{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T09:10:37Z","timestamp":1789031437773,"version":"build-2803163510"},"reference-count":25,"publisher":"Public Library of Science (PLoS)","issue":"7","license":[{"start":{"date-parts":[[2025,7,24]],"date-time":"2025-07-24T00:00:00Z","timestamp":1753315200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100019703","name":"Lunit","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100019703","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:p>The number of commercially available artificial intelligence (AI) tools to support radiological workflows is constantly increasing, yet dedicated solutions for children are largely unavailable. Here, we repurposed an AI-tool developed for chest radiograph interpretation in adults (Lunit INSIGHT CXR) and investigated its diagnostic performance in a real-world pediatric clinical dataset. 958 consecutive frontal chest radiographs of children aged 2\u221214 years were included and analyzed with the commercially available AI-tool. The reference standard was determined in a dedicated reading session by a board-certified radiologist. The original reports validated by specialized pediatric radiologists, were considered as second readings. All discordant findings were reanalyzed in consensus. The diagnostic performance of the AI-tool was validated using standard measures of accuracy. For this, the continuous AI output (ranging from 0\u2212100) was binarized using vendor recommended thresholds recommended for adults and optimized thresholds identified for children. Relevant findings were defined as consolidation, atelectasis, nodule, cardiomegaly, mediastinal widening due to mass, pleural effusion and pneumothorax. 200 radiographs [20.9%] demonstrated at least one relevant pathology. Using the adult threshold, the AI-tool showed a high performance for all relevant findings with an AUC 0.94 (95% CI: 0.92\u20130.95) and. In stratified analysis by age (2\u22127 vs. 7\u201314-years-old) a significantly higher performance (p\u2009&lt;\u20090.001) was found for older children with an AUC of 0.96 (95% CI: 0.94\u20130.98) with a sensitivity and specificity of 87.5% and 82.3% respectively, which further increased using optimized thresholds for children. Repurposing existing AI-tools developed for adult application to pediatric patients could support clinical workflows until dedicated solutions become available.<\/jats:p>","DOI":"10.1371\/journal.pone.0328295","type":"journal-article","created":{"date-parts":[[2025,7,24]],"date-time":"2025-07-24T17:22:36Z","timestamp":1753377756000},"page":"e0328295","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":5,"title":["Deep learning for pediatric chest x-ray diagnosis: Repurposing a commercial tool developed for adults"],"prefix":"10.1371","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6784-6727","authenticated-orcid":true,"given":"Prerana","family":"Agarwal","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5881-6043","authenticated-orcid":true,"given":"Alexander","family":"Rau","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Helen","family":"Ngo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ambika","family":"Seth","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fabian","family":"Bamberg","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9022-6000","authenticated-orcid":true,"given":"Elmar","family":"Kotter","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jakob","family":"Weiss","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2025,7,24]]},"reference":[{"issue":"4","key":"pone.0328295.ref001","doi-asserted-by":"crossref","first-page":"903","DOI":"10.2214\/AJR.16.16449","article-title":"Pediatric Chest Radiographs: Common and Less Common Errors","volume":"207","author":"SJ Menashe","year":"2016","journal-title":"AJR Am J Roentgenol"},{"issue":"7","key":"pone.0328295.ref002","doi-asserted-by":"crossref","DOI":"10.1097\/CCM.0000000000004397","article-title":"Artificial Intelligence Algorithm