{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T16:33:43Z","timestamp":1783010023615,"version":"3.54.5"},"reference-count":46,"publisher":"MDPI AG","issue":"12","license":[{"start":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T00:00:00Z","timestamp":1766016000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100010425","name":"Tri-Service General Hospital","doi-asserted-by":"crossref","award":["TSGH-B-114026"],"award-info":[{"award-number":["TSGH-B-114026"]}],"id":[{"id":"10.13039\/501100010425","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100010425","name":"Tri-Service General Hospital","doi-asserted-by":"crossref","award":["MND-MAB-C02-115007"],"award-info":[{"award-number":["MND-MAB-C02-115007"]}],"id":[{"id":"10.13039\/501100010425","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100010425","name":"Tri-Service General Hospital","doi-asserted-by":"crossref","award":["TSGH-E-114241"],"award-info":[{"award-number":["TSGH-E-114241"]}],"id":[{"id":"10.13039\/501100010425","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Bioengineering"],"abstract":"<jats:p>Tuberculosis (TB) remains a major global health challenge, and early, accurate diagnosis is essential for effective disease control. Chest radiography (CXR) is widely used for TB screening because of its accessibility, yet its limited specificity necessitates confirmatory molecular testing such as polymerase chain reaction (PCR) assays. This study aimed to evaluate the diagnostic performance of a deep learning model (DLM) for TB detection using CXR and to compare its predictive accuracy with PCR results, specifically in a low-burden region. A retrospective dataset of CXR images and corresponding PCR findings was obtained from two hospitals. The DLM, based on the CheXzero vision transformer, was trained on a large imaging dataset and evaluated using receiver operating characteristic (ROC) curves and area under the curve (AUC) metrics. Internal and external validation sets assessed sensitivity, specificity, and predictive values, with subgroup analyses according to imaging modality, demographics, and comorbidities. The model achieved an AUC of 0.915 internally and 0.850 externally, maintaining good sensitivity and specificity, though performance declined when limited to PCR-confirmed cases. Accuracy was lower for older adults and those with chronic kidney disease, chronic obstructive pulmonary disease, or heart failure. These findings suggest AI-assisted CXR screening may support TB detection in resource-limited settings, but PCR confirmation remains essential.<\/jats:p>","DOI":"10.3390\/bioengineering12121377","type":"journal-article","created":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T13:45:07Z","timestamp":1766065507000},"page":"1377","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Integrating AI with PCR for Tuberculosis Diagnosis: Evaluating a Deep Learning Model for Chest X-Rays"],"prefix":"10.3390","volume":"12","author":[{"given":"Wei-Cheng","family":"Chiu","sequence":"first","affiliation":[{"name":"Department of Family and Community Medicine, Tri-Service General Hospital, National Defense Medical University, Taipei 114, Taiwan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8944-174X","authenticated-orcid":false,"given":"Shan-Yueh","family":"Chang","sequence":"additional","affiliation":[{"name":"Division of Pulmonary and Critical Care Medicine, Department of Internal Medicine, School of Medicine, Tri-Service General Hospital, National Defense Medical University, Taipei 114, Taiwan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2337-2096","authenticated-orcid":false,"given":"Chin","family":"Lin","sequence":"additional","affiliation":[{"name":"Graduate Institute of Life Sciences, National Defense Medical University, Taipei 114, Taiwan, China"},{"name":"Medical Technology Education Center, School of Medicine, National Defense Medical University, Taipei 114, Taiwan, China"},{"name":"Department of Artificial Intelligence and Internet of Things, Tri-Service General Hospital, National Defense Medical University, Taipei 114, Taiwan, China"},{"name":"School of Public Health, National Defense Medical University, Taipei 114, Taiwan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Teng-Wei","family":"Chen","sequence":"additional","affiliation":[{"name":"Division of General Surgery, Department of Surgery, Tri-Service General Hospital, National Defense Medical University, Taipei 114, Taiwan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0574-5736","authenticated-orcid":false,"given":"Wen-Hui","family":"Fang","sequence":"additional","affiliation":[{"name":"Department of Family and Community Medicine, Tri-Service General Hospital, National Defense Medical University, Taipei 114, Taiwan, China"},{"name":"Medical Technology Education Center, School of Medicine, National Defense Medical University, Taipei 114, Taiwan, China"},{"name":"Artificial Intelligence of Things Center, Tri-Service General Hospital, National Defense Medical University, Taipei 114, Taiwan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2025,12,18]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"463","DOI":"10.1128\/CMR.16.3.463-496.2003","article-title":"Mycobacterium tuberculosis pathogenesis and molecular determinants of virulence","volume":"16","author":"Smith","year":"2003","journal-title":"Clin. Microbiol. Rev."