{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,23]],"date-time":"2026-09-23T19:00:42Z","timestamp":1790190042902,"version":"4.1.0"},"reference-count":34,"publisher":"Oxford University Press (OUP)","issue":"3","license":[{"start":{"date-parts":[[2026,4,16]],"date-time":"2026-04-16T00:00:00Z","timestamp":1776297600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000060","name":"National Institute of Allergy and Infectious Diseases","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000060","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["R01AI155765"],"award-info":[{"award-number":["R01AI155765"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["AI068634"],"award-info":[{"award-number":["AI068634"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"name":"BCBB Support Services","award":["HHSN316201300006W"],"award-info":[{"award-number":["HHSN316201300006W"]}]},{"name":"BCBB Support Services","award":["75N93022F00001"],"award-info":[{"award-number":["75N93022F00001"]}]},{"name":"Business and Science Data Analytics","award":["HHSN316201200018W"],"award-info":[{"award-number":["HHSN316201200018W"]}]},{"name":"Deloitte Consulting LLP"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,9,23]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Chest X-ray (CXR) can assess pulmonary tuberculosis (TB) severity and may guide duration of treatment. However, the optimal radiological metric and its integration with clinical variables for predicting treatment outcomes remains unclear.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We used logistic regression to associate human-read and commercial artificial intelligence\u2013generated CXR metrics with unfavorable outcome in the TB Portals real-world dataset (n = 2809). We assessed the standalone predictive accuracy for each of 10 radiological features for unfavorable outcomes, and combined the best-performing features with other clinical data. We fine-tuned ensembles of convolutional neural nets (CNNs) to automate human-read percent of lung involved (PLI) measurement directly from CXR images (n = 5261).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Human-read PLI is the only CXR finding associated with outcome across drug resistance and human immunodeficiency virus (HIV) subgroups and is optimally combined with age, sex, and smear grade for predicting treatment outcome. PLI predicts outcomes better than cavitation (area under the curve [AUC], 0.654 vs 0.581, respectively), performs better than all tested Qure.ai automated features (qXR v2), and improves outcome prediction when added to sex + age + smear grade (\u0394AUC, 0.028 [95% confidence interval, .007\u2013.042]). The CNN ensemble for predicting PLI &amp;gt;25% achieves an AUC of 0.850.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>PLI performs better than cavitation as a radiological marker for predicting TB treatment outcome, and improves risk stratification when combined with key clinical variables. Automation of PLI can be predicted using CNNs to enable scalability and accurate assessment.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1093\/infdis\/jiag149","type":"journal-article","created":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T11:27:47Z","timestamp":1775561267000},"page":"e600-e612","source":"Crossref","is-referenced-by-count":2,"title":["Tuberculosis Disease Severity Assessment Using Clinical Variables and Radiology Enabled by Artificial Intelligence"],"prefix":"10.1093","volume":"234","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6768-4537","authenticated-orcid":false,"given":"Marwan","family":"Ghanem","sequence":"first","affiliation":[{"name":"Department of Biomedical Informatics, Harvard Medical School , Boston, Massachusetts ,","place":["USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ratnam","family":"Srivastava","sequence":"additional","affiliation":[{"name":"Department of Biomedical Informatics, Harvard Medical School , Boston, Massachusetts ,","place":["USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2759-4470","authenticated-orcid":false,"given":"Yasha","family":"Ektefaie","sequence":"additional","affiliation":[{"name":"Department of Biomedical Informatics, Harvard Medical School , Boston, Massachusetts ,","place":["USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Drew","family":"Hoppes","sequence":"additional","affiliation":[{"name":"National Institute of Allergy and Infectious Diseases, National Institutes of Health , Bethesda, Maryland ,","place":["USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gabriel","family":"Rosenfeld","sequence":"additional","affiliation":[{"name":"National Institute of Allergy and Infectious Diseases, National