Detecting Lung Infection in Supine Chest Radiographs of Critically Ill Patients With a Diagnostic Accuracy Similar to Board-Certified Radiologists","volume":"48","author":"J Rueckel","year":"2020","journal-title":"Crit Care Med"},{"issue":"5","key":"pone.0328295.ref003","doi-asserted-by":"crossref","first-page":"511","DOI":"10.3348\/kjr.2019.0821","article-title":"Clinical Implementation of Deep Learning in Thoracic Radiology: Potential Applications and Challenges","volume":"21","author":"EJ Hwang","year":"2020","journal-title":"Korean J Radiol"},{"issue":"3","key":"pone.0328295.ref004","doi-asserted-by":"crossref","first-page":"687","DOI":"10.1148\/radiol.2020201240","article-title":"Performance of a Deep Learning Algorithm Compared with Radiologic Interpretation for Lung Cancer Detection on Chest Radiographs in a Health Screening Population","volume":"297","author":"JH Lee","year":"2020","journal-title":"Radiology"},{"key":"pone.0328295.ref005","doi-asserted-by":"crossref","first-page":"583427","DOI":"10.3389\/frai.2020.583427","article-title":"Tuberculosis Diagnostics and Localization in Chest X-Rays via Deep Learning Models","volume":"3","author":"R Guo","year":"2020","journal-title":"Front Artif Intell"},{"issue":"6","key":"pone.0328295.ref006","doi-asserted-by":"crossref","first-page":"696","DOI":"10.1177\/0284185114538017","article-title":"Computer-aided detection system for chest radiography: reducing report turnaround times of examinations with abnormalities","volume":"56","author":"E-F Kao","year":"2015","journal-title":"Acta Radiol"},{"key":"pone.0328295.ref007","author":"Diagnostic Image Analysis Group","year":"2020"},{"issue":"8","key":"pone.0328295.ref008","doi-asserted-by":"crossref","first-page":"730","DOI":"10.1016\/j.jacr.2023.06.003","article-title":"Use of Artificial Intelligence in Radiology: Impact on Pediatric Patients, a White Paper From the ACR Pediatric AI Workgroup","volume":"20","author":"MBK Sammer","year":"2023","journal-title":"J Am Coll Radiol"},{"issue":"8","key":"pone.0328295.ref009","doi-asserted-by":"crossref","first-page":"748","DOI":"10.1016\/j.jacr.2023.04.017","article-title":"Commercially available artificial intelligence algorithms of interest to pediatric radiology: The growing gap between potential use and data training","volume":"20","author":"LO Tierradentro-Garcia","year":"2023","journal-title":"Journal of the American College of Radiology"},{"issue":"8","key":"pone.0328295.ref010","doi-asserted-by":"crossref","first-page":"1568","DOI":"10.1007\/s00247-022-05368-w","article-title":"Pediatric chest radiograph interpretation: how far has artificial intelligence come? A systematic literature review","volume":"52","author":"S Padash","year":"2022","journal-title":"Pediatr Radiol"},{"issue":"1","key":"pone.0328295.ref011","doi-asserted-by":"crossref","first-page":"31329","DOI":"10.1038\/s41598-024-82775-z","article-title":"Optimizing adult-oriented artificial intelligence for pediatric chest radiographs by adjusting operating points","volume":"14","author":"HJ Shin","year":"2024","journal-title":"Sci Rep"},{"issue":"1","key":"pone.0328295.ref012","doi-asserted-by":"crossref","first-page":"10215","DOI":"10.1038\/s41598-022-14519-w","article-title":"Diagnostic performance of artificial intelligence approved for adults for the interpretation of pediatric chest radiographs","volume":"12","author":"HJ Shin","year":"2022","journal-title":"Sci Rep"},{"issue":"8","key":"pone.0328295.ref013","doi-asserted-by":"crossref","first-page":"742","DOI":"10.1016\/j.jacr.2023.07.004","article-title":"Applying Artificial Intelligence to Pediatric Chest Imaging: Reliability of Leveraging Adult-Based Artificial Intelligence Models","volume":"20","author":"G Morcos","year":"2023","journal-title":"J Am Coll Radiol"},{"issue":"3","key":"pone.0328295.ref014","doi-asserted-by":"crossref","DOI":"10.1001\/jamanetworkopen.2019.1095","article-title":"Development and validation of a deep learning\u2013based automated detection algorithm for major thoracic