{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,22]],"date-time":"2026-07-22T13:51:39Z","timestamp":1784728299083,"version":"3.55.0"},"reference-count":29,"publisher":"Public Library of Science (PLoS)","issue":"3","license":[{"start":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T00:00:00Z","timestamp":1774569600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:sec id=\"sec001\">\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Tuberculosis remains a major global health challenge, particularly in resource-limited settings where access to expert radiological interpretation is constrained. Artificial intelligence offers a promising solution to enhance diagnostic accuracy and efficiency in TB screening.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"sec002\">\n                    <jats:title>Aim<\/jats:title>\n                    <jats:p>This study aimed to evaluate the diagnostic performance of an AI-based system compared to a radiologist in screening for TB using chest X-rays from 1,010 patients.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"sec003\">\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>Patients were adults \u226518 years with suspected TB in a high-burden setting. GeneXpert MTB\/RIF served as reference to assess accuracy, sensitivity, specificity, PPV, NPV, and AUC for radiologist and AI TB predictions. Comparisons used McNemar\u2019s test and Cohen\u2019s kappa to evaluate agreement and significance of differences.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"sec004\">\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The AI system demonstrated superior performance with an accuracy of 91%, sensitivity of 86%, specificity of 93%, PPV of 85%, NPV of 94%, and AUC of 0.90. In contrast, the radiologist achieved an accuracy of 86%, sensitivity of 84%, specificity of 87%, PPV of 76%, NPV of 92%, and AUC of 0.86. McNemar\u2019s test revealed a statistically significant difference between the two modalities (p\u2009=\u20090.0021). Cohen\u2019s kappa indicated substantial agreement between AI and GeneXpert MTB\/RIF result (\u03ba\u2009=\u20090.79), moderate agreement for the radiologist and GeneXpert MTB\/RIF result (\u03ba\u2009=\u20090.69), and moderate agreement between radiologist and AI predictions (\u03ba\u2009=\u20090.53).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"sec005\">\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>The AI system outperformed the radiologist in TB screening, demonstrating higher diagnostic accuracy and agreement with GeneXpert MTB\/RIF result. These findings support the integration of AI into TB screening workflows, particularly in settings with limited access to expert radiological interpretation.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1371\/journal.pone.0342988","type":"journal-article","created":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T17:42:08Z","timestamp":1774633328000},"page":"e0342988","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":3,"title":["Diagnostic accuracy of AI-assisted chest radiographs in tuberculosis screening: A Ghanaian clinical study"],"prefix":"10.1371","volume":"21","author":[{"given":"Derick Seyram","family":"Sule","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kofi Adesi","family":"Kyei","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"William Kwadwo","family":"Antwi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Godwill","family":"Acquah","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6322-5341","authenticated-orcid":true,"given":"Klenam","family":"Dzefi-Tettey","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1466-150X","authenticated-orcid":true,"given":"Joseph","family":"Daniels","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0742-6007","authenticated-orcid":true,"given":"Andrew Yaw","family":"Nyantakyi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2026,3,27]]},"reference":[{"issue":"1","key":"pone.0342988.ref001","doi-asserted-by":"crossref","first-page":"206","DOI":"10.1186\/s12879-025-10622-1","article-title":"Completeness of tuberculosis case notification in Ghana: record linkage and capture-recapture analysis of three TB registries","volume":"25","author":"MP Kwabla","year":"2025","journal-title":"BMC Infect Dis"},{"issue":"1","key":"pone.0342988.ref002","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":"J