{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T11:23:50Z","timestamp":1775820230587,"version":"3.50.1"},"reference-count":39,"publisher":"MDPI AG","issue":"8","license":[{"start":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T00:00:00Z","timestamp":1775779200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"AZMed"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Diagnostics"],"abstract":"<jats:p>Background: Conventional radiography faces high error rates (3\u201310%) due to heavy clinical workloads. While AI has emerged as a supportive tool, there is an evidence gap regarding the clinical utility of integrated AI systems in detecting both skeletal and thoracic abnormalities. Objectives: This large-scale, international multicenter study aims to validate the performance of a unified radiographic AI suite across an expanded diagnostic scope while confirming its continued robustness. Methods: A retrospective performance evaluation was conducted using 21,581 adult and pediatric X-rays collected from 20 countries. The reference standard was established through independent review by two expert readers, with adjudication of a third radiologist in cases of discordance. Diagnostic metrics, including Area Under the Curve (AUC), sensitivity, and specificity, were calculated for all 18 pathologies. Subgroup analysis was performed by patients\u2019 age, sex, and country of acquisition. Results: For the nine findings within the expanded scope, AUC values exceeded 96.1%, with sensitivity and specificity ranges from 94.5 to 98.8% and 86.6 to 96.1%, respectively. Similarly, for the nine historically validated findings, AUCs remained above 96.1%, with sensitivity and specificity localized between 94.5 and 97.8% and 84.6 and 89.4%, respectively. Consistency was maintained across subgroups. Conclusions: The results confirm the potential of deep learning to transition from narrow, task-specific tools to a unified, high-performance diagnostic system.<\/jats:p>","DOI":"10.3390\/diagnostics16081137","type":"journal-article","created":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T10:20:16Z","timestamp":1775816416000},"page":"1137","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["International Multicenter Validation of an Expanded AI Diagnostic System for 18 Pathologies in Thoracic and Musculoskeletal Radiography"],"prefix":"10.3390","volume":"16","author":[{"given":"Jean-Laurent","family":"Sultan","sequence":"first","affiliation":[{"name":"Groupe Alloradio (Simago) Private Imaging Medical Center, Montalembert, 9 Rue de Montalembert, 75007 Paris, France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-7256-5385","authenticated-orcid":false,"given":"Pauline","family":"Beaumel","sequence":"additional","affiliation":[{"name":"AZmed, 10 Rue d\u2019Uz\u00e8s, 75002 Paris, France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Maria","family":"Dementjeva","sequence":"additional","affiliation":[{"name":"SA Narva Haigla (Narva Hospital), Haigla 1, 20104 Narva, Estonia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hugo","family":"Declercq","sequence":"additional","affiliation":[{"name":"Department of Radiology, az Sint-Blasius, Kroonveldlaan 50, 9200 Dendermonde, Belgium"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ilana","family":"Sultan","sequence":"additional","affiliation":[{"name":"Groupe Alloradio (Simago) Private Imaging Medical Center, Montalembert, 9 Rue de Montalembert, 75007 Paris, France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Julia","family":"Reinas","sequence":"additional","affiliation":[{"name":"SA Narva Haigla (Narva Hospital), Haigla 1, 20104 Narva, Estonia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Maria Dolores","family":"Dur\u00e1n Vila","sequence":"additional","affiliation":[{"name":"Servicio de Radiodiagn\u00f3stico, Complejo Hospitalario Universitario de Pontevedra (CHUP), Calle Mourente s\/n, 36071 Pontevedra, Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2026,4,10]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Delrue, L., and Gosselin, R. (2011). Difficulties in Interpretation of Chest Radiography. Comparative Interpretation of CT and Standard Radiography of the Chest, Springer.","DOI":"10.1007\/978-3-540-79942-9_2"},{"key":"ref_2","unstructured":"Longo, D.L. (2018). Harrison\u2019s Principles of Internal Medicine, McGraw-Hill Education. [20th ed.]."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"843","DOI":"10.1001\/jama.2019.11456","article-title":"Trends in Use of Medical Imaging in US Health Care Systems and in Ontario, Canada, 2000\u20132016","volume":"322","author":"Kwan","year":"2019","journal-title":"JAMA"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"710","DOI":"10.1080\/02841850600806340","article-title":"Systematic analysis of missed extremity fractures in emergency radiology","volume":"47","author":"Wei","year":"2006","journal-title":"Acta Radiol."