Institutes of Health , Bethesda, Maryland ,","place":["USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0315-7727","authenticated-orcid":false,"given":"Ziv","family":"Yaniv","sequence":"additional","affiliation":[{"name":"National Institute of Allergy and Infectious Diseases, National Institutes of Health , Bethesda, Maryland ,","place":["USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alina","family":"Grinev","sequence":"additional","affiliation":[{"name":"National Institute of Allergy and Infectious Diseases, National Institutes of Health , Bethesda, Maryland ,","place":["USA"]},{"name":"NTT Data Company Research Data and Communications Technology Corp, , New York, New York ,","place":["USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ava Y","family":"Xu","sequence":"additional","affiliation":[{"name":"Department of Bioengineering and Therapeutic Sciences, University of California, SanFrancisco , San Francisco, California ,","place":["USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2581-349X","authenticated-orcid":false,"given":"Eunsol","family":"Yang","sequence":"additional","affiliation":[{"name":"Department of Bioengineering and Therapeutic Sciences, University of California, SanFrancisco , San Francisco, California ,","place":["USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1438-0692","authenticated-orcid":false,"given":"Gustavo E","family":"Vel\u00e1squez","sequence":"additional","affiliation":[{"name":"UCSF Center for Tuberculosis, University of California, SanFrancisco , San Francisco, California ,","place":["USA"]},{"name":"Division of HIV, Infectious Diseases, and Global Medicine, University of California, SanFrancisco , San Francisco, California ,","place":["USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3170-0865","authenticated-orcid":false,"given":"Linda","family":"Harrison","sequence":"additional","affiliation":[{"name":"Center for Biostatistics in AIDS Research, Department of Biostatistics, Harvard T.H. Chan School of Public Health , Boston, Massachusetts ,","place":["USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4190-9045","authenticated-orcid":false,"given":"Alex","family":"Rosenthal","sequence":"additional","affiliation":[{"name":"National Institute of Allergy and Infectious Diseases, National Institutes of Health , Bethesda, Maryland ,","place":["USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Radojka M","family":"Savic","sequence":"additional","affiliation":[{"name":"Department of Bioengineering and Therapeutic Sciences, University of California, SanFrancisco , San Francisco, California ,","place":["USA"]},{"name":"UCSF Center for Tuberculosis, University of California, SanFrancisco , San Francisco, California ,","place":["USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Karen R","family":"Jacobson","sequence":"additional","affiliation":[{"name":"Section of Infectious Diseases, Boston University School of Medicine , Boston, Massachusetts ,","place":["USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3871-5760","authenticated-orcid":false,"given":"Maha R","family":"Farhat","sequence":"additional","affiliation":[{"name":"Department of Biomedical Informatics, Harvard Medical School , Boston, Massachusetts ,","place":["USA"]},{"name":"Division of Pulmonary and Critical Care Medicine, Massachusetts General Hospital , Boston, Massachusetts ,","place":["USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2026,4,16]]},"reference":[{"key":"2026092314160902000_jiag149-B1","doi-asserted-by":"crossref","first-page":"e684","DOI":"10.1016\/S2214-109X(23)00082-7","article-title":"Quantifying progression and regression across the spectrum of pulmonary tuberculosis: a data synthesis study","volume":"11","author":"Richards","year":"2023","journal-title":"Lancet Global Health"},{"key":"2026092314160902000_jiag149-B2","doi-asserted-by":"crossref","first-page":"1175","DOI":"10.1016\/S1473-3099(20)30732-5","article-title":"Measuring health-care delays among privately insured patients with tuberculosis in the USA: an observational cohort study","volume":"21","author":"El Halabi","year":"2021","journal-title":"Lancet Infect Dis"},{"key":"2026092314160902000_jiag149-B3","doi-asserted-by":"crossref","first-page":"751","DOI":"10.1159\/000512531","article-title":"Post-tuberculosis lung disease: clinical review of an under-recognised global challenge","volume":"100","author":"Allwood","year":"2021","journal-title":"Respiration"},{"key":"2026092314160902000_jiag149-B4","doi-asserted-by":"crossref","first-page":"1708","DOI":"10.1038\/s41591-018-0224-2","article-title":"A patient-level pooled analysis of treatment-shortening regimens for drug-susceptible pulmonary