{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,14]],"date-time":"2026-10-14T21:43:47Z","timestamp":1792014227264,"version":"4.4.0"},"reference-count":43,"publisher":"Oxford University Press (OUP)","issue":"8","license":[{"start":{"date-parts":[[2021,7,21]],"date-time":"2021-07-21T00:00:00Z","timestamp":1626825600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,4,28]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Automated radiologic analysis using computer-aided detection software (CAD) could facilitate chest X-ray (CXR) use in tuberculosis diagnosis. There is little to no evidence on the accuracy of commercially available deep learning-based CAD in different populations, including patients with smear-negative tuberculosis and people living with human immunodeficiency virus (HIV, PLWH).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We collected CXRs and individual patient data (IPD) from studies evaluating CAD in patients self-referring for tuberculosis symptoms with culture or nucleic acid amplification testing as the reference. We reanalyzed CXRs with three CAD programs (CAD4TB version (v) 6, Lunit v3.1.0.0, and qXR v2). We estimated sensitivity and specificity within each study and pooled using IPD meta-analysis. We used multivariable meta-regression to identify characteristics modifying accuracy.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>We included CXRs and IPD of 3727\/3967 participants from 4\/7 eligible studies. 17% (621\/3727) were PLWH. 17% (645\/3727) had microbiologically confirmed tuberculosis. Despite using the same threshold score for classifying CXR in every study, sensitivity and specificity varied from study to study. The software had similar unadjusted accuracy (at 90% pooled sensitivity, pooled specificities were: CAD4TBv6, 56.9% [95% confidence interval {CI}: 51.7\u201361.9]; Lunit, 54.1% [95% CI: 44.6\u201363.3]; qXRv2, 60.5% [95% CI: 51.7\u201368.6]). Adjusted absolute differences in pooled sensitivity between PLWH and HIV-uninfected participants were: CAD4TBv6, \u221213.4% [\u221221.1, \u22126.9]; Lunit, +2.2% [\u22123.6, +6.3]; qXRv2: \u221213.4% [\u221221.5, \u22126.6]; between smear-negative and smear-positive tuberculosis was: were CAD4TBv6, \u221212.3% [\u221219.5, \u22126.1]; Lunit, \u221217.2% [\u221224.6, \u221210.5]; qXRv2, \u221216.6% [\u221224.4, \u22129.9]. Accuracy was similar to human readers.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>For CAD CXR analysis to be implemented as a high-sensitivity tuberculosis rule-out test, users will need threshold scores identified from their own patient populations and stratified by HIV and smear status.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1093\/cid\/ciab639","type":"journal-article","created":{"date-parts":[[2021,7,20]],"date-time":"2021-07-20T15:33:04Z","timestamp":1626795184000},"page":"1390-1400","source":"Crossref","is-referenced-by-count":77,"title":["Chest X-ray Analysis With Deep Learning-Based Software as a Triage Test for Pulmonary Tuberculosis: An Individual Patient Data Meta-Analysis of Diagnostic Accuracy"],"prefix":"10.1093","volume":"74","author":[{"given":"Gamuchirai","family":"Tavaziva","sequence":"first","affiliation":[{"name":"McGill International TB Centre, Research Institute of the McGill University Health Centre, Montreal, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Miriam","family":"Harris","sequence":"additional","affiliation":[{"name":"McGill International TB Centre, Research Institute of the McGill University Health Centre, Montreal, Canada"},{"name":"Clinical Addiction Research and Education Unit, Section of General Internal Medicine, Department of Medicine, Boston University School of Medicine and Boston Medical Center, Boston, Massachusetts, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Syed K","family":"Abidi","sequence":"additional","affiliation":[{"name":"McGill International TB Centre, Research Institute of the McGill University Health Centre, Montreal, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Coralie","family":"Geric","sequence":"additional","affiliation":[{"name":"McGill International TB Centre, Research Institute of the McGill University Health Centre, Montreal, Canada"},{"name":"Departments of Medicine & Epidemiology, Biostatistics & Occupational Health, McGill