{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,2]],"date-time":"2026-10-02T13:53:38Z","timestamp":1790949218638,"version":"4.1.0"},"reference-count":30,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2025,10,17]],"date-time":"2025-10-17T00:00:00Z","timestamp":1760659200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,10,17]],"date-time":"2025-10-17T00:00:00Z","timestamp":1760659200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100001659","name":"Deutsche Forschungsgemeinschaft","doi-asserted-by":"publisher","award":["2136\/7-1"],"award-info":[{"award-number":["2136\/7-1"]}],"id":[{"id":"10.13039\/501100001659","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001659","name":"Deutsche Forschungsgemeinschaft","doi-asserted-by":"publisher","award":["2136\/3-1"],"award-info":[{"award-number":["2136\/3-1"]}],"id":[{"id":"10.13039\/501100001659","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001659","name":"Deutsche Forschungsgemeinschaft","doi-asserted-by":"publisher","award":["1700\/7-1"],"award-info":[{"award-number":["1700\/7-1"]}],"id":[{"id":"10.13039\/501100001659","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002347","name":"Bundesministerium f\u00fcr Bildung und Forschung","doi-asserted-by":"publisher","award":["SWAG - 01KD2215B"],"award-info":[{"award-number":["SWAG - 01KD2215B"]}],"id":[{"id":"10.13039\/501100002347","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002347","name":"Bundesministerium f\u00fcr Bildung und Forschung","doi-asserted-by":"publisher","award":["Transform Liver - 031L0312C"],"award-info":[{"award-number":["Transform Liver - 031L0312C"]}],"id":[{"id":"10.13039\/501100002347","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002347","name":"Bundesministerium f\u00fcr Bildung und Forschung","doi-asserted-by":"publisher","award":["DECIPHER-M - 01KD2420B"],"award-info":[{"award-number":["DECIPHER-M - 01KD2420B"]}],"id":[{"id":"10.13039\/501100002347","id-type":"DOI","asserted-by":"publisher"}]},{"name":"European Union Research and Innovation Programme","award":["ODELIA - GA 101057091"],"award-info":[{"award-number":["ODELIA - GA 101057091"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Eur Radiol"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Objectives<\/jats:title>\n                    <jats:p>Developing a deep-learning model for automated multi-tissue, multi-condition knee MRI analysis and assessing its clinical potential.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Material and methods<\/jats:title>\n                    <jats:p>\n                      This retrospective dual-center study included 3121 MRI studies from 3018 adults, who underwent routine knee MRI examinations at a radiologic practice (2012\u20132019). Twenty-three conditions across cartilage, menisci, bone marrow, ligaments, and other soft tissues were manually labeled. A 3D slice transformer network was trained for binary classification and evaluated in terms of the area under the receiver operating characteristic curve (AUC), sensitivity, and specificity using a five-fold cross-validation and an external test set of 448 MRI studies (429 adults) from a university hospital (2022\u20132023). To assess differences in diagnostic performance, two inexperienced and two experienced radiology residents read 50 external test studies with and without model assistance. Paired\n                      <jats:italic>t<\/jats:italic>\n                      -tests were used for statistical analysis.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      Averaged over cross-validation tests, the model\u2019s AUC was at least 0.85 for 8 conditions and at least 0.75 for 18 conditions. Generalization on the external test set was robust, with a mean absolute AUC difference of 0.05\u2009\u00b1\u20090.03 per condition. Model assistance improved accuracy and sensitivity for inexperienced residents, increased inter-reader agreement for both groups, and increased sensitivity and shortened reading times by 10% (\n                      <jats:italic>p<\/jats:italic>\n                      \u2009=\u20090.045) for experienced residents. Specificity decreased slightly when conditions with low model performance (AUC\u2009&lt;\u20090.75) were included.