tuberculosis","volume":"24","author":"Imperial","year":"2018","journal-title":"Nat Med"},{"key":"2026092314160902000_jiag149-B5","doi-asserted-by":"crossref","first-page":"1086","DOI":"10.1164\/rccm.202101-0117OC","article-title":"Precision-enhancing risk stratification tools for selecting optimal treatment durations in tuberculosis clinical trials","volume":"204","author":"Imperial","year":"2021","journal-title":"Am J Respir Crit Care Med"},{"key":"2026092314160902000_jiag149-B6","doi-asserted-by":"crossref","first-page":"773","DOI":"10.1186\/s13063-023-07701-6","article-title":"Evaluating newly approved drugs in combination regimens for multidrug-resistant tuberculosis with fluoroquinolone resistance (endTB-Q): study protocol for a multi-country randomized controlled trial","volume":"24","author":"Patil","year":"2023","journal-title":"Trials"},{"key":"2026092314160902000_jiag149-B7","doi-asserted-by":"crossref","first-page":"1705","DOI":"10.1056\/NEJMoa2033400","article-title":"Four-month rifapentine regimens with or without moxifloxacin for tuberculosis","volume":"384","author":"Dorman","year":"2021","journal-title":"N Engl J Med"},{"key":"2026092314160902000_jiag149-B8"},{"key":"2026092314160902000_jiag149-B9","doi-asserted-by":"crossref","first-page":"e183779","DOI":"10.1001\/jamanetworkopen.2018.3779","article-title":"Assessment of validity of a blood-based 3-gene signature score for progression and diagnosis of tuberculosis, disease severity, and treatment response","volume":"1","author":"Warsinske","year":"2018","journal-title":"JAMA Netw Open"},{"key":"2026092314160902000_jiag149-B10","doi-asserted-by":"crossref","first-page":"825","DOI":"10.3109\/00365548.2013.826876","article-title":"TBscore II: refining and validating a simple clinical score for treatment monitoring of patients with pulmonary tuberculosis","volume":"45","author":"Rudolf","year":"2013","journal-title":"Scand J Infect Dis"},{"key":"2026092314160902000_jiag149-B11","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":"2026092314160902000_jiag149-B12","doi-asserted-by":"crossref","first-page":"e0226507","DOI":"10.1371\/journal.pone.0226507","article-title":"Factors predictive of the success of tuberculosis treatment: a systematic review with meta-analysis","volume":"14","author":"Chaves Torres","year":"2019","journal-title":"PLoS One"},{"key":"2026092314160902000_jiag149-B13","doi-asserted-by":"crossref","first-page":"81","DOI":"10.1186\/1741-7015-9-81","article-title":"The impact of diabetes on tuberculosis treatment outcomes: a systematic review","volume":"9","author":"Baker","year":"2011","journal-title":"BMC Med"},{"key":"2026092314160902000_jiag149-B14","doi-asserted-by":"crossref","first-page":"303","DOI":"10.1016\/j.trstmh.2012.01.011","article-title":"Risk factors for unfavorable outcome of pulmonary tuberculosis in adults in Taipei, Taiwan","volume":"106","author":"Yen","year":"2012","journal-title":"Trans R Soc Trop Med Hyg"},{"key":"2026092314160902000_jiag149-B15","doi-asserted-by":"crossref","first-page":"1588","DOI":"10.1056\/NEJMoa1315817","article-title":"A four-month gatifloxacin-containing regimen for treating tuberculosis","volume":"371","author":"Merle","year":"2014","journal-title":"N Engl J Med"},{"key":"2026092314160902000_jiag149-B16","doi-asserted-by":"crossref","first-page":"e0257647","DOI":"10.1371\/journal.pone.0257647","article-title":"Predictors of unfavorable responses to therapy in rifampicin-sensitive pulmonary tuberculosis using an integrated approach of radiological presentation and sputum mycobacterial burden","volume":"16","author":"Gopalan","year":"2021","journal-title":"PLoS One"},{"key":"2026092314160902000_jiag149-B17","doi-asserted-by":"crossref","first-page":"1214","DOI":"10.1164\/rccm.202107-1779OC","article-title":"An all-oral 6-month regimen for multidrug-resistant tuberculosis: a multicenter, randomized controlled clinical trial (the NExT study)","volume":"205","author":"Esmail","year":"2022","journal-title":"Am J Respir Crit Care Med"},{"key":"2026092314160902000_jiag149-B18","doi-asserted-by":"crossref","first-page":"873","DOI":"10.1056\/NEJMoa2212537","article-title":"Treatment strategy for rifampin-susceptible tuberculosis","volume":"388","author":"Paton","year":"2023","journal-title":"N Engl J Med"},{"key":"2026092314160902000_jiag149-B19","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":"2026092314160902000_jiag149-B20","doi-asserted-by":"crossref","first-page":"23895","DOI":"10.1038\/s41598-021-03265-0","article-title":"Independent evaluation of 12 artificial intelligence solutions for the detection of tuberculosis","volume":"11","author":"Codlin","year":"2021","journal-title":"Sci