diseases on chest radiographs","volume":"2","author":"EJ Hwang","year":"2019","journal-title":"JAMA Network Open"},{"issue":"1","key":"pone.0328295.ref015","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.crad.2022.08.129","article-title":"Validation study of machine-learning chest radiograph software in primary and emergency medicine","volume":"78","author":"EJR van Beek","year":"2023","journal-title":"Clin Radiol"},{"issue":"10","key":"pone.0328295.ref016","doi-asserted-by":"crossref","first-page":"1150","DOI":"10.3348\/kjr.2020.0536","article-title":"Implementation of a Deep Learning-Based Computer-Aided Detection System for the Interpretation of Chest Radiographs in Patients Suspected for COVID-19","volume":"21","author":"EJ Hwang","year":"2020","journal-title":"Korean J Radiol"},{"issue":"6","key":"pone.0328295.ref017","doi-asserted-by":"crossref","first-page":"1981","DOI":"10.3390\/jcm9061981","article-title":"Clinical Validation of a Deep Learning Algorithm for Detection of Pneumonia on Chest Radiographs in Emergency Department Patients with Acute Febrile Respiratory Illness","volume":"9","author":"JH Kim","year":"2020","journal-title":"J Clin Med"},{"issue":"2","key":"pone.0328295.ref018","doi-asserted-by":"crossref","first-page":"455","DOI":"10.1148\/radiol.2021210578","article-title":"Deep Learning for Detection of Pulmonary Metastasis on Chest Radiographs","volume":"301","author":"EJ Hwang","year":"2021","journal-title":"Radiology"},{"issue":"3","key":"pone.0328295.ref019","doi-asserted-by":"crossref","first-page":"826","DOI":"10.1148\/radiol.2015151516","article-title":"STARD 2015: An Updated List of Essential Items for Reporting Diagnostic Accuracy Studies","volume":"277","author":"PM Bossuyt","year":"2015","journal-title":"Radiology"},{"key":"pone.0328295.ref020","doi-asserted-by":"crossref","first-page":"104964","DOI":"10.1016\/j.cmpb.2019.06.023","article-title":"A transfer learning method with deep residual network for pediatric pneumonia diagnosis","volume":"187","author":"G Liang","year":"2020","journal-title":"Comput Methods Programs Biomed"},{"issue":"10","key":"pone.0328295.ref021","doi-asserted-by":"crossref","first-page":"1617","DOI":"10.1002\/ppul.24431","article-title":"Using deep-learning techniques for pulmonary-thoracic segmentations and improvement of pneumonia diagnosis in pediatric chest radiographs","volume":"54","author":"L E","year":"2019","journal-title":"Pediatr Pulmonol"},{"issue":"1","key":"pone.0328295.ref022","doi-asserted-by":"crossref","first-page":"131","DOI":"10.1016\/j.jcf.2019.04.016","article-title":"Deep learning to automate Brasfield chest radiographic scoring for cystic fibrosis","volume":"19","author":"EJ Zucker","year":"2020","journal-title":"J Cyst Fibros"},{"key":"pone.0328295.ref023","author":"JPVJ Cohen","year":"2020"},{"issue":"1","key":"pone.0328295.ref024","doi-asserted-by":"crossref","first-page":"87","DOI":"10.1148\/radiology.182.1.1727316","article-title":"Primary tuberculosis in childhood: radiographic manifestations","volume":"182","author":"AN Leung","year":"1992","journal-title":"Radiology"},{"issue":"2","key":"pone.0328295.ref025","doi-asserted-by":"crossref","DOI":"10.1148\/radiol.231693","article-title":"Coarse race and ethnicity labels mask granular underdiagnosis disparities in deep learning models for chest radiograph diagnosis","volume":"309","author":"P Bachina","year":"2023","journal-title":"Radiology"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0328295","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,24]],"date-time":"2025-07-24T17:22:41Z","timestamp":1753377761000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0328295"}},"subtitle":[],"editor":[{"given":"Shahriar","family":"Ahmed","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2025,7,24]]},"references-count":25,"journal-issue":{"issue":"7","published-online":{"date-parts":[[2025,7,24]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0328295","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7,24]]}}}