{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,29]],"date-time":"2026-10-29T03:48:48Z","timestamp":1793245728495,"version":"4.5.0"},"reference-count":39,"publisher":"American Medical Association (AMA)","issue":"8","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["JAMA Netw Open"],"abstract":"\n Importance<\/jats:title>\n Adolescent idiopathic scoliosis (AIS) is the most common pediatric spinal disorder. Routine physical examinations by trained personnel are critical to diagnose severity and monitor curve progression in AIS. In the presence of concerning malformation, radiographs are necessary for diagnosis or follow-up, guiding further management, such as bracing correction for moderate malformation and spine surgery for severe malformation. If left unattended, progressive deterioration occurs in two-thirds of patients, leading to significant health concerns for growing children.<\/jats:p>\n <\/jats:sec>\n \n Objective<\/jats:title>\n To assess the ability of an open platform application (app) using a validated deep learning model to classify AIS severity and curve type, as well as identify progression.<\/jats:p>\n <\/jats:sec>\n \n Design, Setting, and Participants<\/jats:title>\n This diagnostic study was performed with data from radiographs and smartphone photographs of the backs of adolescent patients at spine clinics. The ScolioNets deep learning model was developed and validated in a prospective training cohort, then incorporated and tested in the AlignProCARE open platform app in 2022. Ground truths (GTs) included severity, curve type, and progression as manually annotated by 2 experienced spine specialists based on the radiographic examinations of the participants\u2019 spines. The GTs and app results were blindly compared with another 2 spine surgeons\u2019 assessments of unclothed back appearance. Data were analyzed from October 2022 to February 2023.<\/jats:p>\n <\/jats:sec>\n \n Exposure<\/jats:title>\n Acquisitions of unclothed back photographs using a mobile app.<\/jats:p>\n <\/jats:sec>\n \n Main Outcomes and Measures<\/jats:title>\n Outcomes of interest were classification of AIS severity and progression. Quantitative statistical analyses were performed to assess the performance of the deep learning model in classifying the deformity as well as in distinguishing progression during 6-month follow-up.<\/jats:p>\n <\/jats:sec>\n \n Results<\/jats:title>\n The training data set consisted of 1780 patients (1295 [72.8%] female; mean [SD] age, 14.3 [3.3] years), and the prospective testing data sets consisted of 378 patients (279 [73.8%] female; mean [SD] age, 14.3 [3.8] years) and 376 follow-ups (294 [78.2%] female; mean [SD] age, 15.6 [2.9] years). The model recommended follow-up with an area under receiver operating characteristic curve (AUC) of 0.839 (95% CI, 0.789-0.882) and considering surgery with an AUC of 0.902 (95% CI, 0.859-0.936), while showing good ability to distinguish among thoracic (AUC, 0.777 [95% CI, 0.745-0.808]), thoracolumbar or lumbar (AUC, 0.760 [95% CI, 0.727-0.791]), or mixed (AUC, 0.860 [95% CI, 0.834-0.887]) curve types. For follow-ups, the model distinguished participants with or without curve progression with an AUC of 0.757 (95% CI, 0.630-0.858). Compared with both surgeons, the model could recognize severities and curve types with a higher sensitivity (eg, sensitivity for recommending follow-up: model, 84.88% [95% CI, 75.54%-91.70%]; senior surgeon, 44.19%; junior surgeon, 62.79%) and negative predictive values (NPVs; eg, NPV for recommending follow-up: model, 89.22% [95% CI, 84.25%-93.70%]; senior surgeon, 71.76%; junior surgeon, 79.35%). For distinguishing curve progression, the sensitivity and NPV were comparable with the senior surgeons (sensitivity, 63.33% [95% CI, 43.86%-80.87%] vs 77.42%; NPV, 68.57% [95% CI, 56.78%-78.37%] vs 72.00%). The junior surgeon reported an inability to identify curve types and progression by observing the unclothed back alone.