{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T05:10:57Z","timestamp":1780377057204,"version":"3.54.1"},"reference-count":25,"publisher":"Public Library of Science (PLoS)","issue":"1","license":[{"start":{"date-parts":[[2025,1,23]],"date-time":"2025-01-23T00:00:00Z","timestamp":1737590400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"German Ministry for Education and Research"}],"content-domain":{"domain":["www.plosdigitalhealth.org"],"crossmark-restriction":false},"short-container-title":["PLOS Digit Health"],"abstract":"<jats:p>AI based software, including computer aided detection software for chest radiographs (CXR-CAD), was developed during the pandemic to improve COVID-19 case finding and triage. In high burden TB countries, the use of highly portable CXR and computer aided detection software has been adopted more broadly to improve the screening and triage of individuals for TB, but there is little evidence in these settings regarding COVID-19 CAD performance. We performed a multicenter, retrospective cross-over study evaluating CXRs from individuals at risk for COVID-19. We evaluated performance of CAD software and radiologists in comparison to COVID-19 laboratory results in 671 individuals evaluated for COVID-19 at sites in Zambia and Malawi between January 2021 and June 2022. All CXRs were interpreted by an expert radiologist and two commercially available COVID-19 CXR-CAD software. Radiologists interpreted CXRs for COVID-19 with a sensitivity of 73% (95% CI: 69%- 76%) and specificity of 49% (95% CI: 40%-58%). One CAD software (CAD2) showed performance in diagnosing COVID-19 that was comparable to that of radiologists, (AUC-ROC of 0.70 (95% CI: 0.65\u20130.75)), while a second (CAD1) showed inferior performance (AUC-ROC of 0.57 (95% CI: 0.52\u20130.63)). Agreement between CAD software and radiologists was moderate for diagnosing COVID-19, and agreement was very good in differentiating normal and abnormal CXRs in this high prevalent population. The study highlights the potential of CXR-CAD as a tool to support effective triage of individuals in Malawi and Zambia during the pandemic, particularly for distinguishing normal from abnormal CXRs. These findings suggest that while current AI-based diagnostics like CXR-CAD show promise, their effectiveness varies significantly. In order to better prepare for future pandemics, there is a need for representative training data to optimize performance in key populations, and ongoing data collection to maintain diagnostic accuracy, especially as new disease strains emerge.<\/jats:p>","DOI":"10.1371\/journal.pdig.0000535","type":"journal-article","created":{"date-parts":[[2025,1,23]],"date-time":"2025-01-23T13:33:01Z","timestamp":1737639181000},"page":"e0000535","update-policy":"https:\/\/doi.org\/10.1371\/journal.pdig.corrections_policy","source":"Crossref","is-referenced-by-count":3,"title":["A comparison of CXR-CAD software to radiologists in identifying COVID-19 in individuals evaluated for Sars CoV-2 infection in Malawi and Zambia"],"prefix":"10.1371","volume":"4","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1391-5715","authenticated-orcid":true,"given":"Sam","family":"Linsen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aur\u00e9lie","family":"Kamoun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andrews","family":"Gunda","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tamara","family":"Mwenifumbo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chancy","family":"Chavula","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lindiwe","family":"Nchimunya","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yucheng","family":"Tsai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Namwaka","family":"Mulenga","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Godfrey","family":"Kadewele","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Eunice