},{"key":"ref_2","unstructured":"World Health Organization (2024). Global Tuberculosis Report 2024, World Health Organization."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"927","DOI":"10.1164\/ajrccm.165.7.2107040","article-title":"The Canadian Collaborative Group in Nosocomial Transmission of Tuberculosis. Delay in diagnosis among hospitalized patients with active tuberculosis\u2014Predictors and outcomes","volume":"165","author":"Greenaway","year":"2002","journal-title":"Am. J. Respir. Crit. Care Med."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Bello, S., Afolabi, R.F., Ajayi, D.T., Sharma, T., Owoeye, D.O., Oduyoye, O., and Jasanya, J. (2019). Empirical evidence of delays in diagnosis and treatment of pulmonary tuberculosis: Systematic review and meta-regression analysis. BMC Public Health, 19.","DOI":"10.1186\/s12889-019-7026-4"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Moule, M.G., and Cirillo, J.D. (2020). Mycobacterium tuberculosis Dissemination Plays a Critical Role in Pathogenesis. Front. Cell Infect. Microbiol., 10.","DOI":"10.3389\/fcimb.2020.00065"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"a017863","DOI":"10.1101\/cshperspect.a017863","article-title":"Multidrug-Resistant Tuberculosis and Extensively Drug-Resistant Tuberculosis","volume":"5","author":"Seung","year":"2015","journal-title":"Cold Spring Harb. Perspect. Med."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"2334","DOI":"10.1016\/S0140-6736(15)00322-0","article-title":"Turning off the tap: Stopping tuberculosis transmission through active case-finding and prompt effective treatment","volume":"386","author":"Yuen","year":"2015","journal-title":"Lancet"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Hoog, A.H.V., Meme, H.K., Laserson, K.F., Agaya, J.A., Muchiri, B.G., Githui, W.A., Odeny, L.O., Marston, B.J., and Borgdorff, M.W. (2012). Screening strategies for tuberculosis prevalence surveys: The value of chest radiography and symptoms. PLoS ONE, 7.","DOI":"10.1371\/journal.pone.0038691"},{"key":"ref_9","unstructured":"World Health Organization (2021). WHO Consolidated Guidelines on Tuberculosis. Module 2: Screening-Systematic Screening for Tuberculosis Disease, World Health Organization."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Esmail, A., Randall, P., Pooran, A., Oelofse, S., Calligaro, G., Warren, R., and Dheda, K. (2020). Impact of a Scalable Intervention Package, Including a Point-of-Care Molecular Diagnostic Tool, on Community-Based Active Case Finding for Tuberculosis: A Pragmatic Randomized Controlled Trial. C53. Global Experiences in TB and NTM Care, American Thoracic Society.","DOI":"10.1164\/ajrccm-conference.2020.201.1_MeetingAbstracts.A5456"},{"key":"ref_11","first-page":"CD009593","article-title":"Xpert\u00ae MTB\/RIF assay for pulmonary tuberculosis and rifampicin resistance in adults","volume":"2014","author":"Steingart","year":"2014","journal-title":"Cochrane Database Syst. Rev."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"18955","DOI":"10.1038\/s41598-021-98114-5","article-title":"A new qualitative RT-PCR assay detecting SARS-CoV-2","volume":"11","author":"Favaro","year":"2021","journal-title":"Sci. Rep."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Bartolomeu-Gon\u00e7alves, G., de Souza, J.M., Fernandes, B.T., Spoladori, L.F.A., Correia, G.F., de Castro, I.M., Borges, P.H.G., Silva-Rodrigues, G., Tavares, E.R., and Yamauchi, L.M. (2024). Tuberculosis Diagnosis: Current, Ongoing, and Future Approaches. Diseases, 12.","DOI":"10.3390\/diseases12090202"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Papageorgiou, V.\u0395., Papageorgiou, D.P., Petmezas, G., Dogoulis, P., Maglaveras, N., and Tsaklidis, G. (2025). Transfer Learning-Boosted CNN for Computationally Efficient Multi-Cancer Detection. Biotechnology and Health Sciences, Springer Nature.","DOI":"10.1007\/978-981-96-6103-9_1"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Papageorgiou, V.E., Dogoulis, P., and Papageorgiou, D.P. (2023). A convolutional neural network of low complexity for tumor anomaly detection. International Congress on Information and Communication Technology, Springer Nature.","DOI":"10.1007\/978-981-99-3236-8_78"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"547","DOI":"10.18280\/ts.380302","article-title":"Brain Tumor Detection Based on Features Extracted and Classified Using a Low-Complexity Neural Network","volume":"38","author":"Papageorgiou","year":"2021","journal-title":"Trait. Du Signal"},{"key":"ref_17","first-page":"77","article-title":"Boosting epidemic forecasting performance with enhanced RNN-type models","volume":"25","author":"Papageorgiou","year":"2025","journal-title":"Oper. Res."