<\/jats:p>\n <\/jats:sec>\n \n Conclusions<\/jats:title>\n This diagnostic study of adolescent patients screened for AIS found that the deep learning app had the potential for out-of-hospital accessible and radiation-free management of children with scoliosis, with comparable performance as spine surgeons experienced in AIS management.<\/jats:p>\n <\/jats:sec>","DOI":"10.1001\/jamanetworkopen.2023.30617","type":"journal-article","created":{"date-parts":[[2023,8,23]],"date-time":"2023-08-23T11:36:33Z","timestamp":1692790593000},"page":"e2330617","source":"Crossref","is-referenced-by-count":66,"title":["Deep Learning Model to Classify and Monitor Idiopathic Scoliosis in Adolescents Using a Single Smartphone Photograph"],"prefix":"10.1001","volume":"6","author":[{"given":"Teng","family":"Zhang","sequence":"first","affiliation":[{"name":"Digital Health Laboratory, School of Clinical Medicine, Faculty of Medicine, The University of Hong Kong, Hong Kong Special Administrative Region, China"},{"name":"Department of Orthopaedics and Traumatology, The University of Hong Kong, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chuang","family":"Zhu","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yongkang","family":"Zhao","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Moxin","family":"Zhao","sequence":"additional","affiliation":[{"name":"Digital Health Laboratory, School of Clinical Medicine, Faculty of Medicine, The University of Hong Kong, Hong Kong Special Administrative Region, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhihao","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ruoning","family":"Song","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nan","family":"Meng","sequence":"additional","affiliation":[{"name":"Digital Health Laboratory, School of Clinical Medicine, Faculty of Medicine, The University of Hong Kong, Hong Kong Special Administrative Region, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alisha","family":"Sial","sequence":"additional","affiliation":[{"name":"SpineLabs, St George and Sutherland Clinical School, University of New South Wales, Sydney, Australia"},{"name":"Spine Service, Department of Orthopaedic Surgery, St George Hospital Campus, Sydney, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ashish","family":"Diwan","sequence":"additional","affiliation":[{"name":"SpineLabs, St George and Sutherland Clinical School, University of New South Wales, Sydney, Australia"},{"name":"Spine Service, Department of Orthopaedic Surgery, St George Hospital Campus, Sydney, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jun","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jason P. Y.","family":"Cheung","sequence":"additional","affiliation":[{"name":"Digital Health Laboratory, School of Clinical Medicine, Faculty of Medicine, The University of Hong Kong, Hong Kong Special Administrative Region, China"},{"name":"Department of Orthopaedics and Traumatology, The University of Hong Kong, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"10","published-online":{"date-parts":[[2023,8,23]]},"reference":[{"issue":"2","key":"zoi230882r1","doi-asserted-by":"publisher","first-page":"128","DOI":"10.1016\/j.rehab.2012.01.003","article-title":"Pathogenesis of idiopathic scoliosis: a review.","volume":"55","author":"de S\u00e8ze","year":"2012","journal-title":"Ann Phys Rehabil Med"},{"issue":"5","key":"zoi230882r2","doi-asserted-by":"publisher","first-page":"825","DOI":"10.1016\/j.spinee.2015.01.019","article-title":"A population-based cohort study of 394,401 children followed for 10 years exhibits sustained effectiveness of scoliosis screening.","volume":"15","author":"Fong","year":"2015","journal-title":"Spine