{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:43:04Z","timestamp":1785544984334,"version":"3.56.0"},"reference-count":51,"publisher":"JMIR Publications Inc.","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["JMIR Res Protoc"],"abstract":"Abstract<\/jats:title>\n \n Background<\/jats:title>\n Artificial intelligence (AI) has the potential to transform chest radiography interpretation by enhancing diagnostic accuracy, identifying subtle findings, reducing errors, and helping prioritize patient care. Although chest radiography remains a cost-effective and widely used imaging tool, its effectiveness is limited by overlapping anatomy and variability in clinical expertise. Integrating AI can help overcome some of these challenges, especially in resource-constrained settings. However, robust validation in real-world clinical contexts is essential before widespread implementation. This study protocol evaluates whether AI assistance improves general practitioners\u2019 ability to detect radiographic findings on chest radiography in adults with respiratory complaints or those undergoing treatment for respiratory diseases compared with unaided interpretation. Potential benefits include increased diagnostic safety, higher physician confidence, more efficient workflows, and expanded access to expert support in underserved areas.<\/jats:p>\n <\/jats:sec>\n \n Objective<\/jats:title>\n This study aims to evaluate whether AI assistance enhances physicians\u2019 ability to detect key radiographic abnormalities, including consolidation or pulmonary opacity, pneumothorax, atelectasis, pleural effusion, and cardiomegaly. The primary outcome is the difference in physicians\u2019 diagnostic accuracy (per examination) when assisted by the AI tool compared with usual practice, using expert radiologist consensus as the reference value.<\/jats:p>\n <\/jats:sec>\n \n Methods<\/jats:title>\n This study is a protocol for a multicenter, stepped-wedge, cluster-randomized clinical trial following the CONSORT-AI (Consolidated Standards of Reporting Trials-Artificial Intelligence) extension and SPIRIT-AI (Standard Protocol Items: Recommendations for Interventional Trials-Artificial Intelligence) guidelines. The intervention involves the diagnostic support solution for chest radiography, Lung Analysis (LuAna), an AI-powered chest X-ray interpretation tool developed in partnership with the Brazilian Ministry of Health. Across 9 cities in Brazil, clusters will transition monthly from unaided chest X-ray interpretation by general practitioners to AI-assisted interpretation, with performance benchmarked against thoracic radiologists. The stepped-wedge design ensures that all clusters receive the intervention, reflecting real-world coordination, enhancing acceptability, improving statistical power, and strengthening causal inference through repeated measures. Diagnostic performance will be compared with a reference standard established by thoracic radiologists.<\/jats:p>\n <\/jats:sec>\n \n Results<\/jats:title>\n This project was funded in October 2024 (following ethics approval by the institutional review board). Data collection commenced in January 2026 and is projected to be completed by September 2026, marking the end of the trial period. As of November 2025, 3 centers were fully prepared for enrollment initiation. The LuAna clinical trial is currently ongoing, with data analysis (including statistical analyses) forecasted to be finalized by November 2026. Results are expected to be published by January 2027.<\/jats:p>\n <\/jats:sec>\n \n Conclusions<\/jats:title>\n This intervention is expected to enhance clinical decision-making by supporting earlier treatment initiation and more appropriate diagnostic pathways for patients with respiratory symptoms while maintaining a favorable safety profile and high physician usability. Findings from this trial will provide real-world evidence on the clinical utility of AI-assisted chest radiography. If effective, LuAna may leverage its scalability and equity advantages to become a replicable model for integrating AI into routine imaging workflows worldwide, especially in regions with limited access to specialist care.