{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T19:45:53Z","timestamp":1789069553787,"version":"build-2803163510"},"reference-count":36,"publisher":"Georg Thieme Verlag KG","issue":"08","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Rofo"],"published-print":{"date-parts":[[2026,8]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>The rising demand for radiology services calls for innovative solutions to sustain diagnostic quality and efficiency. This study evaluated the diagnostic agreement between two commercially available artificial intelligence (AI) chest X-ray systems and human radiologists during routine clinical practice.<\/jats:p>\n                  <jats:p>We retrospectively analyzed 279 chest X-rays (204 standing, 63 supine, 12 sitting) from a Swiss university hospital. Seven thoracic pathologies \u2013 cardiomegaly, consolidation, mediastinal mass, nodule, pleural effusion, pneumothorax, and pulmonary oedema \u2013 were assessed. Radiologists\u2019 routine reports were compared against Rayvolve (AZmed) and ChestView (Gleamer, both from Paris, France). A Python code, provided as open access supplement, calculated performance metrics, agreement measures, and effect size quantification.<\/jats:p>\n                  <jats:p>Agreement between radiologists and AI ranged from moderate to almost perfect: Human-AZmed (Gwet\u2019s AC1: 0.47\u20130.72, moderate to substantial), and Human-Gleamer (Gwet\u2019s AC1: 0.56\u20130.96, moderate to almost perfect). Balanced accuracies ranged from 0.67\u20130.85 for Human-AZmed and 0.71\u20130.85 for Human-Gleamer, with peak performance for pleural effusion (0.85 both systems). Specificity consistently exceeded sensitivity across pathologies (0.70\u20130.98 vs 0.45\u20130.85). Common findings showed strong performance, pleural effusion (MCC 0.70\u20130.73), cardiomegaly (MCC 0.51), and consolidation (MCC 0.45\u20130.46). Rare pathologies demonstrated lower agreement, mediastinal mass, and nodules (MCC 0.23\u20130.31). Standing radiographs yielded superior agreement compared to supine studies. The two AI systems showed substantial inter-system agreement for consolidation and pleural effusion (balanced accuracy 0.81\u20130.84).<\/jats:p>\n                  <jats:p>Both commercial AI chest X-ray systems demonstrated comparable performance to human radiologists for common thoracic pathologies, with no meaningful differences between platforms. Performance was strongest for standing radiographs but declined for rare findings and supine studies. Position-dependent variability and reduced sensitivity for uncommon pathologies underscore the continued need for human oversight in clinical practice.<\/jats:p>","DOI":"10.1055\/a-2772-7798","type":"journal-article","created":{"date-parts":[[2026,1,20]],"date-time":"2026-01-20T23:48:17Z","timestamp":1768952897000},"page":"1037-1048","source":"Crossref","is-referenced-by-count":4,"title":["Novel Artificial Intelligence Chest X-ray Diagnostics: A Quality Assessment of Their Agreement with Human Doctors in Clinical Routine"],"prefix":"10.1055","volume":"198","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4182-3516","authenticated-orcid":false,"given":"Wolfram A.","family":"Bosbach","sequence":"additional","affiliation":[{"name":"Bern University Hospital, University of Bern, Switzerland","place":["Bern"],"department":["Department of Nuclear Medicine, Inselspital"]},{"name":"Bern University Hospital, University of Bern, Switzerland","place":["Bern"],"department":["Department of Diagnostic, Interventional and Paediatric Radiology (DIPR), Inselspital"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Luca","family":"Schoeni","sequence":"additional","affiliation":[{"name":"Bern University Hospital, University of Bern, Switzerland","place":["Bern"],"department":["Department of Nuclear Medicine, Inselspital"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2889-5489","authenticated-orcid":false,"given":"Jan Felix","family":"Senge","sequence":"additional","affiliation":[{"name":"University of Bremen, Germany","place":["Bremen"],"department":["Department of Mathematics and Computer Science"]},{"name":"Polish Academy of