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>Our deep-learning model performed well across diverse knee conditions and effectively assisted radiology residents. Future work should focus on more fine-grained predictions for subtle or rare conditions to enable comprehensive joint assessment in clinical practice.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Key Points<\/jats:title>\n                    <jats:p>\n                      <jats:bold>\n                        <jats:italic>Question<\/jats:italic>\n                      <\/jats:bold>\n                      <jats:italic>Increasing MRI utilization adds pressure on radiologists, necessitating comprehensive AI models for image analysis to manage this growing demand efficiently<\/jats:italic>\n                      .\n                    <\/jats:p>\n                    <jats:p>\n                      <jats:bold>\n                        <jats:italic>Findings<\/jats:italic>\n                      <\/jats:bold>\n                      <jats:italic>Our AI model enhanced diagnostic performance and efficiency of resident radiologists when reading knee MRI studies, demonstrating robust results across diverse conditions and two datasets<\/jats:italic>\n                      .\n                    <\/jats:p>\n                    <jats:p>\n                      <jats:bold>\n                        <jats:italic>Clinical relevance<\/jats:italic>\n                      <\/jats:bold>\n                      <jats:italic>Model assistance increases the sensitivity of radiologists, helping to identify pathologies that were overlooked without AI assistance. Reduced reading times suggest potential alleviation of radiologists\u2019 workload<\/jats:italic>\n                      .\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Graphical Abstract<\/jats:title>\n                  <\/jats:sec>","DOI":"10.1007\/s00330-025-12052-8","type":"journal-article","created":{"date-parts":[[2025,10,17]],"date-time":"2025-10-17T17:31:14Z","timestamp":1760722274000},"page":"2563-2575","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Comprehensive deep learning-assisted multi-condition analysis of knee MRI studies improves resident radiologist performance"],"prefix":"10.1007","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-5022-9120","authenticated-orcid":false,"given":"Roman","family":"Vuskov","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2127-0782","authenticated-orcid":false,"given":"Alexander","family":"Hermans","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Martin","family":"Pixberg","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jonas","family":"M\u00fcller-H\u00fcbenthal","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andreas","family":"Brauksiepe","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Eric","family":"Corban","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Malin","family":"Cubukcu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Julia","family":"Nowak","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aleksandar","family":"Kargaliev","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-2801-3679","authenticated-orcid":false,"given":"Marc","family":"von der St\u00fcck","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Robert","family":"Siepmann","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8696-2363","authenticated-orcid":false,"given":"Christiane","family":"Kuhl","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9605-0728","authenticated-orcid":false,"given":"Daniel","family":"Truhn","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5267-9962","authenticated-orcid":false,"given":"Sven","family":"Nebelung","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,10,17]]},"reference":[{"key":"12052_CR1","doi-asserted-by":"publisher","first-page":"843","DOI":"10.1001\/jama.2019.11456","volume":"322","author":"R Smith-Bindman","year":"2019","unstructured":"Smith-Bindman R, Kwan ML, Marlow EC