University, Montreal, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marianne","family":"Breuninger","sequence":"additional","affiliation":[{"name":"Division of Infectious Diseases, Department I of Internal Medicine, University of Cologne, Cologne, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Keertan","family":"Dheda","sequence":"additional","affiliation":[{"name":"Centre for Lung Infection and Immunity Unit, Division of Pulmonology and UCT Lung Institute, University of Cape Town, Cape Town, South Africa"},{"name":"Faculty of Infectious and Tropical Diseases, Department of Infection Biology, London School of Hygiene and Tropical Medicine, London, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aliasgar","family":"Esmail","sequence":"additional","affiliation":[{"name":"Centre for Lung Infection and Immunity Unit, Division of Pulmonology and UCT Lung Institute, University of Cape Town, Cape Town, South Africa"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Monde","family":"Muyoyeta","sequence":"additional","affiliation":[{"name":"Zambart, Lusaka, Zambia"},{"name":"Centre for Infectious Disease Research in Zambia, Lusaka, Zambia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Klaus","family":"Reither","sequence":"additional","affiliation":[{"name":"Swiss Tropical and Public Health Institute, Basel, Switzerland"},{"name":"University of Basel, Basel, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Arman","family":"Majidulla","sequence":"additional","affiliation":[{"name":"Interactive Research & Development (IRD) Pakistan, Karachi, Pakistan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aamir J","family":"Khan","sequence":"additional","affiliation":[{"name":"IRD Global, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jonathon R","family":"Campbell","sequence":"additional","affiliation":[{"name":"McGill International TB Centre, Research Institute of the McGill University Health Centre, Montreal, Canada"},{"name":"Departments of Medicine & Epidemiology, Biostatistics & Occupational Health, McGill University, Montreal, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pierre-Marie","family":"David","sequence":"additional","affiliation":[{"name":"D\u00e9partement des M\u00e9dicaments et Sant\u00e9 des Populations, Faculty of Pharmacy, Universit\u00e9 de Montr\u00e9al, Montreal, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Claudia","family":"Denkinger","sequence":"additional","affiliation":[{"name":"Division of Tropical Medicine, Center of Infectious Diseases, University Hospital Heidelberg, Heidelberg, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cecily","family":"Miller","sequence":"additional","affiliation":[{"name":"World Health Organization, Geneva, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ruvandhi","family":"Nathavitharana","sequence":"additional","affiliation":[{"name":"Division of Infectious Diseases, Beth Israel Deaconess Medical Center, Harvard Medical School, Boston, Massachusetts, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Madhukar","family":"Pai","sequence":"additional","affiliation":[{"name":"McGill International TB Centre, Research Institute of the McGill University Health Centre, Montreal, Canada"},{"name":"Departments of Medicine & Epidemiology, Biostatistics & Occupational Health, McGill University, Montreal, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andrea","family":"Benedetti","sequence":"additional","affiliation":[{"name":"McGill International TB Centre, Research Institute of the McGill University Health Centre, Montreal, Canada"},{"name":"Departments of Medicine & Epidemiology, Biostatistics & Occupational Health, McGill University, Montreal, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Faiz","family":"Ahmad Khan","sequence":"additional","affiliation":[{"name":"McGill International TB Centre, Research Institute of the McGill University Health Centre, Montreal, Canada"},{"name":"Departments of Medicine & Epidemiology, Biostatistics & Occupational Health, McGill University, Montreal, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2021,7,21]]},"reference":[{"key":"2022042816585040800_CIT0001","doi-asserted-by":"crossref","first-page":"850","DOI":"10.1056\/NEJM190712261572602","article-title":"The Use of X-Ray examinations in pulmonary tuberculosis","volume":"157","author":"Williams","year":"1907","journal-title":"Boston Med Surg