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"108557","DOI":"10.1016\/j.compbiomed.2024.108557","article-title":"Recent advancements and applications of deep learning in heart failure: A systematic review","volume":"176","author":"Petmezas","year":"2024","journal-title":"Comput. Biol. Med."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"528","DOI":"10.3934\/mbe.2025020","article-title":"Uncertainty CNNs: A path to enhanced medical image classification performance","volume":"22","author":"Papageorgiou","year":"2025","journal-title":"Math. Biosci. Eng."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"e30308","DOI":"10.1016\/j.heliyon.2024.e30308","article-title":"Contribution to pulmonary diseases diagnostic from X-ray images using innovative deep learning models","volume":"10","author":"Bennour","year":"2024","journal-title":"Heliyon"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"120","DOI":"10.1007\/s10916-025-02263-3","article-title":"A Pretraining Approach for Small-sample Training Employing Radiographs (PASTER): A Multimodal Transformer Trained by Chest Radiography and Free-text Reports","volume":"49","author":"Chen","year":"2025","journal-title":"J. Med. Syst."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"127976","DOI":"10.1016\/j.neucom.2024.127976","article-title":"DenseViT-XGB: A hybrid approach for dates varieties identification","volume":"596","author":"Neji","year":"2024","journal-title":"Neurocomputing"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"11","DOI":"10.1186\/s41479-024-00133-z","article-title":"Early detection of tuberculosis: A systematic review","volume":"16","author":"Yayan","year":"2024","journal-title":"Pneumonia"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Gelaw, S.M., Kik, S.V., Ruhwald, M., Ongarello, S., Egzertegegne, T.S., Gorbacheva, O., Gilpin, C., Marano, N., Lee, S., and Phares, C.R. (2023). Diagnostic accuracy of three computer-aided detection systems for detecting pulmonary tuberculosis on chest radiography when used for screening: Analysis of an international, multicenter migrants screening study. PLOS Glob. Public Health, 3.","DOI":"10.1371\/journal.pgph.0000402"},{"key":"ref_25","unstructured":"Crowder, R., Thangakunam, B., Andama, A., Christopher, D.J., Dalay, V., Nwamba, W., Kik, S.V., Van Nguyen, D., Nhung, N.V., and Phillips, P.P.J. (2024). Diagnostic accuracy of TB screening tests in a prospective multinational cohort: Chest-X-ray with computer-aided detection, Xpert TB host response, and C-reactive protein. Clin. Infect. Dis."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"e543","DOI":"10.1016\/S2589-7500(21)00116-3","article-title":"Tuberculosis detection from chest x-rays for triaging in a high tuberculosis-burden setting: An evaluation of five artificial intelligence algorithms","volume":"3","author":"Qin","year":"2021","journal-title":"Lancet Digit. Health"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Kak, N., Chakraborty, K., Sadaphal, S., AlMossawi, H.J., Calnan, M., and Vikarunnessa, B. (2020). Strategic priorities for TB control in Bangladesh, Indonesia, and the Philippines\u2014comparative analysis of national TB prevalence surveys. BMC Public Health, 20.","DOI":"10.1186\/s12889-020-08675-9"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Li, S., Mensah, E., Liu, M., Pan, L., Lu, W., Zhou, S., Zhang, L., Cheng, Y., Zhao, H., and Wei, S. (2025). The burden of tuberculosis and drug resistance in 22 Sub-Saharan African countries, 1990-2021: A GBD 2021 analysis and progress towards WHO 2035 targets with projections to 2050. Front. Microbiol., 16.","DOI":"10.3389\/fmicb.2025.1695592"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"29101","DOI":"10.1038\/s41598-024-80343-z","article-title":"Trends and annual percentage changes in tuberculosis mortality estimated by Joinpoint regression and age-period-cohort analyses, Taiwan, 1978-2022","volume":"14","author":"Chen","year":"2024","journal-title":"Sci. Rep."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"4138","DOI":"10.1128\/JCM.05434-11","article-title":"Evaluation of the GeneXpert MTB\/RIF assay for rapid diagnosis of tuberculosis and detection of rifampin resistance in pulmonary and extrapulmonary specimens","volume":"49","author":"Zeka","year":"2011","journal-title":"J. Clin. Microbiol."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"1399","DOI":"10.1038\/s41551-022-00936-9","article-title":"Expert-level detection of pathologies from unannotated chest X-ray images via self-supervised learning","volume":"6","author":"Tiu","year":"2022","journal-title":"Nat. Biomed. Eng."