et al (2019) Trends in use of medical imaging in US Health Care Systems and in Ontario, Canada, 2000-2016. JAMA 322:843\u2013856","journal-title":"JAMA"},{"key":"12052_CR2","unstructured":"Organisation for Economic Co-operation and Development (2025) Diagnostic exams. OECD. Available via https:\/\/data-viewer.oecd.org\/?chartId=8f10997a-970b-41a7-a722-e2fc7c97f1b7. Accessed 25 Mar 2025"},{"key":"12052_CR3","doi-asserted-by":"publisher","first-page":"1191","DOI":"10.1016\/j.acra.2015.05.007","volume":"22","author":"RJ McDonald","year":"2015","unstructured":"McDonald RJ, Schwartz KM, Eckel LJ et al (2015) The effects of changes in utilization and technological advancements of cross-sectional imaging on radiologist workload. Acad Radiol 22:1191\u20131198","journal-title":"Acad Radiol"},{"key":"12052_CR4","doi-asserted-by":"publisher","unstructured":"Chung CB, Pathria MN, Resnick D (2024) MRI in MSK: Is it the ultimate examination? Skeletal Radiol https:\/\/doi.org\/10.1007\/s00256-024-04601-x","DOI":"10.1007\/s00256-024-04601-x"},{"key":"12052_CR5","doi-asserted-by":"publisher","first-page":"136","DOI":"10.1080\/10401334.2018.1542307","volume":"31","author":"A Kassam","year":"2019","unstructured":"Kassam A, Cowan M, Topps M (2019) Lessons learned to aid in developing fatigue risk management plans for resident physicians. Teach Learn Med 31:136\u2013145","journal-title":"Teach Learn Med"},{"key":"12052_CR6","doi-asserted-by":"publisher","first-page":"1614","DOI":"10.2214\/AJR.20.24172","volume":"216","author":"AS Chaudhari","year":"2021","unstructured":"Chaudhari AS, Grissom MJ, Fang Z et al (2021) Diagnostic accuracy of quantitative multicontrast 5-minute knee MRI using prospective artificial intelligence image quality enhancement. AJR Am J Roentgenol 216:1614\u20131625","journal-title":"AJR Am J Roentgenol"},{"key":"12052_CR7","doi-asserted-by":"crossref","unstructured":"Lee J, Jung M, Park J et al (2023) Highly accelerated knee magnetic resonance imaging using deep neural network (DNN)\u2013based reconstruction: prospective, multi-reader, multi-vendor study. Sci Rep 13:17264","DOI":"10.1038\/s41598-023-44248-7"},{"key":"12052_CR8","doi-asserted-by":"publisher","first-page":"e081860","DOI":"10.1136\/bmjopen-2023-081860","volume":"14","author":"B Hofmann","year":"2024","unstructured":"Hofmann B, H\u00e5vik V, Andersen ER, Brands\u00e6ter I\u00d8, Kjelle E (2024) Low-value MRI of the knee in Norway: a register-based study to identify the proportion of potentially low-value MRIs and estimate the related costs. BMJ Open 14:e081860","journal-title":"BMJ Open"},{"key":"12052_CR9","doi-asserted-by":"publisher","first-page":"e230764","DOI":"10.1148\/radiol.230764","volume":"310","author":"A Guermazi","year":"2024","unstructured":"Guermazi A, Omoumi P, Tordjman M et al (2024) How AI may transform musculoskeletal imaging. Radiology 310:e230764","journal-title":"Radiology"},{"key":"12052_CR10","doi-asserted-by":"publisher","first-page":"537","DOI":"10.3390\/diagnostics12020537","volume":"12","author":"A Siouras","year":"2022","unstructured":"Siouras A, Moustakidis S, Giannakidis A et al (2022) Knee injury detection using deep learning on MRI studies: a systematic review. Diagnostics (Basel) 12:537","journal-title":"Diagnostics (Basel)"},{"key":"12052_CR11","doi-asserted-by":"publisher","first-page":"e200165","DOI":"10.1148\/ryai.2021200165","volume":"3","author":"B Astuto","year":"2021","unstructured":"Astuto B, Flament I, K. Namiri N et al (2021) Automatic deep learning\u2013assisted detection and grading of abnormalities in knee MRI studies. Radiol Artif Intell 3:e200165","journal-title":"Radiol Artif Intell"},{"key":"12052_CR12","doi-asserted-by":"publisher","first-page":"445","DOI":"10.1007\/s00256-023-04416-2","volume":"53","author":"SM Santomartino","year":"2024","unstructured":"Santomartino SM, Kung J, Yi PH (2024) Systematic review of artificial intelligence development and evaluation for MRI diagnosis of knee ligament or meniscus tears. Skeletal Radiol 53:445\u2013454","journal-title":"Skeletal Radiol"},{"key":"12052_CR13","doi-asserted-by":"publisher","unstructured":"Mead