J"},{"key":"2022042816585040800_CIT0002","doi-asserted-by":"crossref","first-page":"663","DOI":"10.1148\/radiol.2413051535","article-title":"Recent advances in chest radiography","volume":"241","author":"McAdams","year":"2006","journal-title":"Radiology"},{"key":"2022042816585040800_CIT0003","doi-asserted-by":"crossref","first-page":"500","DOI":"10.1038\/s41568-018-0016-5","article-title":"Artificial intelligence in radiology","volume":"18","author":"Hosny","year":"2018","journal-title":"Nat Rev Cancer"},{"key":"2022042816585040800_CIT0004","doi-asserted-by":"crossref","first-page":"e0221339","DOI":"10.1371\/journal.pone.0221339","article-title":"A systematic review of the diagnostic accuracy of artificial intelligence-based computer programs to analyze chest x-rays for pulmonary tuberculosis","volume":"14","author":"Harris","year":"2019","journal-title":"PLoS One"},{"key":"2022042816585040800_CIT0005","doi-asserted-by":"crossref","first-page":"1226","DOI":"10.5588\/ijtld.15.0926","article-title":"Computer-aided detection of pulmonary tuberculosis on digital chest radiographs: a systematic review","volume":"20","author":"Pande","year":"2016","journal-title":"Int J Tuberc Lung Dis"},{"key":"2022042816585040800_CIT0006","doi-asserted-by":"crossref","first-page":"e573","DOI":"10.1016\/S2589-7500(20)30221-1","article-title":"Deep learning-based chest X-ray analysis software as triage tests for pulmonary tuberculosis: a prospective study of diagnostic accuracy for culture-confirmed disease","volume":"2","author":"Ahmad Khan","year":"2020","journal-title":"Lancet Digit Health"},{"key":"2022042816585040800_CIT0007","volume-title":"Chest Radiography in Tuberculosis Detection - Summary of current WHO recommendations and guidance on programmatic approaches, 2016","author":"World Health Organization.","year":"2016"},{"key":"2022042816585040800_CIT0008","doi-asserted-by":"crossref","first-page":"1657","DOI":"10.1001\/jama.2015.3656","article-title":"Preferred reporting items for systematic review and meta-analyses of individual participant data: the PRISMA-IPD statement","volume":"313","author":"Stewart","year":"2015","journal-title":"JAMA"},{"key":"2022042816585040800_CIT0009","doi-asserted-by":"crossref","first-page":"529","DOI":"10.7326\/0003-4819-155-8-201110180-00009","article-title":"QUADAS-2: a revised tool for the quality assessment of diagnostic accuracy studies","volume":"155","author":"Whiting","year":"2011","journal-title":"Ann Intern Med"},{"key":"2022042816585040800_CIT0010","doi-asserted-by":"crossref","first-page":"97","DOI":"10.1186\/s12874-016-0196-1","article-title":"Modelling multiple thresholds in meta-analysis of diagnostic test accuracy studies","volume":"16","author":"Steinhauser","year":"2016","journal-title":"BMC Med Res Methodol"},{"key":"2022042816585040800_CIT0011","volume-title":"diagmeta: meta-analysis of diagnostic accuracy studies with several R packages","author":"R\u00fccker","year":"2019"},{"key":"2022042816585040800_CIT0012"},{"key":"2022042816585040800_CIT0013","volume-title":"High-priority target product profiles for new tuberculosis diagnostics: report of a consensus meeting","author":"World Health Organization.","year":"2014"},{"key":"2022042816585040800_CIT0014","volume-title":"Meta-analysis of diagnostic accuracy with mada. R Packages","author":"Doebler","year":"2015"},{"key":"2022042816585040800_CIT0015","doi-asserted-by":"crossref","first-page":"982","DOI":"10.1016\/j.jclinepi.2005.02.022","article-title":"Bivariate analysis of sensitivity and specificity produces informative summary measures in diagnostic reviews","volume":"58","author":"Reitsma","year":"2005","journal-title":"J Clin Epidemiol"},{"key":"2022042816585040800_CIT0016","volume-title":"Systematic screening for active tuberculosis: principles and recommendations","author":"World Health Organization.","year":"2013"},{"key":"2022042816585040800_CIT0017","volume-title":"Base SAS\u00ae 9.4 procedures guide: statistical procedures, 6th ed","author":"SAS Institute Inc.","year":"2016"},{"key":"2022042816585040800_CIT0018","volume-title":"R: a language and environment for statistical computing","author":"R Foundation for Statistical Computing.","year":"2013"},{"key":"2022042816585040800_CIT0019","doi-asserted-by":"crossref","first-page":"e106381","DOI":"10.1371\/journal.pone.0106381","article-title":"Diagnostic accuracy of computer-aided