<\/jats:p>\n <\/jats:sec>","DOI":"10.2196\/88626","type":"journal-article","created":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T09:00:05Z","timestamp":1773133205000},"page":"e88626-e88626","source":"Crossref","is-referenced-by-count":0,"title":["AI-Assisted Chest X-Ray Interpretation in Resource-Limited Settings: LuAna Stepped-Wedge Trial Protocol"],"prefix":"10.2196","volume":"15","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6616-302X","authenticated-orcid":false,"given":"Maria Carolina Bueno","family":"da Silva","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1601-3055","authenticated-orcid":false,"given":"Paula Bresciani M","family":"de Andrade","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1266-0095","authenticated-orcid":false,"given":"Henrique Min Ho","family":"Lee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-3048-8264","authenticated-orcid":false,"given":"Pedro Vinicius Alves","family":"Silva","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8922-7890","authenticated-orcid":false,"given":"Ana Cristina","family":"Ferreira","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-8360-1642","authenticated-orcid":false,"given":"Cintia Pereira","family":"Kuss","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9606-0328","authenticated-orcid":false,"given":"Maria Gabriela de Almeida","family":"Rodrigues","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2230-9573","authenticated-orcid":false,"given":"Guilherme Alberto Sousa","family":"Ribeiro","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6917-8339","authenticated-orcid":false,"given":"Thiago Fellipe Ortiz","family":"Camargo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-3050-3829","authenticated-orcid":false,"given":"William Yang Chen","family":"Fan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-0776-7051","authenticated-orcid":false,"given":"Pedro Vieira Santana","family":"Netto","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-1820-6151","authenticated-orcid":false,"given":"Giovanna de Souza","family":"Mendes","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1941-7899","authenticated-orcid":false,"given":"Gilberto","family":"Szarf","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1635-2225","authenticated-orcid":false,"given":"Rafael Maffei","family":"Loureiro","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1520-9387","authenticated-orcid":false,"given":"Ary","family":"Serpa Neto","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7487-397X","authenticated-orcid":false,"given":"Joselisa P\u00e9res Queiroz de","family":"Paiva","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8440-6590","authenticated-orcid":false,"given":"Jaqueline Driemeyer Correia","family":"Horvath","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1010","published-online":{"date-parts":[[2026,7,13]]},"reference":[{"key":"R1","unstructured":"Artificial intelligence for health: opportunities, risks, and governance. World Health Organization. 2024. URL: https:\/\/www.who.int\/news-room\/events\/detail\/2024\/05\/30\/default-calendar\/artificial-intelligence-for-health-opportunities-risks-and-governance [Accessed 19-05-2026]"},{"issue":"3","key":"R2","doi-asserted-by":"publisher","DOI":"10.1056\/AIp2400875","article-title":"The utility of generative AI in advancing global health","volume":"2","author":"Akbarialiabad","journal-title":"NEJM AI"},{"key":"R3","unstructured":"The 17 Goals. United Nations Sustainable Development Goals (SDGs). URL: https:\/\/sdgs.un.org\/goals [Accessed 19-05-2026]"},{"key":"R4","unstructured":"Rajpurkar P Irvin J Zhu K et al. CheXNet: radiologist-level pneumonia detection on chest X-rays with deep learning. arXiv. Preprint posted online on Nov 14, 2017. [doi: 10.48550\/arXiv.1711.05225]"},{"issue":"3","key":"R5","doi-asserted-by":"publisher","first-page":"573","DOI":"10.1148\/radiol.2019191225","article-title":"Deep learning for chest radiograph diagnosis in the emergency department","volume":"293","author":"Hwang","journal-title":"Radiology"},{"issue":"6","key":"R6","doi-asserted-by":"publisher","first-page":"1021","DOI":"10.1007\/s12553-025-00999-z","article-title":"Innovations in artificial intelligence to minimize diagnostic error - a comparison with human interpretation of chest radiographs in the clinical context: a scoping review","volume":"15","author":"Sierra","journal-title":"Health