Yayan","year":"2024","journal-title":"Pneumonia (Nathan)"},{"key":"pone.0342988.ref003","doi-asserted-by":"crossref","first-page":"100556","DOI":"10.1016\/j.ijregi.2024.100556","article-title":"Advancing tuberculosis elimination in India: a qualitative review of current strategies and areas for improvement in TB preventive treatment","volume":"14","author":"H Shah","year":"2024","journal-title":"IJID Reg"},{"issue":"9","key":"pone.0342988.ref004","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":"ZZ Qin","year":"2021","journal-title":"Lancet Digit Health"},{"key":"pone.0342988.ref005","doi-asserted-by":"crossref","first-page":"204","DOI":"10.4103\/ijmr.ijmr_845_22","article-title":"A comparison of the quality of images of chest X-ray between handheld portable digital X-ray & routinely used digital X-ray machine","volume":"157","author":"R Kamal","year":"2023","journal-title":"Indian J Med Res"},{"issue":"2","key":"pone.0342988.ref006","doi-asserted-by":"crossref","first-page":"278","DOI":"10.4046\/trd.2024.0062","article-title":"Application of artificial intelligence in thoracic radiology: a narrative review","volume":"88","author":"WH Lim","year":"2025","journal-title":"Tuberc Respir Dis (Seoul)"},{"key":"pone.0342988.ref007","doi-asserted-by":"crossref","first-page":"3223","DOI":"10.21037\/jtd-2025-604","article-title":"A systematic review and meta-analysis of artificial intelligence software for tuberculosis diagnosis using chest X-ray imaging","volume":"17","author":"ZL Han","year":"2025","journal-title":"J Thorac Dis"},{"key":"pone.0342988.ref008","doi-asserted-by":"crossref","first-page":"1512910","DOI":"10.3389\/frai.2025.1512910","article-title":"Clinical validation of an artificial intelligence algorithm for classifying tuberculosis and pulmonary findings in chest radiographs","volume":"8","author":"TFO de Camargo","year":"2025","journal-title":"Front Artif Intell"},{"issue":"9","key":"pone.0342988.ref009","doi-asserted-by":"crossref","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":"M Harris","year":"2019","journal-title":"PLoS One"},{"issue":"11","key":"pone.0342988.ref010","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":"KC Santosh","year":"2022","journal-title":"J Med Syst"},{"key":"pone.0342988.ref011","doi-asserted-by":"crossref","first-page":"81","DOI":"10.18517\/ijaseit.9.1.7567","article-title":"Artificial intelligence in diagnosing tuberculosis: a review","volume":"9","author":"S Meraj","year":"2019","journal-title":"Int J Adv Sci Eng Inf Technol"},{"issue":"9","key":"pone.0342988.ref012","doi-asserted-by":"crossref","first-page":"1060","DOI":"10.3390\/healthcare13091060","article-title":"Integrating digital health innovations to achieve universal health coverage: promoting health outcomes and quality through global public health equity","volume":"13","author":"MM Ahmed","year":"2025","journal-title":"Healthcare (Basel)"},{"issue":"2","key":"pone.0342988.ref013","doi-asserted-by":"crossref","DOI":"10.1148\/ryai.230327","article-title":"AI for detection of tuberculosis: implications for global health","volume":"6","author":"EJ Hwang","year":"2024","journal-title":"Radiol Artif Intell"},{"issue":"1","key":"pone.0342988.ref014","doi-asserted-by":"crossref","first-page":"17","DOI":"10.1186\/s44263-023-00017-2","article-title":"Comparing tuberculosis symptom screening to chest X-ray with artificial intelligence in an active case finding campaign in Northeast Nigeria","volume":"1","author":"S John","year":"2023","journal-title":"BMC Glob Public Health"},{"key":"pone.0342988.ref015","doi-asserted-by":"crossref","first-page":"100505","DOI":"10.1016\/j.smhl.2024.100505","article-title":"Application of medical artificial intelligence technology in sub-Saharan Africa: prospects for medical laboratories","volume":"33","author":"RK Dadzie Ephraim","year":"2024","journal-title":"Smart Health"},{"issue":"1","key":"pone.0342988.ref016","doi-asserted-by":"crossref","first-page":"755","DOI":"10.1186\/s12913-023-09755-3","article-title":"Geographic availability of and physical accessibility to tuberculosis diagnostic tests in Ghana: a cross-sectional survey","volume":"23","author":"D Kuupiel","year":"2023","journal-title":"BMC Health Serv Res"},{"issue":"6","key":"pone.0342988.ref017","doi-asserted-by":"crossref","first-page":"184","DOI":"10.3390\/diseases13060184","article-title":"Integration of AI and ML in tuberculosis (TB) management: from diagnosis to drug discovery","volume":"13","author":"S Memon","year":"2025","journal-title":"Diseases"},{"issue":"4","key":"pone.0342988.ref018","doi-asserted-by":"crossref","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":"M Muyoyeta","year":"2014","journal-title":"PLoS One"},{"issue":"2","key":"pone.0342988.ref019","doi-asserted-by":"crossref","first-page":"574","DOI":"10.1148\/radiol.2017162326","article-title":"Deep learning at chest radiography: automated classification of pulmonary tuberculosis by using convolutional neural networks","volume":"284","author":"P Lakhani","year":"2017","journal-title":"Radiology"},{"issue":"1","key":"pone.0342988.ref020","doi-asserted-by":"crossref","first-page":"14917","DOI":"10.1038\/s41598-024-65703-z","article-title":"A deep learning-based algorithm for pulmonary tuberculosis detection in chest radiography","volume":"14","author":"C-F Chen","year":"2024","journal-title":"Sci Rep"},{"issue":"17","key":"pone.0342988.ref021","doi-asserted-by":"crossref","first-page":"2760","DOI":"10.3390\/diagnostics13172760","article-title":"Redefining radiology: a review of artificial intelligence integration in medical imaging","volume":"13","author":"R Najjar","year":"2023","journal-title":"Diagnostics (Basel)"},{"issue":"3","key":"pone.0342988.ref022","doi-asserted-by":"crossref","first-page":"489","DOI":"10.1007\/s12553-025-00970-y","article-title":"The role of AI in mitigating the impact of radiologist shortages: a systematised review","volume":"15","author":"N Achour","year":"2025","journal-title":"Health Technol (Berl)"},{"issue":"3","key":"pone.0342988.ref023","doi-asserted-by":"crossref","first-page":"324","DOI":"10.3390\/healthcare13030324","article-title":"Investigation into application of AI and telemedicine in rural communities: a systematic literature review","volume":"13","author":"K Perez","year":"2025","journal-title":"Healthcare"},{"issue":"8","key":"pone.0342988.ref024","doi-asserted-by":"crossref","first-page":"1828","DOI":"10.51594\/csitrj.v5i8.1447","article-title":"The impact of artificial intelligence on early diagnosis of chronic diseases in rural areas","volume":"5","author":"EV Emeihe","year":"2024","journal-title":"Comput Sci IT Res J"},{"key":"pone.0342988.ref025","doi-asserted-by":"crossref","first-page":"1433450","DOI":"10.3389\/fpubh.2025.1433450","article-title":"Artificial intelligence: a useful tool in active tuberculosis screening among vulnerable groups in Romania - advantages and limitations","volume":"13","author":"B Mahler","year":"2025","journal-title":"Front Public Health"},{"issue":"2","key":"pone.0342988.ref026","first-page":"75","article-title":"Bias in artificial intelligence for medical imaging: fundamentals, detection, avoidance, mitigation, challenges, ethics, and prospects","volume":"31","author":"B Ko\u00e7ak","year":"2025","journal-title":"Diagn Interv Radiol"},{"issue":"12","key":"pone.0342988.ref027","doi-asserted-by":"crossref","first-page":"2176","DOI":"10.1038\/s41591-021-01595-0","article-title":"Underdiagnosis bias of artificial intelligence algorithms applied to chest radiographs in under-served patient populations","volume":"27","author":"L Seyyed-Kalantari","year":"2021","journal-title":"Nat Med"},{"key":"pone.0342988.ref028","doi-asserted-by":"crossref","first-page":"842","DOI":"10.1016\/j.jacr.2023.06.025","article-title":"Shortcuts causing bias in radiology artificial intelligence: causes, evaluation, and mitigation","volume":"20","author":"I Banerjee","year":"2023","journal-title":"J Am Coll Radiol"},{"issue":"4","key":"pone.0342988.ref029","doi-asserted-by":"crossref","DOI":"10.1016\/j.heliyon.2024.e26297","article-title":"Ethical and regulatory challenges of AI technologies in healthcare: a narrative review","volume":"10","author":"C Mennella","year":"2024","journal-title":"Heliyon"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0342988","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T17:42:13Z","timestamp":1774633333000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0342988"}},"subtitle":[],"editor":[{"given":"Felix","family":"Bongomin","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,3,27]]},"references-count":29,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2026,3,27]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0342988","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,27]]}}}