detection of pulmonary tuberculosis in chest radiographs: a validation study from sub-Saharan Africa","volume":"9","author":"Breuninger","year":"2014","journal-title":"PLoS One"},{"key":"2022042816585040800_CIT0020","doi-asserted-by":"crossref","first-page":"e93757","DOI":"10.1371\/journal.pone.0093757","article-title":"The sensitivity and specificity of using a computer aided diagnosis program for automatically scoring chest X-rays of presumptive TB patients compared with Xpert MTB\/RIF in Lusaka Zambia","volume":"9","author":"Muyoyeta","year":"2014","journal-title":"PLoS One"},{"key":"2022042816585040800_CIT0021","doi-asserted-by":"crossref","first-page":"25265","DOI":"10.1038\/srep25265","article-title":"An automated tuberculosis screening strategy combining X-ray-based computer-aided detection and clinical information","volume":"6","author":"Melendez","year":"2016","journal-title":"Sci Rep"},{"key":"2022042816585040800_CIT0022","doi-asserted-by":"crossref","first-page":"12215","DOI":"10.1038\/srep12215","article-title":"Automated chest-radiography as a triage for Xpert testing in resource-constrained settings: a prospective study of diagnostic accuracy and costs","volume":"5","author":"Philipsen","year":"2015","journal-title":"Sci Rep"},{"key":"2022042816585040800_CIT0023","doi-asserted-by":"crossref","first-page":"15000","DOI":"10.1038\/s41598-019-51503-3","article-title":"Using artificial intelligence to read chest radiographs for tuberculosis detection: a multi-site evaluation of the diagnostic accuracy of three deep learning systems","volume":"9","author":"Qin","year":"2019","journal-title":"Sci Rep"},{"key":"2022042816585040800_CIT0024","doi-asserted-by":"crossref","first-page":"420","DOI":"10.1378\/chest.109.2.420","article-title":"The validity of classic symptoms and chest radiographic configuration in predicting pulmonary tuberculosis","volume":"109","author":"Cohen","year":"1996","journal-title":"Chest"},{"key":"2022042816585040800_CIT0025","doi-asserted-by":"crossref","first-page":"1613","DOI":"10.5588\/ijtld.13.0325","article-title":"Detection of tuberculosis using digital chest radiography: automated reading vs interpretation by clinical officers","volume":"17","author":"Maduskar","year":"2013","journal-title":"Int J Tuberc Lung Dis"},{"key":"2022042816585040800_CIT0026","doi-asserted-by":"crossref","first-page":"480","DOI":"10.1183\/09031936.00107412","article-title":"Scoring systems using chest radiographic features for the diagnosis of pulmonary tuberculosis in adults: a systematic review","volume":"42","author":"Pinto","year":"2013","journal-title":"Eur Respir J"},{"issue":"5","key":"2022042816585040800_CIT0027","doi-asserted-by":"crossref","DOI":"10.1183\/13993003.02159-2016","article-title":"An evaluation of automated chest radiography reading software for tuberculosis screening among public- and private-sector patients","volume":"49","author":"Rahman","year":"2017","journal-title":"Eur Respir J"},{"key":"2022042816585040800_CIT0028","first-page":"347","article-title":"Predictors of smear-negative pulmonary tuberculosis in HIV-infected patients, Battambang, Cambodia","volume":"13","author":"Tamhane","year":"2009","journal-title":"Int J Tuberc Lung Dis"},{"key":"2022042816585040800_CIT0029","doi-asserted-by":"crossref","first-page":"111","DOI":"10.1186\/1471-2334-5-111","article-title":"The role and performance of chest X-ray for the diagnosis of tuberculosis: a cost-effectiveness analysis in Nairobi, Kenya","volume":"5","author":"van Cleeff","year":"2005","journal-title":"BMC Infect Dis"},{"key":"2022042816585040800_CIT0030","doi-asserted-by":"crossref","first-page":"281","DOI":"10.1016\/S0954-6111(97)90031-7","article-title":"Diagnostic strategy for pulmonary tuberculosis in a low-incidence country: results of chest X-ray and sputum cultured for Mycobacterium tuberculosis","volume":"91","author":"Wilcke","year":"1997","journal-title":"Respir Med"},{"key":"2022042816585040800_CIT0031","first-page":"137","article-title":"Chest radiograph abnormalities associated with tuberculosis: reproducibility and yield of active cases","volume":"6","author":"Graham","year":"2002","journal-title":"Int J Tuberc Lung Dis"},{"key":"2022042816585040800_CIT0032","doi-asserted-by":"crossref","first-page":"379","DOI":"10.1136\/bmj.331.7513.379","article-title":"Variability in interpretation of chest