Rep"},{"key":"2026092314160902000_jiag149-B21","doi-asserted-by":"crossref","first-page":"e0224445","DOI":"10.1371\/journal.pone.0224445","article-title":"Performance of Qure.ai automatic classifiers against a large annotated database of patients with diverse forms of tuberculosis","volume":"15","author":"Engle","year":"2020","journal-title":"PLoS One"},{"key":"2026092314160902000_jiag149-B22","doi-asserted-by":"crossref","first-page":"1669","DOI":"10.1093\/cid\/ciae055","article-title":"Serial mass screening for tuberculosis among incarcerated persons in Brazil","volume":"78","author":"Pivetta de Araujo","year":"2024","journal-title":"Clin Infect Dis"},{"key":"2026092314160902000_jiag149-B23","doi-asserted-by":"crossref","first-page":"3267","DOI":"10.1128\/JCM.01013-17","article-title":"The TB Portals: an open-access, web-based platform for global drug-resistant-tuberculosis data sharing and analysis","volume":"55","author":"Rosenthal","year":"2017","journal-title":"J Clin Microbiol"},{"key":"2026092314160902000_jiag149-B24"},{"key":"2026092314160902000_jiag149-B25","first-page":"2825","article-title":"Scikit-learn: machine learning in Python","volume":"12","author":"Pedregosa","year":"2011","journal-title":"J Mach Learn Res"},{"key":"2026092314160902000_jiag149-B26","first-page":"1","article-title":"Statsmodels: econometric and statistical modeling with Python","volume":"7","author":"Seabold","year":"2010","journal-title":"SciPy"},{"key":"2026092314160902000_jiag149-B27","first-page":"231","article-title":"TorchXRayVision: a library of chest X-ray datasets and models. In:","volume":"172","author":"Cohen","year":"2022","journal-title":"Proceedings of the 5th International Conference on Medical Imaging with Deep Learning,"},{"key":"2026092314160902000_jiag149-B28","doi-asserted-by":"crossref","first-page":"2173","DOI":"10.1007\/s10278-024-01052-7","article-title":"Automated pulmonary tuberculosis severity assessment on chest X-rays","volume":"37","author":"Kantipudi","year":"2024","journal-title":"J Imaging Inform Med"},{"key":"2026092314160902000_jiag149-B29","doi-asserted-by":"crossref","first-page":"1677","DOI":"10.1093\/cid\/ciae058","article-title":"For tuberculosis, not \u201cto screen or not to screen?\u201d but \u201cwho?\u201d and \u201chow?\u201d","volume":"78","author":"Farhat","year":"2024","journal-title":"Clin Infect Dis"},{"key":"2026092314160902000_jiag149-B30"},{"key":"2026092314160902000_jiag149-B31","doi-asserted-by":"crossref","first-page":"837","DOI":"10.1016\/S0009-9260(97)80078-5","article-title":"Radiological features of pulmonary tuberculosis in 963 HIV-infected adults at three Central African hospitals","volume":"52","author":"Tshibwabwa-Tumba","year":"1997","journal-title":"Clin Radiol"},{"key":"2026092314160902000_jiag149-B32","doi-asserted-by":"publisher","author":"Kulkarni","DOI":"10.1101\/2025.08.05.25333066"},{"key":"2026092314160902000_jiag149-B33","doi-asserted-by":"crossref","first-page":"100518","DOI":"10.1016\/j.ejro.2023.100518","article-title":"Predictive capabilities of baseline radiological findings for early and late disease outcomes within sensitive and multi-drug resistant tuberculosis cases","volume":"11","author":"Rosenfeld","year":"2023","journal-title":"Eur J Radiol Open"},{"key":"2026092314160902000_jiag149-B34","doi-asserted-by":"publisher","DOI":"10.1093\/cid\/ciaf467","article-title":"Characterizing treatment adherence trajectories in the endTB multisite cohort of drug-resistant tuberculosis patients: an application of group-based trajectory modeling [manuscript published online ahead of print 22 August 2025]","author":"Law","year":"2025","journal-title":"Clin Infect Dis"}],"container-title":["The Journal of Infectious Diseases"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/jid\/advance-article-pdf\/doi\/10.1093\/infdis\/jiag149\/68079869\/jiag149.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/jid\/article-pdf\/234\/3\/e600\/68079869\/jiag149.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/jid\/article-pdf\/234\/3\/e600\/68079869\/jiag149.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,23]],"date-time":"2026-09-23T18:16:23Z","timestamp":1790187383000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/jid\/article\/234\/3\/e600\/8653949"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,16]]},"references-count":34,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2026,4,16]]},"published-print":{"date-parts":[[2026,9,23]]}},"URL":"https:\/\/doi.org\/10.1093\/infdis\/jiag149","relation":{},"ISSN":["0022-1899","1537-6613"],"issn-type":[{"value":"0022-1899","type":"print"},{"value":"1537-6613","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2026,9,15]]},"published":{"date-parts":[[2026,4,16]]}}}