J"},{"issue":"17","key":"zoi230882r3","doi-asserted-by":"publisher","first-page":"1607","DOI":"10.1097\/BRS.0b013e3181c7cb8c","article-title":"Clinical effectiveness of school screening for adolescent idiopathic scoliosis: a large population-based retrospective cohort study.","volume":"35","author":"Luk","year":"2010","journal-title":"Spine (Phila Pa 1976)"},{"issue":"14","key":"zoi230882r4","doi-asserted-by":"publisher","DOI":"10.2106\/JBJS.20.00775","article-title":"Impact of COVID-19 on orthopaedic and trauma service: an epidemiological study.","volume":"102","author":"Wong","year":"2020","journal-title":"J Bone Joint Surg Am"},{"issue":"4","key":"zoi230882r5","doi-asserted-by":"publisher","first-page":"811","DOI":"10.3174\/ajnr.A4173","article-title":"Systematic literature review of imaging features of spinal degeneration in asymptomatic populations.","volume":"36","author":"Brinjikji","year":"2015","journal-title":"AJNR Am J Neuroradiol"},{"issue":"4","key":"zoi230882r6","doi-asserted-by":"publisher","first-page":"629","DOI":"10.1016\/j.rcl.2012.04.014","article-title":"Imaging the intervertebral disk: age-related changes, herniations, and radicular pain.","volume":"50","author":"Del Grande","year":"2012","journal-title":"Radiol Clin North Am"},{"issue":"1","key":"zoi230882r7","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s11832-016-0713-0","article-title":"EOS biplanar x-ray imaging: concept, developments, benefits, and limitations.","volume":"10","author":"Melhem","year":"2016","journal-title":"J Child Orthop"},{"key":"zoi230882r8","doi-asserted-by":"publisher","first-page":"38287","DOI":"10.1109\/Access.6287639","article-title":"Learning-based coronal spine alignment prediction using smartphone-acquired scoliosis radiograph images.","volume":"9","author":"Zhang","year":"2021","journal-title":"IEEE Access"},{"key":"zoi230882r9","doi-asserted-by":"publisher","first-page":"124596","DOI":"10.1109\/Access.6287639","article-title":"An automated and accurate spine curve analysis system.","volume":"7","author":"Chen","year":"2019","journal-title":"IEEE Access"},{"key":"zoi230882r10","doi-asserted-by":"publisher","DOI":"10.1155\/2019\/6357171","article-title":"Cobb angle measurement of spine from x-ray images using convolutional neural network.","volume":"2019","author":"Horng","year":"2019","journal-title":"Comput Math Methods Med"},{"issue":"6","key":"zoi230882r11","doi-asserted-by":"publisher","first-page":"621","DOI":"10.1097\/00004032-199406000-00002","article-title":"Projecting the lifetime risk of cancer from exposure to diagnostic ionizing radiation for adolescent idiopathic scoliosis.","volume":"66","author":"Levy","year":"1994","journal-title":"Health Phys"},{"issue":"16","key":"zoi230882r12","doi-asserted-by":"publisher","first-page":"2052","DOI":"10.1097\/00007632-200008150-00009","article-title":"Breast cancer mortality after diagnostic radiography: findings from the U.S. Scoliosis Cohort Study.","volume":"25","author":"Doody","year":"2000","journal-title":"Spine (Phila Pa 1976)"},{"issue":"2","key":"zoi230882r13","doi-asserted-by":"publisher","first-page":"251","DOI":"10.1097\/01241398-200003000-00023","article-title":"The risk of carcinogenesis from radiographs to pediatric orthopaedic patients.","volume":"20","author":"Bone","year":"2000","journal-title":"J Pediatr Orthop"},{"issue":"3","key":"zoi230882r14","doi-asserted-by":"publisher","first-page":"271","DOI":"10.1097\/00001648-199805000-00010","article-title":"Adverse reproductive outcomes among women exposed to low levels of ionizing radiation from diagnostic radiography for adolescent idiopathic scoliosis.","volume":"9","author":"Goldberg","year":"1998","journal-title":"Epidemiology"},{"issue":"5","key":"zoi230882r15","doi-asserted-by":"publisher","first-page":"559","DOI":"10.1001\/jama.289.5.559","article-title":"Health