Sciences, Mazowieckie, Poland","place":["Warsaw"],"department":["Dioscuri Centre in Topological Data Analysis"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Milena","family":"Mitrakovic","sequence":"additional","affiliation":[{"name":"Bern University Hospital, University of Bern, Switzerland","place":["Bern"],"department":["Department of Diagnostic, Interventional and Paediatric Radiology (DIPR), Inselspital"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3918-8066","authenticated-orcid":false,"given":"Marc-Andr\u00e9","family":"Weber","sequence":"additional","affiliation":[{"name":"University Medical Center Rostock, Germany","place":["Rostock"],"department":["Institute of Diagnostic and Interventional Radiology, Pediatric Radiology and Neuroradiology"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pawel","family":"Dlotko","sequence":"additional","affiliation":[{"name":"Polish Academy of Sciences, Mazowieckie, Poland","place":["Warsaw"],"department":["Dioscuri Centre in Topological Data Analysis"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Keivan","family":"Daneshvar","sequence":"additional","affiliation":[{"name":"Bern University Hospital, University of Bern, Switzerland","place":["Bern"],"department":["Department of Diagnostic, Interventional and Paediatric Radiology (DIPR), Inselspital"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"194","published-online":{"date-parts":[[2026,1,20]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"120","DOI":"10.1016\/j.carj.2018.02.002","article-title":"Canadian Association of Radiologists White Paper on Artificial Intelligence in Radiology","volume":"69","author":"A Tang","year":"2018","journal-title":"Can Assoc Radiol J"},{"key":"ref2","doi-asserted-by":"publisher","first-page":"102","DOI":"10.1067\/j.cpradiol.2023.04.001","article-title":"Ability of ChatGPT to generate competent radiology reports for distal radius fracture by use of RSNA template items and integrated AO classifier","volume":"53","author":"WA Bosbach","year":"2023","journal-title":"Curr Probl Diagn Radiol"},{"key":"ref3","doi-asserted-by":"publisher","first-page":"1","DOI":"10.59667\/sjoranm.v7i2.12","article-title":"ChatGPT may free time needed by the interventional radiologist for administration\/documentation: A study on the RSNA PICC line reporting template","volume":"7","author":"JF Senge","year":"2024","journal-title":"Swiss J Radiol Nucl Med"},{"key":"ref4","doi-asserted-by":"publisher","first-page":"142","DOI":"10.1186\/s13550-025-01323-6","article-title":"Automation of 99mTc Mercaptoacetyltriglycine (MAG3) Report Writing Using a Vision Language Model","volume":"15","author":"WA Bosbach","year":"2025","journal-title":"EJNMMI Res"},{"key":"ref5","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1177\/08465371231170133","article-title":"Appropriateness of Recommendations Provided by ChatGPT to Interventional Radiologists","author":"M Barat","year":"2023","journal-title":"Can Assoc Radiol J"},{"key":"ref6","doi-asserted-by":"publisher","first-page":"287","DOI":"10.1109\/ICCP60212.2023.10398648","article-title":"A Deep Learning-based Fully Automated Approach for Body Composition Analysis in 3D Whole Body Dixon MRI","author":"S Ramedani","year":"2023","journal-title":"2023 IEEE 19th Int Conf Intell Comput Commun Process"},{"key":"ref7","doi-asserted-by":"publisher","first-page":"3055","DOI":"10.1002\/mrm.26977","article-title":"Learning a variational network for reconstruction of accelerated MRI data","volume":"79","author":"K Hammernik","year":"2018","journal-title":"Magn Reson Med"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1055\/a-2594-7085","article-title":"Evaluating the Diagnostic Accuracy of ChatGPT-4.0 in Classifying Multimodal Musculoskeletal Masses: A Comparative Study with Human Raters","author":"WA Bosbach","year":"2025","journal-title":"Rofo"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.6084\/m9.figshare.28560842.v1","article-title":"Open access supplement to the manuscript: Bosbach WA, Schoeni L, Beisbart C et al. Evaluating the Diagnostic Accuracy of ChatGPT-4.0 in Classifying Multimodal Musculoskeletal Masses: A Comparative Study with Human Raters. Rofo 2025; accepted for