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"1493","DOI":"10.1001\/archinte.165.13.1493","article-title":"Diagnostic error in internal medicine","volume":"165","author":"Graber","year":"2005","journal-title":"Arch. Intern. Med."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"1681","DOI":"10.1016\/j.mayocp.2018.10.023","article-title":"Changes in Burnout and Satisfaction With Work-Life Integration in Physicians and the General US Working Population Between 2011 and 2017","volume":"94","author":"Shanafelt","year":"2019","journal-title":"Mayo Clin. Proc."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"50","DOI":"10.1148\/radiol.211785","article-title":"Artificial Intelligence in Fracture Detection: A Systematic Review and Meta-Analysis","volume":"304","author":"Kuo","year":"2022","journal-title":"Radiology"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"44","DOI":"10.1038\/s41591-018-0300-7","article-title":"High-performance medicine: The convergence of human and artificial intelligence","volume":"25","author":"Topol","year":"2019","journal-title":"Nat. Med."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"263","DOI":"10.1136\/emj.18.4.263","article-title":"Diagnostic errors in an accident and emergency department","volume":"77","author":"Guly","year":"2001","journal-title":"Emerg. Med. J."},{"key":"ref_10","unstructured":"Simonyan, K., and Zisserman, A. (2014). Very Deep Convolutional Networks for Large-Scale Image Recognition. arXiv, arXiv:1409.1556."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"3349","DOI":"10.1109\/TPAMI.2020.2983686","article-title":"Deep High-Resolution Representation Learning for Visual Recognition","volume":"43","author":"Wang","year":"2020","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"89","DOI":"10.1038\/s41586-019-1799-6","article-title":"International evaluation of an AI system for breast cancer screening","volume":"577","author":"McKinney","year":"2020","journal-title":"Nature"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"e496","DOI":"10.1016\/S2589-7500(21)00106-0","article-title":"Effect of a comprehensive deep-learning model on the accuracy of chest x-ray interpretation by radiologists: A retrospective, multireader multicase study","volume":"3","author":"Seah","year":"2021","journal-title":"Lancet Digit. Health"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"573","DOI":"10.1148\/radiol.2019191225","article-title":"Deep Learning for Chest Radiograph Diagnosis in the Emergency Department","volume":"293","author":"Hwang","year":"2019","journal-title":"Radiology"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"5525","DOI":"10.1007\/s00330-020-06946-y","article-title":"Implementation of artificial intelligence (AI) applications in radiology: Hindering and facilitating factors","volume":"30","author":"Strohm","year":"2020","journal-title":"Eur. Radiol."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Oppenheimer, J., L\u00fcken, S., Hamm, B., and Niehues, S.M. (2023). A Prospective Approach to Integration of AI Fracture Detection Software in Radiographs into Clinical Workflow. Life, 13.","DOI":"10.3390\/life13010223"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"65","DOI":"10.1038\/s41746-021-00438-z","article-title":"Diagnostic accuracy of deep learning in medical imaging: A systematic review and meta-analysis","volume":"4","author":"Aggarwal","year":"2021","journal-title":"NPJ Digit. Med."},{"key":"ref_18","doi-asserted-by":"crossref","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":"Dupuis","year":"2022","journal-title":"Diagn. Interv. Imaging"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"1989","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","volume":"31","author":"Fu","year":"2024","journal-title":"Acad. Radiol."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Bettinger, H., Lenczner, G., Guigui, J., Rotenberg, L., Zerbib, E., Attia, A., Vidal, J., and Beaumel, P. (2024). Evaluation of the Performance of an Artificial Intelligence (AI) Algorithm in Detecting Thoracic Pathologies on Chest Radiographs. Diagnostics, 14.","DOI":"10.3390\/diagnostics14111183"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"1121","DOI":"10.1016\/j.acra.2025.11.022","article-title":"Enhancing Pediatric Fracture Detection: Multicenter Evaluation of a Deep Learning AI Model and Its Impact on Radiologist Performance","volume":"33","author":"Raj","year":"2025","journal-title":"Acad. Radiol."