K, Cross T, Roger G, Sabharwal R, Singh S, Giannotti N (2024) MRI deep learning models for assisted diagnosis of knee pathologies: a systematic review. Eur Radiol. https:\/\/doi.org\/10.1007\/s00330-024-11105-8","DOI":"10.1007\/s00330-024-11105-8"},{"key":"12052_CR14","doi-asserted-by":"publisher","first-page":"143","DOI":"10.1109\/42.836373","volume":"19","author":"LG Nyul","year":"2000","unstructured":"Nyul LG, Udupa JK, Zhang X (2000) New variants of a method of MRI scale standardization. IEEE Trans Med Imaging 19:143\u2013150","journal-title":"IEEE Trans Med Imaging"},{"key":"12052_CR15","doi-asserted-by":"publisher","unstructured":"Deng J, Dong W, Socher R, Li L-J, Li K, Fei-Fei L (2009) ImageNet: a large-scale hierarchical image database. IEEE Conference on Computer Vision and Pattern Recognition. IEEE. https:\/\/doi.org\/10.1109\/CVPR.2009.5206848","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"12052_CR16","doi-asserted-by":"publisher","first-page":"1384","DOI":"10.3390\/diagnostics11081384","volume":"11","author":"Y Dai","year":"2021","unstructured":"Dai Y, Gao Y, Liu F (2021) TransMed: transformers advance multi-modal medical image classification. Diagnostics (Basel) 11:1384","journal-title":"Diagnostics (Basel)"},{"key":"12052_CR17","doi-asserted-by":"publisher","unstructured":"He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. IEEE Conference on Computer Vision and Pattern Recognition. IEEE. https:\/\/doi.org\/10.1109\/CVPR.2016.90","DOI":"10.1109\/CVPR.2016.90"},{"key":"12052_CR18","unstructured":"Vaswani A, Shazeer N, Parmar N et al (2017) Attention is all you need. Proceedings of the 31st International Conference on Neural Information Processing Systems. Curran Associates Inc."},{"key":"12052_CR19","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1002\/1097-0142(1950)3:1<32::AID-CNCR2820030106>3.0.CO;2-3","volume":"3","author":"WJ Youden","year":"1950","unstructured":"Youden WJ (1950) Index for rating diagnostic tests. Cancer 3:32\u201335","journal-title":"Cancer"},{"key":"12052_CR20","doi-asserted-by":"crossref","unstructured":"Bluemke DA, Moy L, Bredella MA et al (2020) Assessing radiology research on artificial intelligence: a brief guide for authors, reviewers, and readers\u2014from the radiology editorial board. Radiology 294:487\u2013489","DOI":"10.1148\/radiol.2019192515"},{"key":"12052_CR21","doi-asserted-by":"publisher","first-page":"990","DOI":"10.1016\/j.joca.2011.05.004","volume":"19","author":"DJ Hunter","year":"2011","unstructured":"Hunter DJ, Guermazi A, Lo GH et al (2011) Evolution of semi-quantitative whole joint assessment of knee OA: MOAKS (MRI Osteoarthritis Knee Score). Osteoarthritis Cartilage 19:990\u20131002","journal-title":"Osteoarthritis Cartilage"},{"key":"12052_CR22","doi-asserted-by":"publisher","first-page":"1552","DOI":"10.3390\/app11041552","volume":"11","author":"P Krakowski","year":"2021","unstructured":"Krakowski P, Karpi\u0144ski R, Jojczuk M, Nogalska A, Jonak J (2021) Knee MRI underestimates the grade of cartilage lesions. Appl Sci 11:1552","journal-title":"Appl Sci"},{"key":"12052_CR23","doi-asserted-by":"publisher","first-page":"180091","DOI":"10.1148\/ryai.2019180091","volume":"1","author":"F Liu","year":"2019","unstructured":"Liu F, Guan B, Zhou Z et al (2019) Fully automated diagnosis of anterior cruciate ligament tears on knee MR images by using deep learning. Radiol Artif Intell 1:180091","journal-title":"Radiol Artif Intell"},{"key":"12052_CR24","doi-asserted-by":"crossref","unstructured":"Xue Y, Yang S, Sun W et al (2024) Approaching expert-level accuracy for differentiating ACL tear types on MRI with deep learning. Sci Rep 14:938","DOI":"10.1038\/s41598-024-51666-8"},{"key":"12052_CR25","doi-asserted-by":"publisher","unstructured":"Ying M, Wang Y, Yang K, Wang H, Liu X (2024) A deep learning knowledge distillation framework using knee MRI and arthroscopy data for meniscus tear detection. Front Bioeng Biotechnol 11. https:\/\/doi.org\/10.3389\/fbioe.2023.1326706","DOI":"10.3389\/fbioe.2023.1326706"},{"key":"12052_CR26","doi-asserted-by":"crossref","unstructured":"Tack