respir Med"},{"issue":"3","key":"zoi221379r18","doi-asserted-by":"publisher","first-page":"374","DOI":"10.1001\/jamaoncol.2021.6720","article-title":"Comparison between the 2021 USPSTF lung cancer screening criteria and other lung cancer screening criteria for racial disparity in eligibility.","volume":"8","author":"Pu","year":"2022","journal-title":"JAMA Oncol"},{"issue":"5 Suppl","key":"zoi221379r19","doi-asserted-by":"publisher","first-page":"e78S","DOI":"10.1378\/chest.12-2350","article-title":"Screening for lung cancer: diagnosis and management of lung cancer, 3rd ed\u2014American College of Chest Physicians evidence-based clinical practice guidelines.","volume":"143","author":"Detterbeck","year":"2013","journal-title":"Chest"},{"issue":"3","key":"zoi221379r20","doi-asserted-by":"publisher","first-page":"399","DOI":"10.1001\/jamainternmed.2016.9022","article-title":"Implementation of lung cancer screening in the Veterans Health Administration.","volume":"177","author":"Kinsinger","year":"2017","journal-title":"JAMA Intern Med"},{"issue":"8","key":"zoi221379r21","doi-asserted-by":"publisher","first-page":"1320","DOI":"10.1513\/AnnalsATS.201612-984OC","article-title":"Pack-year cigarette smoking history for determination of lung cancer screening eligibility\u2014comparison of the electronic medical record versus a shared decision-making conversation.","volume":"14","author":"Modin","year":"2017","journal-title":"Ann Am Thorac Soc"},{"issue":"9","key":"zoi221379r22","doi-asserted-by":"publisher","first-page":"704","DOI":"10.7326\/M20-1868","article-title":"Deep learning using chest radiographs to identify high-risk smokers for lung cancer screening computed tomography: development and validation of a prediction model.","volume":"173","author":"Lu","year":"2020","journal-title":"Ann Intern Med"},{"issue":"1","key":"zoi221379r23","doi-asserted-by":"publisher","first-page":"209","DOI":"10.1148\/radiol.212877","article-title":"Deep learning to optimize candidate selection for lung cancer CT screening: advancing the 2021 USPSTF recommendations.","volume":"305","author":"Lee","year":"2022","journal-title":"Radiology"},{"issue":"6","key":"zoi221379r24","doi-asserted-by":"publisher","first-page":"273S","DOI":"10.1016\/S0197-2456(00)00098-2","article-title":"Design of the Prostate, Lung, Colorectal and Ovarian (PLCO) cancer screening trial.","volume":"21","author":"Prorok","year":"2000","journal-title":"Control Clin Trials"},{"issue":"17","key":"zoi221379r25","doi-asserted-by":"publisher","first-page":"1865","DOI":"10.1001\/jama.2011.1591","article-title":"Screening by chest radiograph and lung cancer mortality: the Prostate, Lung, Colorectal, and Ovarian (PLCO) randomized trial.","volume":"306","author":"Oken","year":"2011","journal-title":"JAMA"},{"issue":"6","key":"zoi221379r27","doi-asserted-by":"publisher","first-page":"251S","DOI":"10.1016\/S0197-2456(00)00097-0","article-title":"The Prostate, Lung, Colorectal and Ovarian (PLCO) cancer screening trial of the National Cancer Institute: history, organization, and status.","volume":"21","author":"Gohagan","year":"2000","journal-title":"Control Clin Trials"},{"issue":"5","key":"zoi221379r28","doi-asserted-by":"publisher","first-page":"779","DOI":"10.1093\/jamia\/ocac020","article-title":"Inaccuracies in electronic health records smoking data and a potential approach to address resulting underestimation in determining lung cancer screening eligibility.","volume":"29","author":"Kukhareva","year":"2022","journal-title":"J Am Med Inform Assoc"},{"issue":"1","key":"zoi221379r29","doi-asserted-by":"publisher","first-page":"737","DOI":"10.1186\/s12913-019-4574-3","article-title":"Algorithms to identify COPD in health systems with and without access to ICD coding: a systematic