publicat","author":"WA Bosbach","year":"2025","journal-title":"Figshare"},{"key":"ref10","doi-asserted-by":"publisher","first-page":"5","DOI":"10.59667\/sjoranm.v5i1.11","article-title":"Regulatory Needs for Radiation Protection Devices based upon Arti\ufb01cial Intelligence \u2013 State task or leave unregulated?","volume":"5","author":"SN Garni","year":"2024","journal-title":"Swiss J Radiol Nucl Med"},{"key":"ref11","doi-asserted-by":"publisher","first-page":"e0313","DOI":"10.1097\/RMR.0000000000000313","article-title":"Deep learning reconstruction of accelerated MRI: False positive cartilage delamination inserted in MRI arthrography under traction","volume":"33","author":"WA Bosbach","year":"2024","journal-title":"Top Magn Reson Imaging"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.6084\/m9.figshare.25943740","article-title":"Open access supplement to the publication: Bosbach WA et al. (2024). Deep learning reconstruction of accelerated MRI: False positive cartilage delamination inserted in MRI arthrography under traction. Topics in MRI","author":"WA Bosbach","year":"2024","journal-title":"Figshare"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2508.14118","article-title":"Hallucinations in medical devices","author":"J Granstedt","year":"2025","journal-title":"ArXiv"},{"key":"ref14","volume-title":"The Chest X-Ray \u2013 A Survival Guide","author":"G De Lacey","year":"2008"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2021.102075","article-title":"Evaluating diagnostic content of AI-generated radiology reports of chest X-rays","volume":"116","author":"Z Babar","year":"2021","journal-title":"Artif Intell Med"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1101\/2022.08.30.22279318","article-title":"Evaluating Progress in Automatic Chest X-Ray Radiology Report Generation","author":"F Yu","year":"2022","journal-title":"MedRxiv"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.3390\/diagnostics14111183","article-title":"Evaluation of the Performance of an Artificial Intelligence (AI) Algorithm in Detecting Thoracic Pathologies on Chest Radiographs","volume":"14","author":"H Bettinger","year":"2024","journal-title":"Diagnostics"},{"key":"ref18","doi-asserted-by":"publisher","first-page":"1675","DOI":"10.1007\/s00247-023-05621-w","article-title":"Comparison of diagnostic performance of a deep learning algorithm, emergency physicians, junior radiologists and senior radiologists in the detection of appendicular fractures in children","volume":"53","author":"I Gasmi","year":"2023","journal-title":"Pediatr Radiol"},{"key":"ref19","doi-asserted-by":"publisher","first-page":"151","DOI":"10.1016\/j.diii.2021.10.007","article-title":"External validation of a commercially available deep learning algorithm for fracture detection in children","volume":"103","author":"M Dupuis","year":"2022","journal-title":"Diagn Interv Imaging"},{"key":"ref20","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.acra.2023.10.042","article-title":"Assessing the Potential of a Deep Learning Tool to Improve Fracture Detection by Radiologists and Emergency Physicians on Extremity Radiographs","author":"T Fu","year":"2023","journal-title":"Acad Radiol"},{"key":"ref21","doi-asserted-by":"publisher","first-page":"318","DOI":"10.1109\/TPAMI.2018.2858826","article-title":"Focal Loss for Dense Object Detection","volume":"42","author":"TY Lin","year":"2020","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"ref22","first-page":"1","volume-title":"Very deep convolutional networks for large-scale image recognition. 3rd Int Conf Learn Represent ICLR 2015 \u2013 Conf Track Proc","author":"K Simonyan","year":"2015"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejrad.2022.110447","article-title":"Assessment of performances of a deep learning algorithm for the detection of limbs and pelvic fractures, dislocations, focal bone lesions, and elbow effusions on trauma X-rays","volume":"154","author":"NE Regnard","year":"2022","journal-title":"Eur J Radiol"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.230860","article-title":"Using AI to Improve Radiologist Performance in Detection of Abnormalities on Chest Radiographs","volume":"309","author":"S