and function of patients with untreated idiopathic scoliosis: a 50-year natural history study.","volume":"289","author":"Weinstein","year":"2003","journal-title":"JAMA"},{"issue":"2","key":"zoi230882r16","first-page":"135","article-title":"CNN-based spine and cobb angle estimator using moire images.","volume":"5","author":"Choi","year":"2017","journal-title":"IIEEJ Trans Image Electronics Visual Computing"},{"key":"zoi230882r17","doi-asserted-by":"publisher","first-page":"390","DOI":"10.1038\/s42003-019-0635-8","article-title":"Development and validation of deep learning algorithms for scoliosis screening using back images.","volume":"2","author":"Yang","year":"2019","journal-title":"Commun Biol"},{"key":"zoi230882r18","doi-asserted-by":"publisher","DOI":"10.1016\/j.eclinm.2021.101252","article-title":"An artificial intelligence powered platform for auto-analyses of spine alignment irrespective of image quality with prospective validation.","volume":"43","author":"Meng","year":"2022","journal-title":"EClinicalMedicine"},{"issue":"3","key":"zoi230882r19","doi-asserted-by":"publisher","first-page":"433","DOI":"10.14444\/7057","article-title":"Remote virtual spinal evaluation in the era of COVID-19.","volume":"14","author":"Yoon","year":"2020","journal-title":"Int J Spine Surg"},{"key":"zoi230882r20","doi-asserted-by":"publisher","first-page":"81","DOI":"10.1016\/j.jot.2018.09.005","article-title":"Spinal phantom comparability study of Cobb angle measurement of scoliosis using digital radiographic imaging.","volume":"15","author":"Chung","year":"2018","journal-title":"J Orthop Translat"},{"issue":"6","key":"zoi230882r21","doi-asserted-by":"publisher","first-page":"815","DOI":"10.2106\/00004623-199506000-00001","article-title":"Effectiveness of treatment with a brace in girls who have adolescent idiopathic scoliosis: a prospective, controlled study based on data from the Brace Study of the Scoliosis Research Society.","volume":"77","author":"Nachemson","year":"1995","journal-title":"J Bone Joint Surg Am"},{"issue":"1","key":"zoi230882r22","doi-asserted-by":"publisher","first-page":"51","DOI":"10.1186\/s12891-017-1423-6","article-title":"The association of lumbar curve magnitude and spinal range of motion in adolescent idiopathic scoliosis: a cross-sectional study.","volume":"18","author":"Eyvazov","year":"2017","journal-title":"BMC Musculoskelet Disord"},{"key":"zoi230882r23","doi-asserted-by":"publisher","DOI":"10.1016\/j.eclinm.2021.101220","article-title":"Application of deep learning upon spinal radiographs to predict progression in adolescent idiopathic scoliosis at first clinic visit.","volume":"42","author":"Wang","year":"2021","journal-title":"EClinicalMedicine"},{"issue":"6","key":"zoi230882r24","doi-asserted-by":"publisher","first-page":"1343","DOI":"10.2106\/JBJS.I.01142","article-title":"Brace wear control of curve progression in adolescent idiopathic scoliosis.","volume":"92","author":"Katz","year":"2010","journal-title":"J Bone Joint Surg Am"},{"issue":"4","key":"zoi230882r26","doi-asserted-by":"publisher","first-page":"427","DOI":"10.1016\/j.ipm.2009.03.002","article-title":"A systematic analysis of performance measures for classification tasks.","volume":"45","author":"Sokolova","year":"2009","journal-title":"Inf Process Manage"},{"issue":"2","key":"zoi230882r27","doi-asserted-by":"publisher","first-page":"753","DOI":"10.1109\/TKDE.2020.2986749","article-title":"Linear approximation of F-measure for the performance evaluation of classification algorithms on imbalanced data sets.","volume":"34","author":"Wong","year":"2022","journal-title":"IEEE T Knowl Data En"},{"key":"zoi230882r28","doi-asserted-by":"publisher","first-page":"48","DOI":"10.1016\/j.neucom.2021.03.091","article-title":"A review on the attention mechanism of deep