review.","volume":"19","author":"Gothe","year":"2019","journal-title":"BMC Health Serv Res"},{"issue":"6","key":"zoi221379r30","doi-asserted-by":"publisher","first-page":"560","DOI":"10.1001\/archinternmed.2010.17","article-title":"Trends in chronic obstructive pulmonary disease prevalence, incidence, and mortality in Ontario, Canada, 1996 to 2007: a population-based study.","volume":"170","author":"Gershon","year":"2010","journal-title":"Arch Intern Med"},{"issue":"1","key":"zoi221379r32","doi-asserted-by":"publisher","first-page":"47","DOI":"10.1038\/s41746-022-00590-0","article-title":"Cohort design and natural language processing to reduce bias in electronic health records research.","volume":"5","author":"Khurshid","year":"2022","journal-title":"NPJ Digit Med"},{"issue":"2","key":"zoi221379r33","doi-asserted-by":"publisher","first-page":"153","DOI":"10.1007\/BF02295996","article-title":"Note on the sampling error of the difference between correlated proportions or percentages.","volume":"12","author":"McNemar","year":"1947","journal-title":"Psychometrika"},{"key":"zoi221379r35","doi-asserted-by":"publisher","first-page":"i6","DOI":"10.1136\/bmj.i6","article-title":"Net benefit approaches to the evaluation of prediction models, molecular markers, and diagnostic tests.","volume":"352","author":"Vickers","year":"2016","journal-title":"BMJ"},{"key":"zoi221379r36","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1186\/s41512-019-0064-7","article-title":"A simple, step-by-step guide to interpreting decision curve analysis.","volume":"3","author":"Vickers","year":"2019","journal-title":"Diagn Progn Res"},{"issue":"4","key":"zoi221379r37","doi-asserted-by":"publisher","first-page":"294","DOI":"10.7326\/0003-4819-157-4-201208210-00014","article-title":"Beyond the usual prediction accuracy metrics: reporting results for clinical decision making.","volume":"157","author":"Localio","year":"2012","journal-title":"Ann Intern Med"},{"issue":"4","key":"zoi221379r38","doi-asserted-by":"publisher","first-page":"412","DOI":"10.6004\/jnccn.2018.0020","article-title":"Lung cancer screening, version 3.2018, NCCN clinical practice guidelines in oncology.","volume":"16","author":"Wood","year":"2018","journal-title":"J Natl Compr Canc Netw"},{"issue":"1","key":"zoi221379r40","doi-asserted-by":"publisher","DOI":"10.1117\/1.JMI.7.1.016502","article-title":"Integrating AI into radiology workflow: levels of research, production, and feedback maturity.","volume":"7","author":"Dikici","year":"2020","journal-title":"J Med Imaging (Bellingham)"},{"issue":"2","key":"zoi221379r41","doi-asserted-by":"publisher","first-page":"170","DOI":"10.1111\/hesr.v55.2","article-title":"Trends in smoking documentation rates in safety net clinics.","volume":"55","author":"Fortmann","year":"2020","journal-title":"Health Serv Res"},{"issue":"572","key":"zoi221379r42","doi-asserted-by":"publisher","first-page":"e121","DOI":"10.3399\/bjgp10X483544","article-title":"Trends in the epidemiology of smoking recorded in UK general practice.","volume":"60","author":"Simpson","year":"2010","journal-title":"Br J Gen Pract"},{"issue":"8","key":"zoi221379r43","doi-asserted-by":"publisher","DOI":"10.2196\/26256","article-title":"Artificial intelligence-based prediction of lung cancer risk using nonimaging electronic medical records: deep learning approach.","volume":"23","author":"Yeh","year":"2021","journal-title":"J Med internet Res"},{"issue":"4","key":"zoi221379r44","doi-asserted-by":"publisher","first-page":"445","DOI":"10.1164\/rccm.202007-2791OC","article-title":"Machine learning for early lung cancer identification using routine clinical and laboratory data.","volume":"204","author":"Gould","year":"2021","journal-title":"Am J Respir Crit Care