Bennani","year":"2023","journal-title":"Radiology"},{"key":"ref25","doi-asserted-by":"publisher","first-page":"299","DOI":"10.1016\/j.diii.2025.03.007","article-title":"Efficacy of a deep learning-based software for chest X-ray analysis in an emergency department","volume":"106","author":"S Selvam","year":"2025","journal-title":"Diagn Interv Imaging"},{"key":"ref27","doi-asserted-by":"publisher","first-page":"2","DOI":"10.2214\/AJR.15.15895","article-title":"How sure are you, doctor? A standardized lexicon to describe the radiologists level of certainty","volume":"207","author":"DM Panicek","year":"2016","journal-title":"Am J Roentgenol"},{"key":"ref31","doi-asserted-by":"publisher","first-page":"159","DOI":"10.2307\/2529310","article-title":"The Measurement of Observer Agreement for Categorical Data","volume":"33","author":"JR Landis","year":"1977","journal-title":"Biometrics"},{"key":"ref33","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/1471-2288-13-61","article-title":"A comparison of Cohen\u2019s Kappa and Gwet\u2019s AC1 when calculating inter-rater reliability coefficients: A study conducted with personality disorder samples Nahathai","volume":"13","author":"N Wongpakaran","year":"2013","journal-title":"BMC Med Res Methodol"},{"key":"ref35","doi-asserted-by":"publisher","first-page":"1796","DOI":"10.1016\/j.amjcard.2011.02.325","article-title":"Meta-analysis of multiple primary prevention trials of cardiovascular events using aspirin","volume":"107","author":"AA Bartolucci","year":"2011","journal-title":"Am J Cardiol"},{"key":"ref36","doi-asserted-by":"publisher","first-page":"997","DOI":"10.1007\/BF02195664","article-title":"The earth is round (p<.05)","volume":"49","author":"J Cohen","year":"1994","journal-title":"Am Psychol"},{"key":"ref37","doi-asserted-by":"publisher","first-page":"279","DOI":"10.4300\/jgme-d-12-00156.1","article-title":"Using Effect Size\u2014or Why the P Value Is Not Enough","volume":"4","author":"GM Sullivan","year":"2012","journal-title":"J Grad Med Educ"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1711.05225","article-title":"CheXNet: Radiologist-Level Pneumonia Detection on Chest X-Rays with Deep Learning","author":"P Rajpurkar","year":"2017","journal-title":"ArXiv"},{"key":"ref42","doi-asserted-by":"publisher","first-page":"590","DOI":"10.1609\/aaai.v33i01.3301590","volume-title":"CheXpert: A large chest radiograph dataset with uncertainty labels and expert comparison. 33rd AAAI Conf Artif Intell","author":"J Irvin","year":"2019"},{"key":"ref43","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s40134-019-0333-9","article-title":"Deep Learning for Chest Radiology: A Review","volume":"7","author":"Y Feng","year":"2019","journal-title":"Curr Radiol Rep"},{"key":"ref44","doi-asserted-by":"publisher","first-page":"650","DOI":"10.1016\/j.chest.2022.10.039","article-title":"Commonly Missed Findings on Chest Radiographs: Causes and Consequences","volume":"163","author":"WB Gefter","year":"2023","journal-title":"Chest"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.7413\/1827-5834014","article-title":"Deskilling of medical professionals: An unintended consequence of AI implementation?","volume":"2","author":"LDD Duran","year":"2021","journal-title":"G Di Filos"}],"container-title":["R\u00f6Fo - Fortschritte auf dem Gebiet der R\u00f6ntgenstrahlen und der bildgebenden Verfahren"],"original-title":[],"language":"de","link":[{"URL":"http:\/\/www.thieme-connect.de\/products\/ejournals\/pdf\/10.1055\/a-2772-7798.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,29]],"date-time":"2026-07-29T22:41:33Z","timestamp":1785364893000},"score":1,"resource":{"primary":{"URL":"http:\/\/www.thieme-connect.de\/DOI\/DOI?10.1055\/a-2772-7798"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,20]]},"references-count":36,"journal-issue":{"issue":"08","published-online":{"date-parts":[[2026,7,29]]},"published-print":{"date-parts":[[2026,8]]}},"URL":"https:\/\/doi.org\/10.1055\/a-2772-7798","archive":["Portico","CLOCKSS"],"relation":{},"ISSN":["1438-9029","1438-9010"],"issn-type":[{"value":"1438-9029","type":"print"},{"value":"1438-9010","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,20]]}}}