Technol"},{"issue":"2","key":"R7","doi-asserted-by":"publisher","first-page":"520","DOI":"10.1148\/radiol.2532082010","article-title":"Radiologic and nuclear medicine studies in the United States and worldwide: frequency, radiation dose, and comparison with other radiation sources\u20131950-2007","volume":"253","author":"Mettler","journal-title":"Radiology"},{"key":"R8","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2021.102125","article-title":"Deep learning for chest X-ray analysis: a survey","volume":"72","author":"\u00c7all\u0131","journal-title":"Med Image Anal"},{"issue":"6","key":"R9","doi-asserted-by":"publisher","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","journal-title":"Radiographics"},{"issue":"1","key":"R10","doi-asserted-by":"publisher","first-page":"171","DOI":"10.1007\/s13244-016-0534-1","article-title":"Error and discrepancy in radiology: inevitable or avoidable?","volume":"8","author":"Brady","journal-title":"Insights Imaging"},{"key":"R11","doi-asserted-by":"publisher","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":"Frija","journal-title":"EClinicalMedicine"},{"issue":"1","key":"R12","doi-asserted-by":"publisher","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","journal-title":"Sci Rep"},{"issue":"3","key":"R13","doi-asserted-by":"publisher","DOI":"10.1001\/jamanetworkopen.2019.1095","article-title":"Development and validation of a deep learning-based automated detection algorithm for major thoracic diseases on chest radiographs","volume":"2","author":"Hwang","journal-title":"JAMA Netw Open"},{"issue":"5","key":"R14","doi-asserted-by":"publisher","first-page":"319","DOI":"10.1016\/j.clml.2024.11.013","article-title":"Artificial intelligence assessment of chest radiographs for COVID-19","volume":"25","author":"Sasaki","journal-title":"Clin Lymphoma Myeloma Leuk"},{"issue":"50","key":"R15","doi-asserted-by":"publisher","first-page":"1","DOI":"10.3310\/LKRT4721","article-title":"Artificial intelligence software for analysing chest X-ray images to identify suspected lung cancer: an evidence synthesis early value assessment","volume":"28","author":"Colquitt","journal-title":"Health Technol Assess"},{"issue":"8","key":"R16","doi-asserted-by":"publisher","first-page":"607","DOI":"10.1016\/j.crad.2021.03.021","article-title":"Augmenting lung cancer diagnosis on chest radiographs: positioning artificial intelligence to improve radiologist performance","volume":"76","author":"Tam","journal-title":"Clin Radiol"},{"issue":"12","key":"R17","doi-asserted-by":"publisher","DOI":"10.1093\/ofid\/ofab567","article-title":"Triage of persons with tuberculosis symptoms using artificial intelligence-based chest radiograph interpretation: a cost-effectiveness analysis","volume":"8","author":"Nsengiyumva","journal-title":"Open Forum Infect Dis"},{"issue":"12","key":"R18","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0277393","article-title":"Economic analysis of different throughput scenarios and implementation strategies of computer-aided detection software as a screening and triage test for pulmonary TB","volume":"17","author":"Bashir","journal-title":"PLoS One"},{"issue":"9","key":"R19","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0256531","article-title":"Costs and cost-effectiveness of a comprehensive tuberculosis case finding strategy in Zambia","volume":"16","author":"Jo","journal-title":"PLoS One"},{"issue":"5","key":"R20","doi-asserted-by":"publisher","first-page":"3501","DOI":"10.1007\/s00330-022-09315-z","article-title":"Multicentre external validation of a commercial artificial intelligence software to analyse chest radiographs in health screening environments with low disease prevalence","volume":"33","author":"Kim","journal-title":"Eur Radiol"},{"issue":"1","key":"R21","doi-asserted-by":"publisher","first-page":"8270","DOI":"10.1038\/s41467-024-52618-6","article-title":"Generalizability assessment of AI models across hospitals in a low-middle and high income country","volume":"15","author":"Yang","journal-title":"Nat Commun"},{"key":"R22","doi-asserted-by":"publisher","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":"de Camargo","journal-title":"Front Artif Intell"},{"issue":"6","key":"R23","doi-asserted-by":"publisher","first-page":"2623","DOI":"10.1021\/acs.jcim.1c00160","article-title":"GHOST: adjusting the decision threshold to handle imbalanced data in machine learning","volume":"61","author":"Esposito","journal-title":"J Chem Inf Model"},{"key":"R24","unstructured":"CARPL. URL: https:\/\/carpl.ai\/ [Accessed 20-05-2026]"},{"key":"R25","doi-asserted-by":"publisher","DOI":"10.1016\/j.eclinm.2025.103228","article-title":"Artificial intelligence for diagnostics in radiology practice: a rapid systematic scoping review","volume":"83","author":"Lawrence","journal-title":"EClinicalMedicine"},{"issue":"1","key":"R26","doi-asserted-by":"publisher","DOI":"10.1016\/j.mcpdig.2024.100188","article-title":"Implementing artificial intelligence algorithms in the radiology workflow: challenges and considerations","volume":"3","author":"Korfiatis","journal-title":"Mayo Clin Proc Digit Health"},{"key":"R27","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2017.07.005","article-title":"A survey on deep learning in medical image analysis","volume":"42","author":"Litjens","journal-title":"Med Image Anal"},{"issue":"2","key":"R28","doi-asserted-by":"publisher","first-page":"182","DOI":"10.1016\/j.cct.2006.05.007","article-title":"Design and analysis of stepped wedge cluster randomized trials","volume":"28","author":"Hussey","journal-title":"Contemp Clin Trials"},{"issue":"1","key":"R29","doi-asserted-by":"publisher","DOI":"10.1186\/s13063-021-05688-6","article-title":"A multicenter cluster randomized, stepped wedge implementation trial for targeted normoxia in critically ill trauma patients: study protocol and statistical analysis plan for the Strategy to Avoid Excessive Oxygen (SAVE-O2) trial","volume":"22","author":"Dylla","journal-title":"Trials"},{"key":"R30","doi-asserted-by":"publisher","DOI":"10.1136\/bmj.h391","article-title":"The stepped wedge cluster randomised trial: rationale, design, analysis, and reporting","volume":"350","author":"Hemming","journal-title":"BMJ"},{"issue":"9","key":"R31","doi-asserted-by":"publisher","first-page":"936","DOI":"10.1016\/j.jclinepi.2010.12.003","article-title":"Systematic review of stepped wedge cluster randomized trials shows that design is particularly used to evaluate interventions during routine implementation","volume":"64","author":"Mdege","journal-title":"J Clin Epidemiol"},{"issue":"9","key":"R32","doi-asserted-by":"publisher","first-page":"1364","DOI":"10.1038\/s41591-020-1034-x","article-title":"Reporting guidelines for clinical trial reports for interventions involving artificial intelligence: the CONSORT-AI extension","volume":"26","author":"Liu","journal-title":"Nat Med"},{"issue":"1","key":"R33","doi-asserted-by":"publisher","DOI":"10.1186\/s13063-020-04951-6","article-title":"Reporting guidelines for clinical trials of artificial intelligence interventions: the SPIRIT-AI and CONSORT-AI guidelines","volume":"22","author":"Ibrahim","journal-title":"Trials"},{"issue":"3","key":"R34","doi-asserted-by":"publisher","first-page":"1043","DOI":"10.1093\/ije\/dyaa077","article-title":"Reflection on modern methods: when is a stepped-wedge cluster randomized trial a good study design choice?","volume":"49","author":"Hemming","journal-title":"Int J Epidemiol"},{"issue":"18","key":"R35","doi-asserted-by":"publisher","first-page":"3627","DOI":"10.1002\/sim.9438","article-title":"The batched stepped wedge design: a design robust to delays in cluster recruitment","volume":"41","author":"Kasza","journal-title":"Stat Med"},{"issue":"3","key":"R36","doi-asserted-by":"publisher","first-page":"979","DOI":"10.1093\/ije\/dyz237","article-title":"A tutorial on sample size calculation for multiple-period cluster randomized parallel, cross-over and stepped-wedge trials using the Shiny CRT calculator","volume":"49","author":"Hemming","journal-title":"Int J Epidemiol"},{"key":"R37","unstructured":"Hartig F . DHARMa: residual diagnostics for hierarchical (multi-level\/mixed) regression models. The Comprehensive R Archive Network (CRAN). URL: https:\/\/cran.r-project.org\/web\/packages\/DHARMa\/vignettes\/DHARMa.html [Accessed 19-05-2026]"},{"key":"R38","doi-asserted-by":"crossref","unstructured":"Boyd K Eng KH Page CD . Area under the precision-recall curve: point estimates and confidence intervals. In: Machine Learning and Knowledge Discovery in Databases. Springer; 