radiographs among Russian clinicians and implications for screening programmes: observational study","volume":"331","author":"Balabanova","year":"2005","journal-title":"BMJ"},{"key":"2022042816585040800_CIT0033","first-page":"302","article-title":"How reliable is chest radiography?","volume-title":"Toman\u2019s tuberculosis case detection, treatment, and monitoring: questions and answers","author":"Koppaka","year":"2005","edition":"2"},{"key":"2022042816585040800_CIT0034","doi-asserted-by":"crossref","first-page":"519 e1","DOI":"10.1016\/j.crad.2017.01.008","article-title":"Evaluation of a chest radiograph reading and recording system for tuberculosis in a HIV-positive cohort","volume":"72","author":"Kosack","year":"2017","journal-title":"Clin Radiol"},{"key":"2022042816585040800_CIT0035","doi-asserted-by":"crossref","first-page":"e54235","DOI":"10.1371\/journal.pone.0054235","article-title":"Development of a simple reliable radiographic scoring system to aid the diagnosis of pulmonary tuberculosis","volume":"8","author":"Pinto","year":"2013","journal-title":"PLoS One"},{"key":"2022042816585040800_CIT0036","doi-asserted-by":"crossref","first-page":"863","DOI":"10.1136\/thx.2010.136242","article-title":"A simple, valid, numerical score for grading chest x-ray severity in adult smear-positive pulmonary tuberculosis","volume":"65","author":"Ralph","year":"2010","journal-title":"Thorax"},{"key":"2022042816585040800_CIT0037","first-page":"1123","article-title":"Intra-observer and overall agreement in the radiological assessment of tuberculosis","volume":"10","author":"Zellweger","year":"2006","journal-title":"Int J Tuberc Lung Dis"},{"key":"2022042816585040800_CIT0038","doi-asserted-by":"crossref","first-page":"1668","DOI":"10.1148\/rg.2015150023","article-title":"Understanding and confronting our mistakes: the epidemiology of error in radiology and strategies for error reduction","volume":"35","author":"Bruno","year":"2015","journal-title":"Radiographics"},{"key":"2022042816585040800_CIT0039","doi-asserted-by":"crossref","first-page":"191","DOI":"10.1016\/j.jacr.2016.10.009","article-title":"Tired in the reading room: the influence of fatigue in radiology","volume":"14","author":"Waite","year":"2017","journal-title":"J Am Coll Radiol"},{"key":"2022042816585040800_CIT0040","doi-asserted-by":"crossref","DOI":"10.1183\/13993003.00953-2017","article-title":"Computer-aided reading of tuberculosis chest radiography: moving the research agenda forward to inform policy","volume":"50","author":"Ahmad Khan","year":"2017","journal-title":"Eur Respir J"},{"key":"2022042816585040800_CIT0041","author":"World Health Organization."},{"key":"2022042816585040800_CIT0042","doi-asserted-by":"crossref","first-page":"12339","DOI":"10.1038\/s41598-018-30810-1","article-title":"Evaluation of the diagnostic accuracy of computer-aided detection of tuberculosis on chest radiography among private sector patients in Pakistan","volume":"8","author":"Zaidi","year":"2018","journal-title":"Sci Rep"},{"key":"2022042816585040800_CIT0043","article-title":"Can artificial intelligence (AI) be used to accurately detect tuberculosis (TB) from chest x-ray? a multiplatform evaluation of five AI products used for TB screening in a high TB-burden setting","author":"Qin","year":"2020","journal-title":"arXiv"}],"container-title":["Clinical Infectious Diseases"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/cid\/advance-article-pdf\/doi\/10.1093\/cid\/ciab639\/41131932\/ciab639.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/cid\/article-pdf\/74\/8\/1390\/43493268\/ciab639.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/cid\/article-pdf\/74\/8\/1390\/43493268\/ciab639.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,28]],"date-time":"2022-04-28T14:23:43Z","timestamp":1651155823000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/cid\/article\/74\/8\/1390\/6324830"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,7,21]]},"references-count":43,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2021,7,21]]},"published-print":{"date-parts":[[2022,4,28]]}},"URL":"https:\/\/doi.org\/10.1093\/cid\/ciab639","relation":{},"ISSN":["1058-4838","1537-6591"],"issn-type":[{"value":"1058-4838","type":"print"},{"value":"1537-6591","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2022,4,15]]},"published":{"date-parts":[[2021,7,21]]}}}