},{"key":"ref_32","unstructured":"Radford, A., Kim, J.W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., and Clark, J. (2021, January 18\u201324). Learning Transferable Visual Models From Natural Language Supervision. Proceedings of the 38th International Conference on Machine Learning, Virtual."},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Chetoui, M., and Akhloufi, M.A. (2022). Explainable Vision Transformers and Radiomics for COVID-19 Detection in Chest X-rays. J. Clin. Med., 11.","DOI":"10.3390\/jcm11113013"},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Chen, T., and Guestrin, C. (2016). XGBoost: A Scalable Tree Boosting System. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Association for Computing Machinery.","DOI":"10.1145\/2939672.2939785"},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Song, X., Zhu, J., Tan, X., Yu, W., Wang, Q., Shen, D., and Chen, W. (2022). XGBoost-Based Feature Learning Method for Mining COVID-19 Novel Diagnostic Markers. Front. Public Health, 10.","DOI":"10.3389\/fpubh.2022.926069"},{"key":"ref_36","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":"ref_37","doi-asserted-by":"crossref","first-page":"739","DOI":"10.1093\/cid\/ciy967","article-title":"Development and Validation of a Deep Learning-based Automatic Detection Algorithm for Active Pulmonary Tuberculosis on Chest Radiographs","volume":"69","author":"Hwang","year":"2019","journal-title":"Clin. Infect. Dis."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"124","DOI":"10.1148\/radiol.212213","article-title":"Deep Learning Detection of Active Pulmonary Tuberculosis at Chest Radiography Matched the Clinical Performance of Radiologists","volume":"306","author":"Kazemzadeh","year":"2023","journal-title":"Radiology"},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"1390","DOI":"10.1093\/cid\/ciab639","article-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","volume":"74","author":"Tavaziva","year":"2022","journal-title":"Clin. Infect. Dis."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"e43154","DOI":"10.2196\/43154","article-title":"Machine and Deep Learning for Tuberculosis Detection on Chest X-Rays: Systematic Literature Review","volume":"25","author":"Hansun","year":"2023","journal-title":"J. Med. Internet Res."},{"key":"ref_41","first-page":"35","article-title":"Application of artificial intelligence in digital chest radiography reading for pulmonary tuberculosis screening","volume":"7","author":"Cao","year":"2021","journal-title":"Chronic Dis. Transl. Med."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"52","DOI":"10.1148\/rg.2017160032","article-title":"Pulmonary Tuberculosis: Role of Radiology in Diagnosis and Management","volume":"37","author":"Nachiappan","year":"2017","journal-title":"Radiographics"},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"e04614","DOI":"10.1016\/j.heliyon.2020.e04614","article-title":"Deep learning for automated classification of tuberculosis-related chest X-Ray: Dataset distribution shift limits diagnostic performance generalizability","volume":"6","author":"Sathitratanacheewin","year":"2020","journal-title":"Heliyon"},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"82","DOI":"10.1007\/s10916-022-01870-8","article-title":"Advances in Deep Learning for Tuberculosis Screening using Chest X-rays: The Last 5 Years Review","volume":"46","author":"Santosh","year":"2022","journal-title":"J. Med. Syst."},{"key":"ref_45","doi-asserted-by":"crossref","unstructured":"Ayano, Y.M., Schwenker, F., Dufera, B.D., and Debelee, T.G. (2022). Interpretable Machine Learning Techniques in ECG-Based Heart Disease Classification: A Systematic Review. Diagnostics, 13.","DOI":"10.3390\/diagnostics13010111"},{"key":"ref_46","doi-asserted-by":"crossref","unstructured":"Bonyani, M., Yeganli, F., and Yeganli, S.F. (November, January 31). Fast and Interpretable Deep Learning Pipeline for Breast Cancer Recognition. Proceedings of the 2022 Medical Technologies Congress (TIPTEKNO), Belek, Turkey.","DOI":"10.1109\/TIPTEKNO56568.2022.9960227"}],"container-title":["Bioengineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2306-5354\/12\/12\/1377\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,20]],"date-time":"2025-12-20T05:12:43Z","timestamp":1766207563000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2306-5354\/12\/12\/1377"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,18]]},"references-count":46,"journal-issue":{"issue":"12","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["bioengineering12121377"],"URL":"https:\/\/doi.org\/10.3390\/bioengineering12121377","relation":{},"ISSN":["2306-5354"],"issn-type":[{"value":"2306-5354","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,18]]}}}