Nahache","family":"Kajombo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Veronica","family":"Sunkutu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jane","family":"Shawa","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rigveda","family":"Kadam","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1107-7754","authenticated-orcid":true,"given":"Matthew","family":"Arentz","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2025,1,23]]},"reference":[{"key":"pdig.0000535.ref001","unstructured":"COVID-19 Estimates Downloads [Internet]. INSTITUTE FOR HEALTH METRICS AND EVALUATION; Available from: http:\/\/www.healthdata.org\/covid\/data-downloads"},{"issue":"10359","key":"pdig.0000535.ref002","doi-asserted-by":"crossref","first-page":"1224","DOI":"10.1016\/S0140-6736(22)01585-9","article-title":"The Lancet Commission on lessons for the future from the COVID-19 pandemic","volume":"400","author":"JD Sachs","year":"2022","journal-title":"Lancet Lond Engl"},{"issue":"10334","key":"pdig.0000535.ref003","doi-asserted-by":"crossref","first-page":"1513","DOI":"10.1016\/S0140-6736(21)02796-3","article-title":"Estimating excess mortality due to the COVID-19 pandemic: a systematic analysis of COVID-19-related mortality, 2020\u201321","volume":"399","author":"COVID-19 Excess Mortality Collaborators","year":"2022","journal-title":"Lancet Lond Engl."},{"issue":"2","key":"pdig.0000535.ref004","doi-asserted-by":"crossref","first-page":"e0277843","DOI":"10.1371\/journal.pone.0277843","article-title":"Early user experience and lessons learned using ultra-portable digital X-ray with computer-aided detection (DXR-CAD) products: A qualitative study from the perspective of healthcare providers.","volume":"18","author":"ZZ Qin","year":"2023","journal-title":"PloS One."},{"key":"pdig.0000535.ref005","doi-asserted-by":"crossref","first-page":"100360","DOI":"10.1016\/j.ejro.2021.100360","article-title":"Chest radiograph characteristics in COVID-19 infection and their association with survival","volume":"8","author":"J Colman","year":"2021","journal-title":"Eur J Radiol Open"},{"issue":"1","key":"pdig.0000535.ref006","doi-asserted-by":"crossref","first-page":"21019","DOI":"10.1038\/s41598-022-25397-7","article-title":"Chest x-ray imaging score is associated with severity of COVID-19 pneumonia: the MBrixia score","volume":"12","author":"CM Jensen","year":"2022","journal-title":"Sci Rep"},{"key":"pdig.0000535.ref007","doi-asserted-by":"crossref","first-page":"101034","DOI":"10.1016\/j.eclinm.2021.101034","article-title":"How to improve access to medical imaging in low- and middle-income countries?","volume":"38","author":"G Frija","year":"2021","journal-title":"EClinicalMedicine"},{"key":"pdig.0000535.ref008","doi-asserted-by":"crossref","first-page":"105134","DOI":"10.1016\/j.compbiomed.2021.105134","article-title":"A computer-aided diagnosis system for the classification of COVID-19 and non-COVID-19 pneumonia on chest X-ray images by integrating CNN with sparse autoencoder and feed forward neural network","volume":"141","author":"JL Gayathri","year":"2022","journal-title":"Comput Biol Med"},{"key":"pdig.0000535.ref009","unstructured":"Stop TB Partnership and FIND resource centre on computer-aided detection products for the diagnosis of tuberculosis [Internet]. Available from: https:\/\/www.ai4hlth.org\/"},{"issue":"7","key":"pdig.0000535.ref010","doi-asserted-by":"crossref","first-page":"825","DOI":"10.1007\/s10439-022-02958-5","article-title":"Detection of COVID-19 from CT and Chest X-ray Images Using Deep Learning Models","volume":"50","author":"W Zouch","year":"2022","journal-title":"Ann Biomed Eng"},{"key":"pdig.0000535.ref011","unstructured":"Use of chest imaging in COVID-19: a rapid advice guide [Internet]. Geneva, World Health Organization; 2020. Available from: https:\/\/www.who.int\/publications\/i\/item\/use-of-chest-imaging-in-covid-19"},{"key":"pdig.0000535.ref012","unstructured":"National Digital Health Strategy 2020\u20132025 2020 [Internet]. Health GoMMo; Available from: https:\/\/www.healthdatacollaborative.org\/fileadmin\/uploads\/hdc\/Documents\/Country_documents\/Malawi\/Malawi_Digital_Health_Strategy__20-25.pdf"},{"key":"pdig.0000535.ref013","unstructured":"Digital Health Strategy 2022\u20132026 2022 [Internet]. Republic of Zambia Ministry of Health; Available from: https:\/\/www.moh.gov.zm\/wp-content\/uploads\/filebase\/guidelines\/presentations\/Digital-Health\/Digital-Health-strategy- final.pdf"},{"key":"pdig.0000535.ref014","doi-asserted-by":"crossref","DOI":"10.1201\/9781315183084","volume-title":"Sample Size Calculations in Clinical Research","author":"SC Chow","year":"2017"},{"issue":"7","key":"pdig.0000535.ref015","doi-asserted-by":"crossref","first-page":"e0000402","DOI":"10.1371\/journal.pgph.0000402","article-title":"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","volume":"3","author":"SM Gelaw","year":"2023","journal-title":"PLOS Glob Public Health."