Med"},{"issue":"3","key":"zoi221379r45","doi-asserted-by":"publisher","first-page":"463","DOI":"10.1001\/jamainternmed.2019.6282","article-title":"Characteristics of Americans with primary care and changes over time, 2002-2015.","volume":"180","author":"Levine","year":"2020","journal-title":"JAMA Intern Med"},{"issue":"8","key":"zoi221379r46","doi-asserted-by":"publisher","first-page":"1044","DOI":"10.1093\/jnci\/djaa170","article-title":"State variation in low-dose computed tomography scanning for lung cancer screening in the United States.","volume":"113","author":"Fedewa","year":"2021","journal-title":"J Natl Cancer Inst"},{"issue":"12","key":"zoi221379r47","doi-asserted-by":"publisher","first-page":"2310","DOI":"10.1377\/hlthaff.2010.1111","article-title":"Clinical decision support systems could be modified to reduce \u2018alert fatigue\u2019 while still minimizing the risk of litigation.","volume":"30","author":"Kesselheim","year":"2011","journal-title":"Health Aff (Millwood)"},{"issue":"1","key":"zoi221379r48","doi-asserted-by":"publisher","first-page":"27","DOI":"10.1631\/FITEE.1700808","article-title":"Visual interpretability for deep learning: a survey.","volume":"19","author":"Zhang","year":"2018","journal-title":"Frontiers of Information Technology & Electronic Engineering"},{"issue":"10","key":"zoi221379r49","doi-asserted-by":"publisher","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":"zoi221379r31","author":"National Institutes of Health","year":"2001"},{"key":"zoi221379r34","doi-asserted-by":"crossref","DOI":"10.1201\/b16654","volume-title":"Modelling Binary Data","author":"Collett","year":"2002"},{"key":"zoi221379r39","author":"Lam","year":"2019"},{"key":"zoi221379r2","unstructured":"National Cancer Institute. Cancer stat facts: common cancer sites. 2022. Accessed May 2, 2019. https:\/\/seer.cancer.gov\/statfacts\/html\/\/common.html"},{"key":"zoi221379r5","unstructured":"Syrek Jensen? T, Ashby? L, Hermansen? J, Hunter? JD. Decision memo for screening for lung cancer with low dose computed tomography (LDCT) (CAG-00439N). Centers for Medicare & Medicaid Services. Published February 5, 2015. Accessed September 11, 2019. https:\/\/www.cms.gov\/medicare-coverage-database\/view\/ncacal-decision-memo.aspx?proposed=N&NCAId=274"},{"key":"zoi221379r9","unstructured":"American Lung Association. Lung Cancer Key Findings. State of Lung Cancer website. Published 2021. Accessed October 20, 2022. https:\/\/www.lung.org\/research\/state-of-lung-cancer\/key-findings"},{"key":"zoi221379r16","unstructured":"Syrek Jensen? T, Chin? J, Baldwin? J, Evans? M, Long? K, Li? C, Mukherjee? DV. Decision memo for screening for lung cancer with low dose computed tomography (LDCT) (CAG-00439R). Published February 10, 2022. Accessed March 1, 2022. https:\/\/www.cms.gov\/medicare-coverage-database\/view\/ncacal-decision-memo.aspx?proposed=N&ncaid=304"},{"key":"zoi221379r26","unstructured":"CXR-LC. GitHub. Updated December 28, 2020. Accessed August 24, 2022. https:\/\/github.com\/circ-ml\/CXR-LC"}],"container-title":["JAMA Network Open"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/jamanetwork.com\/journals\/jamanetworkopen\/articlepdf\/2799952\/raghu_2022_oi_221379_1671210657.23234.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,28]],"date-time":"2022-12-28T16:34:50Z","timestamp":1672245290000},"score":1,"resource":{"primary":{"URL":"https:\/\/jamanetwork.com\/journals\/jamanetworkopen\/fullarticle\/2799952"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,12,28]]},"references-count":49,"journal-issue":{"issue":"12","published-print":{"date-parts":[[2022,12,1]]}},"URL":"https:\/\/doi.org\/10.1001\/jamanetworkopen.2022.48793","relation":{},"ISSN":["2574-3805"],"issn-type":[{"value":"2574-3805","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,12,28]]}}}