learning.","volume":"452","author":"Niu","year":"2021","journal-title":"Neurocomputing"},{"issue":"4","key":"zoi230882r34","doi-asserted-by":"publisher","first-page":"990","DOI":"10.1007\/s00586-021-06860-x","article-title":"The smartphone as a tool to screen for scoliosis, applicable by everyone.","volume":"31","author":"van West","year":"2022","journal-title":"Eur Spine J"},{"issue":"8","key":"zoi230882r35","doi-asserted-by":"publisher","first-page":"e72","DOI":"10.1097\/BPO.0b013e31826bb109","article-title":"Validation of a scoliometer smartphone app to assess scoliosis.","volume":"32","author":"Franko","year":"2012","journal-title":"J Pediatr Orthop"},{"issue":"6","key":"zoi230882r36","doi-asserted-by":"publisher","DOI":"10.1001\/jamanetworkopen.2022.18348","article-title":"Association of children\u2019s hospital status with value for common surgical conditions.","volume":"5","author":"Raval","year":"2022","journal-title":"JAMA Netw Open"},{"issue":"2","key":"zoi230882r37","doi-asserted-by":"publisher","DOI":"10.1001\/jamanetworkopen.2021.47447","article-title":"Prevalence, cost, and variation in cost of pediatric hospitalizations in Ontario, Canada.","volume":"5","author":"Gill","year":"2022","journal-title":"JAMA Netw Open"},{"key":"zoi230882r38","doi-asserted-by":"publisher","first-page":"15030","DOI":"10.1038\/nrdp.2015.30","article-title":"Adolescent idiopathic scoliosis.","volume":"1","author":"Cheng","year":"2015","journal-title":"Nat Rev Dis Primers"},{"issue":"3","key":"zoi230882r39","doi-asserted-by":"publisher","DOI":"10.7759\/cureus.13944","article-title":"Mobile application for scoliosis screening using a standard 2D digital camera.","volume":"13","author":"Akazawa","year":"2021","journal-title":"Cureus"},{"key":"zoi230882r25","author":"Lin","year":"2021"},{"key":"zoi230882r31","author":"Desai","year":"2020"},{"key":"zoi230882r29","doi-asserted-by":"crossref","unstructured":"Fukui? H, Hirakawa? T, Yamashita? T, Fujiyoshi? H. Attention branch network: learning of attention mechanism for visual explanation.? arXiv. Preprint posted online December 25, 2018. doi:10.1109\/CVPR.2019.01096","DOI":"10.1109\/CVPR.2019.01096"},{"key":"zoi230882r30","doi-asserted-by":"crossref","unstructured":"Zhou? B, Khosla? A, Lapedriza? A, Oliva? A, Torralba? A. Learning deep features for discriminative localization.? arXiv. Preprint posted online December 14, 2015. doi:10.1109\/CVPR.2016.319","DOI":"10.1109\/CVPR.2016.319"},{"key":"zoi230882r32","doi-asserted-by":"crossref","unstructured":"Jalwana? MAAK, Akhtar? N, Bennamoun? M, Mian? A. CAMERAS: enhanced resolution and sanity preserving class activation mapping for image saliency. arXiv. Preprint posted online June 20, 2021. doi:10.1109\/CVPR46437.2021.01606","DOI":"10.1109\/CVPR46437.2021.01606"},{"key":"zoi230882r33","doi-asserted-by":"crossref","unstructured":"Wang? H, Wang? Z, Du? M, . Score-CAM: score-weighted visual explanations for convolutional neural networks.? arXiv. Preprint posted online October 3, 2019. doi:10.1109\/CVPRW50498.2020.00020\/arXiv.1910.01279","DOI":"10.1109\/CVPRW50498.2020.00020"}],"container-title":["JAMA Network Open"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/jamanetwork.com\/journals\/jamanetworkopen\/articlepdf\/2808701\/zhang_2023_oi_230882_1692134969.01914.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,23]],"date-time":"2023-08-23T11:36:37Z","timestamp":1692790597000},"score":1,"resource":{"primary":{"URL":"https:\/\/jamanetwork.com\/journals\/jamanetworkopen\/fullarticle\/2808701"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,8,23]]},"references-count":39,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2023,8,1]]}},"URL":"https:\/\/doi.org\/10.1001\/jamanetworkopen.2023.30617","relation":{},"ISSN":["2574-3805"],"issn-type":[{"value":"2574-3805","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,8,23]]}}}