2013:451-466. [doi: 10.1007\/978-3-642-40994-3_29]","DOI":"10.1007\/978-3-642-40994-3_29"},{"issue":"1","key":"R39","doi-asserted-by":"publisher","first-page":"145","DOI":"10.1093\/bioinformatics\/btw570","article-title":"Precrec: fast and accurate precision-recall and ROC curve calculations in R","volume":"33","author":"Saito","journal-title":"Bioinformatics"},{"issue":"4","key":"R40","doi-asserted-by":"publisher","DOI":"10.1148\/ryai.240300","article-title":"Checklist for Artificial Intelligence in Medical Imaging (CLAIM): 2024 update","volume":"6","author":"Tejani","journal-title":"Radiol Artif Intell"},{"issue":"1","key":"R41","doi-asserted-by":"publisher","DOI":"10.1186\/s13063-015-0837-4","article-title":"Logistic, ethical, and political dimensions of stepped wedge trials: critical review and case studies","volume":"16","author":"Prost","journal-title":"Trials"},{"issue":"Suppl 2","key":"R42","doi-asserted-by":"publisher","DOI":"10.1186\/s13063-019-3842-1","article-title":"Ethical issues in the design and conduct of stepped-wedge cluster randomized trials in low-resource settings","volume":"20","author":"Joag","journal-title":"Trials"},{"issue":"5","key":"R43","doi-asserted-by":"publisher","first-page":"924","DOI":"10.1038\/s41591-022-01772-9","article-title":"Reporting guideline for the early-stage clinical evaluation of decision support systems driven by artificial intelligence: DECIDE-AI","volume":"28","author":"Vasey","journal-title":"Nat Med"},{"key":"R44","doi-asserted-by":"publisher","DOI":"10.1136\/bmj.m689","article-title":"Artificial intelligence versus clinicians: systematic review of design, reporting standards, and claims of deep learning studies","volume":"368","author":"Nagendran","journal-title":"BMJ"},{"issue":"5","key":"R45","doi-asserted-by":"publisher","first-page":"e367","DOI":"10.1016\/S2589-7500(24)00047-5","article-title":"Randomised controlled trials evaluating artificial intelligence in clinical practice: a scoping review","volume":"6","author":"Han","journal-title":"Lancet Digit Health"},{"issue":"1","key":"R46","doi-asserted-by":"publisher","DOI":"10.1186\/s12916-019-1426-2","article-title":"Key challenges for delivering clinical impact with artificial intelligence","volume":"17","author":"Kelly","journal-title":"BMC Med"},{"issue":"6","key":"R47","doi-asserted-by":"publisher","DOI":"10.1117\/1.JMI.10.6.061104","article-title":"Toward fairness in artificial intelligence for medical image analysis: identification and mitigation of potential biases in the roadmap from data collection to model deployment","volume":"10","author":"Drukker","journal-title":"J Med Imaging (Bellingham)"},{"issue":"1","key":"R48","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-024-01276-5","article-title":"Addressing fairness issues in deep learning-based medical image analysis: a systematic review","volume":"7","author":"Xu","journal-title":"NPJ Digit Med"},{"issue":"3","key":"R49","doi-asserted-by":"publisher","first-page":"231","DOI":"10.1136\/bmjqs-2018-008370","article-title":"Artificial intelligence, bias and clinical safety","volume":"28","author":"Challen","journal-title":"BMJ Qual Saf"},{"issue":"1","key":"R50","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1148\/radiol.2020192224","article-title":"Preparing medical imaging data for machine learning","volume":"295","author":"Willemink","journal-title":"Radiology"},{"issue":"11","key":"R51","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pmed.1002683","article-title":"Variable generalization performance of a deep learning model to detect pneumonia in chest radiographs: a cross-sectional study","volume":"15","author":"Zech","journal-title":"PLoS Med"}],"container-title":["JMIR Research Protocols"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.researchprotocols.org\/2026\/1\/e88626","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T22:24:53Z","timestamp":1785536693000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.researchprotocols.org\/2026\/1\/e88626"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,13]]},"references-count":51,"URL":"https:\/\/doi.org\/10.2196\/88626","relation":{},"ISSN":["1929-0748"],"issn-type":[{"value":"1929-0748","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,13]]},"article-number":"v15i3e88626"}}