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"7998","DOI":"10.1007\/s00330-022-08784-6","article-title":"Radiology artificial intelligence: A systematic review and evaluation of methods (RAISE)","volume":"32","author":"Kelly","year":"2022","journal-title":"Eur. Radiol."},{"key":"ref_23","doi-asserted-by":"crossref","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":"Gefter","year":"2023","journal-title":"Chest"},{"key":"ref_24","first-page":"k2387","article-title":"Prevalence and outcomes of incidental imaging findings: Umbrella review","volume":"361","author":"Muntinga","year":"2018","journal-title":"BMJ"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"e543","DOI":"10.1016\/S2589-7500(21)00116-3","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":"Qin","year":"2021","journal-title":"Lancet Digit. Health"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"6268","DOI":"10.1038\/s41598-019-42557-4","article-title":"Efficient Deep Network Architectures for Fast Chest X-Ray Tuberculosis Screening and Visualization","volume":"9","author":"Pasa","year":"2019","journal-title":"Sci. Rep."},{"key":"ref_27","unstructured":"World Health Organization (2021). Chest Radiography in Tuberculosis Detection: Summary of Current WHO Recommendations and Guidance on Programmatic Approaches, WHO. Available online: https:\/\/www.who.int\/publications\/i\/item\/9789241511506."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"60","DOI":"10.1016\/j.media.2017.07.005","article-title":"A survey on deep learning in medical image analysis","volume":"42","author":"Litjens","year":"2017","journal-title":"Med. Image Anal."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"3283","DOI":"10.1038\/s41591-025-03953-8","article-title":"The STARD-AI reporting guideline for diagnostic accuracy studies using artificial intelligence","volume":"31","author":"Sounderajah","year":"2025","journal-title":"Nat. Med."},{"key":"ref_30","unstructured":"(2017). Health informatics\u2014Pseudonymization (Standard No. ISO 25237:2017)."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"318","DOI":"10.1109\/TPAMI.2018.2858826","article-title":"Focal Loss for Dense Object Detection","volume":"42","author":"Lin","year":"2020","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_32","unstructured":"(2026, January 21). AZtrauma: AI for Fracture Detection. Available online: https:\/\/www.azmed.co\/azproducts-pages\/aztrauma."},{"key":"ref_33","unstructured":"(2026, January 21). AZchest: AI for Chest X-Ray Analysis. Available online: https:\/\/www.azmed.co\/fr\/azproducts-pages\/azchest."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"171","DOI":"10.1007\/s13244-016-0534-1","article-title":"Error and Discrepancy in Radiology: Inevitable or Avoidable?","volume":"8","author":"Brady","year":"2016","journal-title":"Insights Imaging"},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"103361","DOI":"10.1016\/j.radi.2026.103361","article-title":"Performance of a complete AI radiographic suite across 258,373 X-rays from 26 countries: A worldwide evaluation","volume":"32","author":"Cohen","year":"2026","journal-title":"Radiography"},{"key":"ref_36","first-page":"286","article-title":"Incidental findings in musculoskeletal imaging","volume":"57","author":"Rehnitz","year":"2017","journal-title":"Radiologe"},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"133","DOI":"10.1097\/00004424-199002000-00006","article-title":"Satisfaction of search in diagnostic radiology","volume":"25","author":"Berbaum","year":"1990","journal-title":"Investig. Radiol."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"7888","DOI":"10.1007\/s00330-021-07833-w","article-title":"Pneumothorax detection in chest radiographs: Optimizing artificial intelligence system for accuracy and confounding bias reduction using in-image annotations in algorithm training","volume":"31","author":"Rueckel","year":"2021","journal-title":"Eur. Radiol."},{"key":"ref_39","unstructured":"World Health Organization (2025). Global Tuberculosis Report 2025, WHO."}],"container-title":["Diagnostics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2075-4418\/16\/8\/1137\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T10:37:05Z","timestamp":1775817425000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2075-4418\/16\/8\/1137"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,10]]},"references-count":39,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2026,4]]}},"alternative-id":["diagnostics16081137"],"URL":"https:\/\/doi.org\/10.3390\/diagnostics16081137","relation":{},"ISSN":["2075-4418"],"issn-type":[{"value":"2075-4418","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,10]]}}}