},{"key":"pdig.0000535.ref016","unstructured":"List of SARS-CoV-2 Diagnostic test kits and equipment eligible for procurement according to Board Decision on Additional Support for Country Responses to COVID-19 2022 [Internet]. The Global Fund; Available from: https:\/\/www.theglobalfund.org\/media\/9629\/covid19_diagnosticproducts_list_en.pdf"},{"issue":"9","key":"pdig.0000535.ref017","doi-asserted-by":"crossref","first-page":"710.e9","DOI":"10.1016\/j.crad.2020.06.005","article-title":"Validation of the British Society of Thoracic Imaging guidelines for COVID-19 chest radiograph reporting","volume":"75","author":"SS Hare","year":"2020","journal-title":"Clin Radiol"},{"key":"pdig.0000535.ref018","first-page":"102049","article-title":"A new resource on artificial intelligence powered computer automated detection software products for tuberculosis programmes and implementers","volume":"127","author":"ZZ Qin","year":"2021","journal-title":"Tuberc Edinb Scotl"},{"issue":"2","key":"pdig.0000535.ref019","doi-asserted-by":"crossref","first-page":"e230327","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":"pdig.0000535.ref020","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":"AJ Codlin","year":"2021","journal-title":"Sci Rep"},{"key":"pdig.0000535.ref021","doi-asserted-by":"crossref","first-page":"77","DOI":"10.1186\/1471-2105-12-77","article-title":"pROC: an open-source package for R and S+ to analyze and compare ROC curves.","volume":"12","author":"X Robin","year":"2011","journal-title":"BMC Bioinformatics"},{"issue":"Pt 1","key":"pdig.0000535.ref022","doi-asserted-by":"crossref","first-page":"29","DOI":"10.1348\/000711006X126600","article-title":"Computing inter-rater reliability and its variance in the presence of high agreement.","volume":"61","author":"KL Gwet","year":"2008","journal-title":"Br J Math Stat Psychol"},{"issue":"3","key":"pdig.0000535.ref023","doi-asserted-by":"crossref","first-page":"e221795","DOI":"10.1148\/radiol.221795","article-title":"SARS-CoV-2 Variants Infection in Relationship to Imaging-based Pneumonia and Clinical Outcomes","volume":"306","author":"JE Lee","year":"2023","journal-title":"Radiology"},{"key":"pdig.0000535.ref024","unstructured":"Focus Group on Artificial Intelligence for Health. Clinical evaluation of AI for health [Internet]. International Telecommunication Union; 2023 Mar. Report No.: FG-AI4H DEL7.4. Available from: https:\/\/www.itu.int\/dms_pub\/itu-t\/opb\/fg\/T-FG-AI4H-2023-3-PDF-E.pdf"},{"key":"pdig.0000535.ref025","unstructured":"Regulatory considerations on artificial intelligence for health [Internet]. Geneva: World Health Organization; 2023. Available from: https:\/\/iris.who.int\/bitstream\/handle\/10665\/373421\/9789240078871-eng.pdf"}],"container-title":["PLOS Digital Health"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pdig.0000535","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,23]],"date-time":"2025-01-23T13:33:25Z","timestamp":1737639205000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pdig.0000535"}},"subtitle":[],"editor":[{"given":"Catherine G.","family":"Bielick","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2025,1,23]]},"references-count":25,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,1,23]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pdig.0000535","relation":{"has-preprint":[{"id-type":"doi","id":"10.1101\/2024.05.19.24307603","asserted-by":"object"}]},"ISSN":["2767-3170"],"issn-type":[{"value":"2767-3170","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,1,23]]}}}