A, Shestakov A, L\u00fcdke D, Zachow S (2021) A multi-task deep learning method for detection of meniscal tears in MRI data from the osteoarthritis initiative database. Front Bioeng Biotechnol 9:747217","DOI":"10.3389\/fbioe.2021.747217"},{"key":"12052_CR27","doi-asserted-by":"publisher","first-page":"64","DOI":"10.1016\/j.ejmp.2021.02.010","volume":"83","author":"B Rizk","year":"2021","unstructured":"Rizk B, Brat H, Zille P et al (2021) Meniscal lesion detection and characterization in adult knee MRI: A deep learning model approach with external validation. Phys Med 83:64\u201371","journal-title":"Phys Med"},{"key":"12052_CR28","doi-asserted-by":"publisher","first-page":"8394","DOI":"10.1007\/s00330-022-08923-z","volume":"32","author":"A Tran","year":"2022","unstructured":"Tran A, Lassalle L, Zille P et al (2022) Deep learning to detect anterior cruciate ligament tear on knee MRI: multi-continental external validation. Eur Radiol 32:8394\u20138403","journal-title":"Eur Radiol"},{"key":"12052_CR29","doi-asserted-by":"publisher","unstructured":"Herpe G, Vesoul T, Zille P et al (2025) Impact of AI assistance on radiologist interpretation of knee MRI. Eur Radiol. https:\/\/doi.org\/10.1007\/s00330-025-11820-w","DOI":"10.1007\/s00330-025-11820-w"},{"key":"12052_CR30","doi-asserted-by":"publisher","first-page":"e2431639","DOI":"10.2214\/AJR.24.31639","volume":"223","author":"CH Savage","year":"2024","unstructured":"Savage CH, Tanwar M, Elkassem AA et al (2024) Prospective evaluation of artificial intelligence triage of intracranial hemorrhage on noncontrast head CT examinations. AJR Am J Roentgenol 223:e2431639","journal-title":"AJR Am J Roentgenol"}],"container-title":["European Radiology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00330-025-12052-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00330-025-12052-8","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00330-025-12052-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,30]],"date-time":"2026-03-30T15:20:08Z","timestamp":1774884008000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00330-025-12052-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,17]]},"references-count":30,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2026,4]]}},"alternative-id":["12052"],"URL":"https:\/\/doi.org\/10.1007\/s00330-025-12052-8","relation":{},"ISSN":["1432-1084"],"issn-type":[{"value":"1432-1084","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,17]]},"assertion":[{"value":"14 July 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 August 2025","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 September 2025","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 October 2025","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Compliance with ethical standards"}},{"value":"The scientific guarantor of this publication is Sven Nebelung.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Guarantor"}},{"value":"The authors of this manuscript declare no relationships with any companies whose products or services may be related to the subject matter of the article.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"No complex statistical methods were necessary for this paper.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Statistics and biometry"}},{"value":"This retrospective study was conducted in accordance with local data protection regulations and the principles outlined in the Declaration of Helsinki. After approval by the local Ethical Committee (Medical Faculty, RWTH Aachen University (Germany): EK 22-319), the requirement for individual informed consent was waived.","order":5,"name":"Ethics","group":{"name":"EthicsHeading","label":"Informed consent"}},{"value":"Institutional Review Board approval was obtained.","order":6,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical approval"}},{"value":"No subject or cohort overlap with previous studies.","order":7,"name":"Ethics","group":{"name":"EthicsHeading","label":"Study subjects or cohorts overlap"}},{"order":8,"name":"Ethics","group":{"name":"EthicsHeading","label":"Methodology"}}]}}